Datasets:

64bits

/

lex_fridman_podcast_for_llm_vicuna

like 14

[ { "from": "human", "value": "So, you know, that's where it got going. So part of the thing that I think I'm calling elegance and beauty in this case, which was there, even with the pogo stick is maybe the efficiency. So letting the body do what it wants to do," }, { "from": "gpt", "value": "trying to discover the efficient movement. It's definitely more efficient. It also becomes easier to control in its own way because the physics are solving some of the problem itself. It's not like you have to do all this calculation and overpower the physics. The physics naturally inherently want to do the right thing. There can even be, you know, feedback mechanisms, stabilizing mechanisms that occur simply by virtue of the physics of the body. And it's, you know, not all in the computer or not even all in your mind as a person." }, { "from": "human", "value": "And there's something interesting in that melding. You were with Mark for many, many, many years, but you were there in this kind of legendary space of Leg Lab at MIT in the basement. All great things happen in the basement. Is there some memories, is there some memories" }, { "from": "gpt", "value": "from that time when in the basement?" }, { "from": "human", "value": "Is there some memory that you have because it's such cutting edge work" }, { "from": "gpt", "value": "in robotics and artificial intelligence? The memories, the distinctive lessons, I would say, I learned in that time period and that I think Mark was a great teacher of, was it's okay to pursue your interests, your curiosity, do something because you love it. You'll do it a lot better if you love it. That is a lasting lesson that I think we apply at the company still." }, { "from": "human", "value": "And it really is a core value. So the interesting thing is I get to, with people like Ross Tedrick and others, like the students that work at those robotics labs are like some of the happiest people I've ever met. I don't know what that is. I meet a lot of PhD students. A lot of them are kind of broken by the wear and tear of the process. But roboticists are, while they work extremely hard and work long hours, there's a happiness there. The only other group of people I've met like that are people that skydive a lot. For some reason, there's a deep fulfilling happiness. Maybe from a long period of struggle to get a thing to work and it works and there's a magic to it, I don't know exactly, because it's so fundamentally hands-on and you're bringing a thing to life." }, { "from": "gpt", "value": "I don't know what it is, but they're happy. We see, our attrition at the company is really low. People come and they love the pursuit. And I think part of that is that there's perhaps an actual connection to it. It's a little bit easier to connect when you have a robot that's moving around in the world and part of your goal is to make it move around in the world. You can identify with that. And this is one of the unique things about the kinds of robots we're building is this physical interaction lets you perhaps identify with it. So I think that is a source of happiness. I don't think it's unique to robotics. I think anybody also who is just pursuing something they love, you can identify. It's easier to work hard at it and be good at it and not everybody gets to find that. I do feel lucky in that way and I think we're lucky as an organization that we've been able to build a business around this and that keeps people engaged." }, { "from": "human", "value": "So if it's all right, let's link on Mark for a little bit longer, Mark Raybert. So he's a legend. He's a legendary engineer and roboticist. What have you learned about life about robotics, Mark?" }, { "from": "gpt", "value": "Through all the many years you worked with him. I think the most important lesson, which was have the courage of your convictions and do what you think is interesting. Be willing to try to find big, big problems to go after. And at the time, like at locomotion, especially in a dynamic machine, nobody had solved it. And that felt like a multi-decade problem to go after. And so have the courage to go after that because you're interested. Don't worry if it's gonna make money. That's been a theme. So that's really probably the most important lesson I think that I got from Mark." }, { "from": "human", "value": "How crazy is the effort of doing" }, { "from": "gpt", "value": "legged robotics at that time especially? Mark got some stuff to work starting from simple ideas. So maybe the other, another important idea that has really become a value of the company is try to simplify a thing to the core essence. And while Mark was showing videos of animals running across the savannah or climbing mountains, what he started with was a pogo stick because he was trying to reduce the problem to something that was manageable and getting the pogo stick to balance. Had in it the fundamental problems that if we solved those you could eventually extrapolate to something that galloped like a horse." }, { "from": "human", "value": "And so look for those simplifying principles." }, { "from": "gpt", "value": "How tough is the job of simplifying a robot? So I'd say in the early days, the thing that made Boston, the researchers at Boston Dynamics special is that we worked on figuring out what that central principle was and then building software or machines around that principle. And that was not easy in the early days. And it took real expertise in understanding the dynamics of motion and feedback control principles. How to build and with the computers at the time, how to build a feedback control algorithm that was simple enough that it could run in real time at a thousand Hertz and actually get that machine to work. And that was not something everybody was doing at that time. Now the world's changing now. And I think the approaches to controlling robots are going to change and they're going to become more broadly available. But at the time, there weren't many groups who could really sort of work at that principled level with both the software and make the hardware work. And I'll say one other thing about your sort of talking about what are the special things. The other thing was it's good to break stuff, you know. Use the robots, break them, repair them, fix and repeat, test, fix and repeat. And that's also a core principle that has become part of the company and it lets you be fearless in your work. Too often, if you are working with a very expensive robot, maybe one that you bought from somebody else or that you don't know how to fix, then you treat it with kit gloves and you can't actually make progress. You have to be able to break something." } ]

[ { "from": "human", "value": "And so I think that's been a principle. So just to linger on that psychologically, how do you deal with that? Because I remember I built a RC car that had some custom stuff, like compute on it, all that kind of stuff, cameras. And because I didn't sleep much, the code I wrote had an issue where it didn't stop the car and the car got confused and at full speed at like 20, 25 miles an hour slammed into a wall. And I just remember sitting there alone in a deep sadness, sort of full of regret, I think. Almost anger, but also sadness because you think about, well, these robots, especially for autonomous vehicles, like you should be taking safety very seriously even in these kinds of things, but just no good feelings. It made me more afraid probably to do this kind of experiments in the future. Perhaps the right way to have seen that is positively." }, { "from": "gpt", "value": "It depends if you could have built that car or just gotten another one, right? That would have been the approach. I remember when I got to grad school, I got some training about operating a lathe and a mill up in the machine shop and I could start to make my own parts. And I remember breaking some piece of equipment in the lab and then realizing, because maybe this was a unique part and I couldn't go buy it. And I realized, oh, I can just go make it. That was an enabling feeling. Then you're not afraid. Yeah, it might take time. It might take more work than you thought it was gonna be required to get this thing done, but you can just go make it. And that's freeing in a way that nothing else is." }, { "from": "human", "value": "And then realizing, bling feeling. You mentioned the feedback control, the dynamics. Sorry for the romantic question, but in the early days and even now, is the dynamics probably more appropriate for the early days?" }, { "from": "gpt", "value": "Is it more art or science? There's a lot of science around it and trying to develop scientific principles that let you extrapolate from one-legged machine to another, develop a core set of principles like a spring mass bouncing system, and then figure out how to apply that from a one-legged machine to a two or a four-legged machine. Those principles are really important and we're definitely a core part of our work. There's also, when we started to pursue humanoid robots, there was so much complexity in that machine that one of the benefits of the humanoid form is you have some intuition about how it should look while it's moving. And that's a little bit of an art, I think. Or maybe it's just tapping into a knowledge that you have deep in your body and then trying to express that in the machine, but that's an intuition that's a little bit more on the art side. Maybe it predates your knowledge. You know, before you have the knowledge of how to control it, you try to work through the art channel and humanoids make that available to you. If it had been a different shape, maybe you wouldn't have had the same intuition about it." }, { "from": "human", "value": "And humanoids make that available. So your knowledge about moving through the world is not made explicit to you. So you just, that's why it's art." }, { "from": "gpt", "value": "And it might, yeah, it might be hard to actually articulate exactly, you know? There's something about, and being a competitive athlete, there's something about seeing movement. You know, a coach, one of the greatest strengths a coach has is being able to see, you know, some little change in what the athlete is doing and then being able to articulate that to the athlete, you know, and then maybe even trying to say, and you should try to feel this. So there's something just in seeing. And again, you know, sometimes it's hard to articulate what it is you're seeing, but there's a, just perceiving the motion at a rate that is," }, { "from": "human", "value": "again, sometimes hard to put into words, you know? Yeah, I wonder how it is possible to achieve sort of truly elegant movement. You have a movie like Ex Machina. I'm not sure if you've seen it, but the main actress in that, who plays the AI robot, I think is a ballerina. I mean, just the natural elegance and the, I don't know, eloquence of movement. It's, it's, it looks efficient and easy and just, it looks right. It looks right is sort of the key, yeah. And then you look at, especially early robots, I mean, they're so cautious in the way they move that it's not the caution that looks wrong. It's something about the movement that looks wrong that feels like it's very inefficient, unnecessarily so." }, { "from": "gpt", "value": "And it's hard to put that into words exactly. I mean, it's- We think, and part of the reason why people are attracted to the machines we build is because the inherent dynamics of movement are closer to right. Because we try to use walking gates or we build a machine around this gate where you're trying to work with the dynamics of the machine instead of to stop them. Some of the early walking machines, you're essentially, you're really trying hard to not let them fall over. And so you're always stopping the tipping motion. And sort of the insight of dynamic stability in a legged machine is to go with it, let the tipping happen, let yourself fall, but then catch yourself with that next foot. And there's something about getting those physics to be expressed in the machine that people interpret as gene, lifelike, or elegant, or just natural looking. And so I think if you get the physics right, it also ends up being more efficient, likely. There's a benefit that it probably ends up being more stable in the long run. It could walk stably over a wider range of conditions." } ]

[ { "from": "human", "value": "And it's more beautiful and attractive at the same time. So how hard is it to get the humanoid robot Atlas to do some of the things it's recently been doing? Let's forget the flips and all of that. Let's just look at the running. Maybe you can correct me, but there's something about running. I mean, that's not careful at all. That's you're falling forward. You're jumping forward and are falling." }, { "from": "gpt", "value": "So how hard is it to get that right? Our first humanoid, we needed to deliver natural looking walking. We took a contract from the army. They wanted a robot that could walk naturally. They wanted to put a suit on the robot and be able to test it in a gas environment. And so they wanted the motion to be natural. And so our goal was a natural looking gate. It was surprisingly hard to get that to work environment. But we did build an early machine. We called it Petman prototype. It was the prototype before the Petman robot. And it had a really nice looking gate where it would stick the leg out. It would do heel strike first before it rolled onto the toes. You didn't land with a flat foot. You extended your leg a little bit. But even then it was hard to get the robot to walk where when you were walking that it fully extended its leg and essentially landed on an extended leg. And if you watch closely how you walk, you probably land on an extended leg but then you immediately flex your knee as you start to make that contact. And getting that all to work well took such a long time. In fact, I probably didn't really see the nice natural walking that I expected out of our humanoids until maybe last year. And the team was developing on our newer generation of Atlas some new techniques for developing a walking control algorithm. And they got that natural looking motion as sort of a byproduct of just a different process they were applying to developing the control. So that probably took 15 years, 10 to 15 years to sort of get that from the Petman prototype was probably in 2008 and what was it, 2022." }, { "from": "human", "value": "Last year that I think I saw a good walking on Atlas. If you could just like link on it what are some challenges of getting good walking? So is it, is this partially like a hardware like actuator problem? Is it the control? Is it the artistic element of just observing the whole system operating in different conditions together? I mean, is there some kind of interesting quirks or challenges you can speak to like the heel strike" }, { "from": "gpt", "value": "or all these kinds of things? Yeah, so one of the things that makes the like this straight leg a challenge is you're sort of up against a singularity a mathematical singularity where when your leg is fully extended it can't go further the other direction. There's only, you can only move in one direction. And that makes all of the calculations around how to produce torques at that joint or positions makes it more complicated. And so having all of the mathematics so it can deal with these singular configurations is one of many challenges that we face. And I'd say in the, in those earlier days again we were working with these really simplified models. So we're trying to boil all the physics of the complex human body into a simpler subsystem that we can more easily describe in mathematics. And sometimes those simpler subsystems don't have all of that complexity of the straight leg built into them. And so what's happened more recently is we're able to apply techniques that let us take the full physics of the robot into account and deal with some of those strange situations like the straight leg." }, { "from": "human", "value": "And I'd say in the leg. So is there a fundamental challenge here that it's maybe you can correct me but is it under actuated?" }, { "from": "gpt", "value": "Are you falling? Under actuated is the right word, right? You can't push the robot in any direction you want to, right? And so that is one of the hard problems" }, { "from": "human", "value": "of like a locomotion." }, { "from": "gpt", "value": "And you have to do that for natural movement. It's not necessarily required for natural movement. It's just required, you know, we don't have a gravity force that you can hook yourself onto to apply an external force in the direction you want at all times, right? The only external forces are being mediated through your feet and how they get mediated depend on how you place your feet. And, you know, you can't just, you know, God's hand can't reach down and push" }, { "from": "human", "value": "in any direction you want, you know, so. Is there some extra challenge to the fact that Alice is such a big robot?" }, { "from": "gpt", "value": "There is. Humanoid form is attractive in many ways, but it's also a challenge in many ways. You have this big upper body that has a lot of mass and inertia, and throwing that inertia around increases the complexity of maintaining balance. And as soon as you pick up something heavy in your arms, you've made that problem even harder. And so in the early work in the Leg Lab and in the early days at the company, we were pursuing these quadruped robots, which had a kind of built-in simplification. You had this big rigid body and then really light legs. So when you swing the legs, the leg motion didn't impact the body motion very much. All the mass and inertia was in the body. But when you have the humanoid, that doesn't work. You have big, heavy legs. You swing the legs, it affects everything else. And so dealing with all of that interaction" } ]

[ { "from": "human", "value": "does make the humanoid a much more complicated platform. And I also saw that at least recently, you've been doing more explicit modeling of the stuff you pick up. Yeah. Which is very, really interesting. So you have to model the shape, the weight distribution. I don't know, like you have to include that as part of the modeling, as part of the planning. Because, okay, so for people who don't know, so Atlas, at least in like a recent video, like throws a heavy bag, throws a bunch of stuff. So what's involved in picking up a thing, a heavy thing, and when that thing is a bunch of different non-standard things, I think it's also picked up like a barbell, and to be able to throw it in some cases," }, { "from": "gpt", "value": "what are some interesting challenges there? So we were definitely trying to show that the robot and the techniques we're applying to Atlas let us deal with heavy things in the world. Because if the robot's gonna be useful, it's actually gotta move stuff around. And that needs to be significant stuff. That's an appreciable portion of the body weight of the robot. And we also think this differentiates us from the other humanoid robot activities that you're seeing out there. Mostly they're not picking stuff up yet, and not heavy stuff anyway. But just like you or me, you need to anticipate that moment. You're reaching out to pick something up, and as soon as you pick it up, your center of mass is gonna shift. And if you're gonna turn in a circle, you have to take that inertia into count. And if you're gonna throw a thing, you've got all of that has to be included in the model of what you're trying to do. So the robot needs to have some idea or expectation of what that weight is, and then sort of predict. Think a couple of seconds ahead, how do I manage now my body plus this big heavy thing together to get, and still maintain balance, right? And so that's a big change for us. And I think the tools we've built are really allowing that to happen quickly now. Some of those motions that you saw in that most recent video, we were able to create in a matter of days. It used to be that it took six months to do anything new on the robot. And now we're starting to develop the tools and let us do that in a matter of days. We think that's really exciting. It means that the ability to create new behaviors" }, { "from": "human", "value": "for the robot is gonna be a quicker process. So being able to explicitly model new things" }, { "from": "gpt", "value": "that it might need to pick up, new types of things. And to some degree, you don't wanna have to pay too much attention to each specific thing, right? There's sort of a generalization here. Obviously, when you grab a thing, you have to conform your hand, your end effector to the surface of that shape. But once it's in your hands, it's probably just the mass and inertia that matter. And the shape may not be as important. And so in some ways, you wanna pay attention to that detailed shape. In others, you wanna generalize it and say, well, all I really care about is the center of mass of this thing," }, { "from": "human", "value": "especially if I'm gonna throw it up on that scaffolding. And it's easier if the body is rigid. What if there's some, doesn't it throw like a sandbag type thing?" }, { "from": "gpt", "value": "That tool bag had loose stuff in it. So it managed that. There are harder things that we haven't done yet. We could have had a big jointed thing" }, { "from": "human", "value": "or I don't know, a bunch of loose wire or rope rope. What about carrying another robot?" }, { "from": "gpt", "value": "How about that? Yeah, we haven't done that yet. Carry spot. I guess we did a little bit of a, we did a little skit around Christmas where we had two spots holding up another spot that was trying to put a bow on a tree." }, { "from": "human", "value": "So I guess we're doing that in a small way." }, { "from": "gpt", "value": "Carry spot." }, { "from": "human", "value": "Okay, that's pretty good. Let me ask the all important question. Do you know how much atlas can curl? I mean, for us humans, that's really one of the most fundamental questions you can ask another human being. Curl, bench." }, { "from": "gpt", "value": "It probably can't curl as much as we can yet. But a metric that I think is interesting is another way of looking at that strength is the box jump. So how high of a box can you jump onto? Question. And atlas, I don't know the exact height. It was probably a meter high or something like that. It was a pretty tall jump that atlas was able to manage when we last tried to do this. And I have video of my chief technical officer doing the same jump. And he really struggled. But the human, getting all the way on top of this box. But then atlas was able to do it. We're now thinking about the next generation of atlas. And we're probably gonna be in the realm of a person can't do it with the next generation. The robots, the actuators are gonna get stronger where it really is the case that at least some of these" }, { "from": "human", "value": "joints, some of these motions will be stronger. And to understand how high I can jump," }, { "from": "gpt", "value": "you probably had to do quite a bit of testing. Oh yeah, and there's lots of videos of it trying and failing and that's all. We don't always release those videos, but they're a lot of fun to look at." } ]

[ { "from": "human", "value": "So we'll talk a little bit about that. But can you talk to the jumping? Because you talked about the walking, it took a long time, many, many years to get the walking to be natural. But there's also really natural looking, robust, resilient jumping." }, { "from": "gpt", "value": "How hard is it to do the jumping? A little bit of a- And this stuff has really evolved rapidly in the last few years. The first time we did a somersault, there was a lot of manual iteration. What is the trajectory? How hard do you throw you? In fact, in these early days, I actually would, when I'd see early experiments that the team was doing, I might make suggestions about how to change the technique. Again, kind of borrowing from my own intuition about how backflips work. But frankly, they don't need that anymore. So in the early days, you had to iterate kind of in almost a manual way, trying to change these trajectories of the arms or the legs to try to get a successful backflip to happen. But more recently, we're running these model predictive control techniques where we're able to, the robot essentially can think in advance for the next second or two about how its motion is going to transpire. And you can solve for optimal trajectories to get from A to B. So this is happening in a much more natural way. And we're really seeing an acceleration happen in the development of these behaviors, again, partly due to these optimization techniques, sometimes learning techniques. So it's hard in that there's a lot of mathematics" }, { "from": "human", "value": "and behind it, but we're figuring that out. So you can do model predictive control for, I mean, I don't even understand what that looks like when the entire robot is in the air, flying and doing a backflip. Yeah." }, { "from": "gpt", "value": "I mean, in the air. But that's the cool part, right? So the physics, we can calculate physics pretty well using Newton's laws about how it's going to evolve over time. And the sick trick, which was a front somersault with a half twist is a good example, right? You saw the robot on various versions of that trick, I've seen it land in different configurations and it still manages to stabilize itself. And so what this model predictive control means is again, in real time, the robot is projecting ahead a second into the future and sort of exploring options. And if I move my arm a little bit more this way, how is that going to affect the outcome? And so it can do these calculations, many of them, and basically solve where, given where I am now, maybe I took off a little bit screwy from how I had planned," }, { "from": "human", "value": "I can adjust." }, { "from": "gpt", "value": "So you're adjusting in the air. Just on the fly. So the model predictive control lets you adjust on the fly. And of course, I think this is what people adapt as well. When we do it, even a gymnastics trick, we try to set it up so it's as close to the same every time, but we figured out how to do some adjustment on the fly. And now we're starting to figure out that the robots can do this adjustment on the fly as well, using these techniques." }, { "from": "human", "value": "In the air. I mean, it just feels, from a robotics perspective," }, { "from": "gpt", "value": "just surreal. Well, that's sort of, you talked about under-actuated, right? So when you're in the air, there's some things you can't change, right? You can't change the momentum while it's in the air, because you can't apply an external force or torque. And so the momentum isn't going to change. So how do you work within the constraint of that fixed momentum to still get from A to B," }, { "from": "human", "value": "where you want to be? That's really under-actuated. You're in the air. I mean, you become a drone for a brief moment in time." }, { "from": "gpt", "value": "No, you're not even a drone, because you can't hover. You can't hover. You're going to impact soon. Be ready." }, { "from": "human", "value": "Yeah. Are you considered like a hover-type thing or no? No, it's too much weight. I mean, it's just incredible. And just even to have the guts to try backflip for such a large body. That's wild." }, { "from": "gpt", "value": "Well, we definitely broke a few robots trying to hit it. But that's where the build-it-break-it-fix-it strategy comes in. You've got to be willing to break. And what ends up happening is you end up, by breaking the robot repeatedly, you find the weak points, and then you end up redesigning it" }, { "from": "human", "value": "so it doesn't break so easily next time, you know? Through the breaking process, you learn a lot, like a lot of lessons and then you keep improving not just how to make the backflip work but everything's just— And how to build the machine better. Yeah. I mean, is there something about just the guts to come up with an idea of saying," }, { "from": "gpt", "value": "you know what, let's try and make it to a backflip? Everything we just did. And how to build the machine better. Well, I think the courage to do a backflip in the first place and to not worry too much about the ridicule of somebody saying, why the heck are you doing backflips with robots? Because a lot of people have asked that, you know, why are you doing this?" } ]

[ { "from": "human", "value": "Because in this— Why go to the moon in this decade and do the other things, JFK? Not because it's easy, because it's hard. Yeah, exactly. Don't ask questions. Okay, so the jumping, I mean, there's a lot of incredible stuff. If we can just rewind a little bit to the DARPA Robotics Challenge in 2015, I think, which was for people who are familiar with the DARPA Challenges, it was first with autonomous vehicles, and there's a lot of interesting challenges around that. And the DARPA Robotics Challenge was when humanoid robots were tasked to do all kinds of manipulation, walking, driving a car, all these kinds of challenges with, if I remember correctly, sort of some slight capability to communicate with humans, but the communication was very poor." }, { "from": "gpt", "value": "So it basically has to be almost entirely autonomous. You could have periods where the communication was entirely interrupted and the robot had to be able to proceed. But you could provide some high-level guidance to the robot, basically low-bandwidth communications" }, { "from": "human", "value": "to steer it. I watched that challenge with kind of tears in my eyes eating popcorn. It was hard. But I wasn't personally losing hundreds of thousands, millions of dollars, and many years of incredible hard work by some of the most brilliant roboticists in the world. So that was why the tragic, that's why the tears came. So anyway, what have you, just looking back to that time, what have you learned from that experience? Maybe if you could describe what it was," }, { "from": "gpt", "value": "sort of the setup for people who haven't seen it. So there was a contest where a bunch of different robots were asked to do a series of tasks, some of those that you mentioned, drive a vehicle, get out, open a door, go identify a valve, shut a valve, use a tool to maybe cut a hole in a surface, and then crawl over some stairs and maybe some rough terrain. So it was, the idea was have a general purpose robot that could do lots of different things. Had to be mobility and manipulation, onboard perception. And there was a contest, which DARPA likes, at the time was running, sort of follow on to the grand challenge, which was let's try to push vehicle autonomy along, right? They encourage people to build autonomous cars. So they're trying to basically push an industry forward. And we were asked, our role in this was to build a humanoid at the time it was our sort of first generation Atlas robot. And we built maybe 10 of them. I don't remember the exact number. And DARPA distributed those to various teams that sort of won a contest, showed that they could program these robots, and then use them to compete against each other. And then other robots were introduced as well. Some teams built their own robots. Carnegie Mellon, for example, built their own robot. And all these robots competed to see who could sort of get through this maze of the fastest. And again, I think the purpose was to kind of push the whole industry forward. This may, we provided the robot and some baseline software, but we didn't actually compete as a participant where we were trying to drive the robot through this maze. We were just trying to support the other teams. It was humbling because it was really a hard task. And honestly, the robots, the tiers were because mostly the robots didn't do it. They fell down repeatedly. It was hard to get through this contest. Some did, and they were rewarded and won. But it was humbling because of just how hard, these tasks weren't all that hard. A person could have done it very easily, but it was really hard to get the robots to do it." }, { "from": "human", "value": "It was really, you know, you know. With the general nature of it, the variety of it. The variety." }, { "from": "gpt", "value": "And also, that I don't know if the tasks were of it." }, { "from": "human", "value": "The variety. Sort of the task in themselves helped us understand what is difficult and what is not. I don't know if that was obvious before the contest was designed. So you kind of try to figure that out. And I think Atlas is really a general robot platform. And it's perhaps not best suited for the specific tasks of that contest. Like for just, for example, probably the hardest task is not the driving of the car, but getting in and out of the car. And Atlas probably, you know, if you were to design a robot that can get into the car easily and get out easily, you probably would not make Atlas that particular car." }, { "from": "gpt", "value": "The robot was a little bit big to get in and out of that car. Right? It doesn't fit, yeah. This is the curse of a general purpose robot. That they're not perfect at any one thing. But they might be able to do a wide variety of things. And that is the goal at the end of the day. You know, I think we all want to build general purpose robots that can be used for lots of different activities. But it's hard. And the wisdom in building successful robots up until this point have been, go build a robot for a specific task and it'll do it very well. And as long as you control that environment, it'll operate perfectly. But robots need to be able to deal with uncertainty. If they're gonna be useful to us in the future, they need to be able to deal with unexpected situations. And that's sort of the goal of a general purpose or a multi-purpose robot. And that's just darn hard. And so some of the other is these curious little failures. Like I remember one of a robot, you know, the first time you start to try to push on the world with a robot, you forget that the world pushes back and will push you over if you're not ready for it. And the robot, you know, reached to grab the door handle. I think it missed the grasp of the door handle. It was expecting that its hand was on the door handle. And so when it tried to turn the knob, it just threw itself over. It didn't realize, Oh, I had missed the door handle. I didn't have, I didn't, I was expecting a force back from the door. It wasn't there. And then I lost my balance. So these little simple things that you and I would take totally for granted and deal with, the robots don't know how to deal with yet. And so you have to start to deal with all of those circumstances." } ]

[ { "from": "human", "value": "And then, I love it. A lot of us experienced this in a, even when sober, but drunk too. Sort of, you pick up a thing and expect it to be, what is it? Heavy. And it turns out to be light. Yeah, and then you woo. Oh yeah. And then, so the same, and I'm sure if your depth perception for whatever reason is screwed up, if you're drunk or some other reason, and then you think you're putting your hand on the table and you miss it." }, { "from": "gpt", "value": "I mean, it's the same kind of situation, but. And then you woo. There's a. Which is why you need to be able to predict forward just a little bit. And so that's where this model of predictive control stuff comes in. Predict forward what you think's gonna happen. And then if that does happen, you're in good shape. If something else happens, you better start predicting again." }, { "from": "human", "value": "So like, regenerate a plan. Yeah. When you don't. I mean, that also requires a very fast feedback loop of updating what your prediction, how it matches to the actual real world. Yeah, those things have to run pretty quickly. What's the challenge of running things pretty quickly? A thousand Hertz of acting and sensing quickly." }, { "from": "gpt", "value": "You know, there's a few different layers of that. You want at the lowest level, you like to run things typically at around a thousand Hertz, which means that, you know, at each joint of the robot, you're measuring position or force and then trying to control your actuator, whether it's a hydraulic or electric motor, trying to control the force coming out of that actuator. And you want to do that really fast. Something like a thousand Hertz. And that means you can't have too much calculation going on at that joint. But that's pretty manageable these days and it's fairly common. And then there's another layer that you're probably calculating, you know, maybe at a hundred Hertz, maybe 10 times slower, which is now starting to look at the overall body motion and thinking about the larger physics of the robot. And that means you can't have the, and then there's yet another loop that's probably happening a little bit slower, which is where you start to bring, you know, your perception and your vision and things like that. And so you need to run all of these loops sort of simultaneously. You do have to manage your computer time so that you can squeeze in all the calculations you need in real time in a very consistent way. And the amount of calculation we can do is increasing as computers get better, which means we can start to do more sophisticated calculations. I can have a more complex model doing my forward prediction. And that might allow me to do even better predictions as I get better and better. And it used to be, again, we had, you know, 10 years ago, we had to have pretty simple models that we were running, you know, at those fast rates because the computers weren't as capable about calculating forward with a sophisticated model." }, { "from": "human", "value": "But as computation gets better, we can do more of that. What about the actual pipeline of software engineering? How easy it is to keep updating Atlas, to do continuous development on it. So how many computers are on there?" }, { "from": "gpt", "value": "Is there a nice pipeline? It's an important part of building a team around it, which means, you know, you need to also have software tools, simulation tools, you know, so we have always made strong use of physics-based simulation tools to do some of this calculation, basically test it in simulation before you put it on the robot, but you also want the same code that you're running in simulation to be the same code you're running on the hardware. And so even getting to the point where it was the same code going from one to the other, we probably didn't really get that working until, you know, a few years, several years ago. But that was, you know, that was a bit of a milestone. And so you want to work, certainly, work these pipelines so that you can make it as easy as possible and have a bunch of people working in parallel, especially when, you know, we only have, you know, four of the Atlas robots, the modern Atlas robots at the company. And, you know, we probably have, you know, 40 developers. They're all trying to gain access to it. And so you need to share resources" }, { "from": "human", "value": "and use some of these, some of the software pipeline. Well, that's a really exciting step to be able to run the exact same code in simulation as on the actual robot. How hard is it to do realistic simulation, physics-based simulation of Atlas, such that, I mean, the dream is like, if it works in simulation, it works perfectly in reality." }, { "from": "gpt", "value": "How hard is it to sort of keep working on closing that gap? The root of some of our physics-based simulation tools really started at MIT. And we built some good physics-based modeling tools there. The early days of the company, we were trying to develop those tools as a commercial product. So we continued to develop them. It wasn't a particularly successful commercial product, but we ended up with some nice physics-based simulation tools so that when we started doing Legged Robotics again, we had a really nice tool to work with. And the things we paid attention to were things that weren't necessarily handled very well in the commercial tools you could buy off the shelf, like interaction with the world, like foot-ground contact. So trying to model those contact events well in a way that captured the important parts of the interaction was a really important element to get right and to also do in a way that was computationally feasible and could run fast. Because if your simulation runs too slow, then your developers are sitting around waiting for stuff to run and compile. So it's always about efficient fast operation as well. So that's been a big part of it. I think developing those tools in parallel to the development of the platform and trying to scale them has really been essential, I'd say, to us being able to assemble a team" } ]

[ { "from": "human", "value": "of people that could do this. Yeah, how to simulate contact, period. So foot-ground contact, but sort of for manipulation." }, { "from": "gpt", "value": "Because don't you want to model all kinds of surfaces? Yeah, so it will be even more complex with manipulation because there's a lot more going on, you know? And you need to capture, I don't know, things slipping and moving in your hand. It's a level of complexity that I think goes above foot-ground contact when you really start doing dexterous manipulation." }, { "from": "human", "value": "So there's challenges ahead still. So how far are we away from me being able to walk with Atlas in the sand along the beach and us both drinking a beer?" }, { "from": "gpt", "value": "So out of a can, out of a can, out of a can. Maybe Atlas could spill his beer because he's got nowhere to put it. Atlas could walk on the sand. So can it? I mean, you know, have we really had him out on the beach? Yeah, we take them outside often, you know, rocks, hills, that sort of thing, even just around our lab in Waltham. We probably haven't been on the sand, but I'm a- So soft surfaces. I don't doubt that we could deal with it. We might have to spend a little bit of time to sort of make that work, but we did take, we had to take Big Dog to Thailand years ago. And we did this great video of the robot walking in the sand, walking into the ocean up to, I don't know, its belly or something like that, and then turning around and walking out, all while playing some cool beach music. Great show, but then, you know, we didn't really clean the robot off, and the salt water was really hard on it. So, you know, we put it in a box, shipped it back. By the time it came back, we had some problems with Corogia." }, { "from": "human", "value": "So can it? Soft surfaces. I don't doubt it, years ago. So it's the salt, it's the salt water. It's not like- Salt stuff. It's not like sand getting into the components or something like this. But I'm sure if this is a big priority, you can make it waterproof." }, { "from": "gpt", "value": "Right, that just wasn't our goal at the time. Well, it's a personal goal of mind to it." }, { "from": "human", "value": "A personal goal of mind to it. Walk along the beach. But it's a human problem too. You get sand everywhere, it's just a jammed mess. So soft surfaces are okay. So, I mean, can we just link on the robotics challenge? There's a pile of like rubble there to walk over." }, { "from": "gpt", "value": "Is that's, how difficult is that task? In the early days of developing Big Dog, the loose rock was the epitome of the hard walking surface because you step down and then the rock and you had these little point feet on the robot and the rock can roll. And you have to deal with that last minute," }, { "from": "human", "value": "change in your foot placement. Yeah, so you step on the thing and that thing responds to you stepping on it." }, { "from": "gpt", "value": "Yeah, and it moves where your point of support is. And so it's really, that became kind of the essence of the test. And so that was the beginning of us starting to build rock piles in our parking lots. And we would actually build boxes full of rocks and bring them into the lab. And then we would have the robots walking across" }, { "from": "human", "value": "these boxes of rocks because that became the essential test. So you mentioned Big Dog. Can we maybe take a stroll through the history about the dynamics? So what and who is Big Dog? By the way, is who? Do you try not to anthropomorphize the robots? Do you try not to, do you try to remember that there, this is like the division I have because for me it's impossible. For me, there's a magic to the being that is a robot. It is not human, but it is the same magic that a living being has when it moves about the world is there in the robot. So I don't know what question I'm asking, but should I say what or who, I guess? Who is Big Dog?" }, { "from": "gpt", "value": "What is Big Dog? Well, I'll say to address the meta question, we don't try to draw hard lines around it being an it or a him or a her. It's okay, right? People, I think part of the magic of these kinds of machines is by nature of their organic movement of their dynamics. It's okay. We tend to want to identify with them. We tend to look at them and sort of attribute maybe feeling to that because we've only seen things that move like this that were alive. And so this is an opportunity. It means that you could have feelings for a machine and people have feelings for their cars. They get attracted to them, attached to them. So that inherently could be a good thing as long as we manage what that interaction is. So we don't put strong boundaries around this and ultimately think it's a benefit, but it also can be a bit of a curse because I think people look at these machines and they attribute a level of intelligence that the machines don't have. Why? Because again, they've seen things move like this that were living beings, which are intelligent. And so they want to attribute intelligence to the robots that isn't appropriate yet," }, { "from": "human", "value": "even though they move like an intelligent being. But you try to acknowledge that the anthropomorphization is there" }, { "from": "gpt", "value": "and try to, first of all, acknowledge that it's there. And have a little fun with it. You know, our most recent video, it's just kind of fun, you know, to look at the robot. We started off the video with Atlas kind of looking around for where the bag of tools was because the guy up on the scaffolding says, send me some tools and Atlas has to kind of look around and see where they are. And there's a little personality there that is fun. It's entertaining. It makes our jobs interesting. And I think in the long run, can enhance interaction between humans and robots in a way that isn't available to machines" } ]

[ { "from": "human", "value": "that don't move that way. You know, it's just kind of fun. This is something to me personally is very interesting. I happen to have a lot of legged robots. I hope to have a lot of spots in my possession. I'm interested in celebrating robotics and celebrating companies, and I also don't want to companies that do incredible stuff like Boston Dynamics and I, there's, you know, I'm a little crazy, and you said, you don't want to, you want to align, you want to help the company because I ultimately want a company that Boston Dynamics to succeed. And part of that, we'll talk about, you know, success kind of requires making money. And so the kind of stuff I'm particularly interested in may not be the thing that makes money in the short term. I can make an argument that it will in the long term, but the kind of stuff I've been playing with is a robust way of having the quadrupas, the robot dogs communicate in motion with their body movement. The same kind of stuff you do with a dog, but not hard-coded, but in a robust way, and be able to communicate excitement or fear, boredom, all these kinds of stuff. And I think as a base layer of function of behavior to add on top of a robot, I think that's a really powerful way to make the robot more usable for humans," }, { "from": "gpt", "value": "for whatever application. I think it's going to be really important. And it's a thing we're beginning to pay attention to. We really want to start, a differentiator for the company has always been, we really want the robot to work. We want it to be useful. Making it work at first meant the legged locomotion really works. It can really get around and it doesn't fall down. But beyond that, now it needs to be a useful tool. And our customers are, for example, factory owners, people who are running a process manufacturing facility. And the robot needs to be able to get through this complex facility in a reliable way, taking measurements really work. We need for people who are operating those robots to understand what the robots are doing. If the robot gets into needs help or is in trouble or something, it needs to be able to communicate. And a physical indication of some sort, so that a person looks at the robot and goes, oh, I know what that robot's doing. The robot's going to go take measurements of my vacuum pump with its thermal camera. You want to be able to indicate that. And we're even just, the robot's about to turn in front of you and maybe indicate that it's going to turn. And so you sort of see and can anticipate its motion. So this kind of communication is going to become more and more important. It wasn't sort of our starting point. But now the robots are really out in the world. And we have about a thousand of them out with customers right now. This layer of physical indication, I think is going to become more and more important. Robots don't be able to indicate that." }, { "from": "human", "value": "Hold on, we have about a thousand. We'll talk about where it goes, because there's a lot of interesting possibilities. But if you can return back to the origins of Boston Dynamics with, so that the more research, the R&D side, before we talk about how to build robots at scale." }, { "from": "gpt", "value": "So big dog, who's big dog? So the company started in 1992. And in probably 2003, I believe is when we took a contract from dark, so basically 10 years, 11 years. We weren't doing robotics. We did a little bit of robotics with Sony. They had IBO, their IBO robot. We were developing some software for that that kind of got us a little bit involved with robotics again. Then there's this opportunity to do a DARPA contract where they wanted to build a robot dog. And we won a contract to build that. And so that was the genesis of big dog. And it was a quadruped. And it was the first time we built a robot that had everything on board that you could actually take the robot out into the wild and operate it. So it had an onboard power plant. It had onboard computers. It had hydraulic actuators that needed to be cooled. So we had cooling systems built in. Everything integrated into the robot. And that was a pretty rough start, right? It was 10 years that we were not a robotics company. We were a simulation company. And then we had to build a robot in about a year. So that was a little bit of a rough transition." }, { "from": "human", "value": "I mean, can you just comment on the roughness of that transition? Because big dog, I mean, this is just big quadruped," }, { "from": "gpt", "value": "four legs robot. We built a few different versions of them. But the first one, the very earliest ones, didn't work very well. And we would take them out. And it was hard to get a go-kart engine driving a hydraulic pump. I was down with what it was. And having that all work while trying to get the robot to stabilize itself." }, { "from": "human", "value": "So what was the power plant? What was the engine? It seemed like my vague recollection. I don't know. It felt very loud and aggressive" }, { "from": "gpt", "value": "and kind of thrown together, is what kind of- Oh, it absolutely was, right? We weren't trying to design the best robot hardware at the time. And we wanted to buy an off-the-shelf engine. And so many of the early versions of big dog had literally go-kart engines or something like that. Usually- Are those gas powered? Are they actually powered two-stroke engines? And the reason why it was two-stroke is two-stroke engines are lighter weight. But they're also- And generally we didn't put mufflers on them because we're trying to save the weight, and we didn't care about the noise. And some of these things were horribly loud. But we're trying to manage weight because managing weight in a legged robot is always important because it has to carry everything." } ]

[ { "from": "human", "value": "Yeah. That said that thing was big." }, { "from": "gpt", "value": "Well, I've seen the videos of it. Yeah, well, I've seen the videos of- Yeah. The early versions stood about, I don't know, belly high, chest high. They probably weighed maybe a couple of hundred pounds. But over the course of probably five years, we were able to get that robot to really manage a remarkable level of rough terrain. So we started out with just walking on the flat, and then we started walking on rocks, and then inclines, and then mud, and slippery mud. And by the end of that program, we were convinced that legged locomotion in a robot could actually work. Because going into it, we didn't know that. We had built quadrupeds at MIT, but they used a giant hydraulic pump in the lab. They used a giant computer that was in the lab. They were always tethered to the lab. This was the first time something that was sort of self-contained walked around in the world and balanced. And the purpose was to prove to ourself that the legged locomotion could really work. And so Big Dog really cut that open for us. And it was the beginning of what became a whole series of robots. So once we showed to DARPA that you could make a legged robot that could work, there was a period at DARPA where robotics got really hot, and there was lots of different programs. And we were able to build other robots. We built other quadrupeds to hand like LS3, designed to carry heavy loads. We built Cheetah, which was designed to explore what are the limits to how fast you can run. We began to build sort of a portfolio of machines and software that let us build" }, { "from": "human", "value": "not just one robot, but a whole family of robots. To push the limits in all kinds of directions." }, { "from": "gpt", "value": "Yeah, and to discover those principles. You asked earlier about the art and science of a legged locomotion. We were able to develop principles of legged locomotion so that we knew how to build a small legged robot or a big one. So the leg length was now a parameter that we could play with. Payload was a parameter we could play with. So we built the LS3, which was an 800 pound robot designed to carry a 400 pound payload. And we learned the design rules, basically developed the design rules. How do you scale different robot systems to their terrain, to their walking speed, to their payload. So when was Spot born? Around 2012 or so. So again, almost 10 years into sort of a run with DARPA where we built a bunch of different quadrupeds. We had sort of a different thread where we started building humanoids. We saw that probably an end was coming where the government was gonna kind of back off from a lot of robotics investment. And in order to maintain progress, we just deduced that, well, we probably need to sell ourselves to somebody who wants to continue to invest in this area. And that was Google. And so at Google, we would meet regularly with Larry Page. And Larry just started asking us, well, what's your product gonna be? And the logical thing, the thing that we had the most history with that we wanted to continue developing was our quadrupeds. But we knew it needed to be smaller. We knew it couldn't have a gas engine. We thought it probably couldn't be hydraulically actuated. So that began the process of exploring if we could migrate to a smaller, electrically actuated robot." }, { "from": "human", "value": "And that was really the genesis of Spot thing with. So not a gas engine and the actuators are electric. Yes. Can you maybe comment on what it's like at Google working with Larry Page, having those meetings and thinking of what will a robot look like that could be built at scale?" }, { "from": "gpt", "value": "What like starting to think about a product? Larry always liked the toothbrush test. He wanted products that you used every day. What they really wanted was a consumer level product, something that would work in your house. We didn't think that was the right next thing to do because to be a consumer level product, cost is going to be very important. Probably needed to cost a few thousand dollars. And we were building these machines that cost hundreds of thousands of dollars, maybe a million dollars to build. Of course we were only building a 2, but we didn't see how to get all the way to this consumer level product. In a short amount of time. In a short amount of time. And he suggested that we make the robots really inexpensive. And part of our philosophy has always been build the best hardware you can. Make the machine operate well so that you're trying to solve, discover the hard problem that you don't know about. Don't make it harder by building a crappy machine basically. Build the best machine you can. There's plenty of hard problems to solve that are going to have to do with under actuated systems and balance. And so we wanted to build these high quality machines still. And we thought that was important for us to continue learning about really what was the important parts of that make robots work. And so there was a little bit of a philosophical difference there. And so ultimately that's why we're building robots for the industrial sector now. Because the industry can afford a more expensive machine because their productivity depends on keeping their factory going. And so if spot costs $100,000 or more that's not such a big expense to them. Whereas at the consumer level no one's going to buy a robot like that. And I think we might eventually get to a consumer level product that will be that cheap. But I think the path to getting there needs to go through these really nice machines" } ]

[ { "from": "human", "value": "so we can then learn how to simplify. So what can you say to the almost the engineering challenge of bringing down cost of a robot? So that presumably when you try to build the robot at scale that also comes into play. When you're trying to make money on a robot even in the industrial setting. But how interesting, how challenging of a thing is that? In particular probably new to an R&D company." }, { "from": "gpt", "value": "Yeah, I'm glad you brought that last part up. The transition from an R&D company to a commercial company that's the thing you worry about. Because you've got these engineers who love hard problems who want to figure out how to make robots work. And you don't know if you have engineers that want to work on the quality and reliability and costs that is ultimately required. And indeed we have brought on a lot of new people who are inspired by those problems. But the big takeaway lesson for me is we have good people. We have engineers who want to solve problems. And the quality and cost and manufacturability is just another kind of problem. And because they're so invested in what we're doing, they're interested in and will go work on those problems as well. And so I think we're managing that transition very well. In fact, I'm really pleased that, I mean, it's a huge undertaking by the way, right? So even having to get reliability to where it needs to be, we have to have fleets of robots that we're just operating 24 seven in our offices to go find those rare failures and eliminate them. It's just a totally different kind of activity than the research activity where you get it to work, you know, the one robot you have to work in a repeatable way, you know, at the high stakes demo. It's just very different." }, { "from": "human", "value": "But I think we're making remarkable progress I guess. So one of the cool things that got a chance to visit Boston Dynamics, and I mean, one of the things that's really cool is to see a large number of robots moving about. Because I think one of the things you notice in the research environment at MIT, for example, I don't think anyone ever has a working robot for a prolonged period of time. Exactly. So like most robots are just sitting there in a sad state of despair waiting to be born, brought to life for a brief moment of time. And just to have, I just remember there's a spot robot, just had like a cowboy hat on, it was just walking randomly for whatever reason. I don't even know. But there's a kind of sense of sentience to it because it doesn't seem like anybody was supervising it." }, { "from": "gpt", "value": "It was just doing its thing. It was just doing its thing. I'm gonna stop way short of the sentience. It is the case that if you come to our office today and walk around the hallways, you're gonna see a dozen robots just kind of walking around all the time. And that's really a reliability test for us. So we have these robots programmed to do autonomous missions, get up off their charging dock, walk around the building, collect data at a few different places and go sit back down. And we want that to be a very reliable process because that's what somebody who's running a brewery, a factory, that's what they need the robot to do. So we have to dog food our own robot. We have to test it in that way. And so on a weekly basis, we have robots that are accruing something like 1500 or maybe 2000 kilometers of walking and over a thousand hours of operation every week. And that's something that almost, I don't think anybody else in the world can do because hey, you have to have a fleet of robots to just accrue that much information. You have to be willing to dedicate it to that test." }, { "from": "human", "value": "And so that's the central in that way. That's how you get the reliability. That's how I get it. What about some of the cost cutting from the manufacturer side? What have you learned from the manufacturer side" }, { "from": "gpt", "value": "of the transition from R&D to- That's how we get it. We're still learning a lot there. We're learning how to cast parts instead of mill it all out of billet aluminum. We're learning how to get plastic molded parts. And we're learning about how to control that process so that you can build the same robot twice in a row. There's a lot to learn there. And we're only partway through that process. We've set up a manufacturing facility in Waltham. It's about a mile from our headquarters. And we're doing final assembly and test of both spots and stretches at that factory. And it's hard because to be honest, we're still iterating on the design of the robot as we find failures from these reliability tests, we need to go engineer changes. And those changes need to now be propagated to the manufacturing line. And that's a hard process, especially when you want to move as fast as we do. And that's been challenging. And it makes it, the folks who are working supply chain, who are trying to get the cheapest parts for us, kind of requires that you buy a lot of them to make them cheap. And then we go change the design from underneath them. And they're like, what are you doing? And so, you know, getting everybody on the same page here, that it, yep, we still need to move fast, but we also need to try to figure out how to reduce costs." }, { "from": "human", "value": "That's one of the challenges of this migration we're going through. And over the past few years, challenges to the supply chain, I imagine you've been a part of a bunch" }, { "from": "gpt", "value": "of stressful meetings. Yeah, things got more expensive and harder to get." } ]

[ { "from": "human", "value": "And yeah, so it's all been a challenge. Is there still room for simplification?" }, { "from": "gpt", "value": "Oh yeah, much more, much more. And, you know, these are really just the first generation of these machines. We're already thinking about what the next generation of Spot's going to look like. Spot was built as a platform. So you could put almost any sensor on it. You know, we provided data communications, mechanical connections, power connections. And, but for example, in the applications that we're excited about, where you're monitoring these factories for their health, for their health, there's probably a simpler machine that we could build that's really focused on that use case. And that's the difference between the general purpose machine or the platform versus the purpose-built machine. And so even though, even in the factory, we'd still like the robot to do lots of different tasks. If we really knew on day one that we're going to be operating in a factory with these three sensors in it, we would have it all integrated in a package that would be easier, more, less expensive, and more reliable. So we're contemplating building, you know," }, { "from": "human", "value": "a next generation of that machine. So we should mention that, so Spot, for people who are somehow not familiar, so is a yellow robotic dog, and has been featured in many dance videos. It also has gained an arm. So what can you say about the arm that Spot has? About the challenges of this design" }, { "from": "gpt", "value": "and the manufacture of it? We think the future of mobile robots is mobile manipulation. That's where, you know, in the past 10 years, it was getting mobility to work, getting the leg of locomotion to work. If you ask, what's the heart problem in the next 10 years? It's getting a mobile robot to do useful manipulation for you. And so we wanted Spot to have an arm to experiment with those problems. And the arm is almost as complex as the robot itself, you know, and it's an attachable payload. It has, you know, several motors and actuators and sensors. It has a camera in the end of its hand. So, you know, you can sort of see something, and the robot will control the motion of its hand to go pick it up autonomously. So in the same way the robot walks and balances, managing its own foot placement to stay balanced. We want manipulation to be mostly autonomous, where the robot, you indicate, okay, go grab that bottle, and then the robot will just go do it using the camera in its hand and then sort of closing in on the grasp. But it's a whole another complex robot on top of a complex-legged robot. And of course we made it, the hand look a little like a head, you know, because again we want it to be sort of identifiable. In the last year, a lot of our sales have been people who already have a robot" }, { "from": "human", "value": "now buying an arm to add to that robot. Oh, interesting. And so the arm is for sale." }, { "from": "gpt", "value": "Oh yeah, oh yeah." }, { "from": "human", "value": "It's an option. What's the interface like to work with the arm? Like is it pretty, so are they designed primarily, I guess just ask that question in general about robots from Boston Dynamics. Is it designed to be easily and efficiently operated remotely by a human being?" }, { "from": "gpt", "value": "Or is there also the capability to push towards autonomy? We want both. In the next version of the software that we release, which will be version 3.3, we're gonna offer the ability of, if you have an autonomous mission for the robot, we're gonna include the option that it can go through a door. Which means it's gonna have to have an arm and it's gonna have to use that arm to open the door. And so that'll be an autonomous manipulation task that you can program easily with the robot, strictly through, you know, we have a tablet interface. And so on the tablet, you know, you sort of see the view that Spot sees. You say, there's the door handle. You know the hinges are on the left and it opens in. The rest is up to you." }, { "from": "human", "value": "Take care of both of you. Take care of it. So it just takes care of everything." }, { "from": "gpt", "value": "Yeah. So we want, and for a task like opening doors, you can automate most of that. And we've automated a few other tasks. We had a customer who had a high powered breaker switch, essentially, it's an electric utility, Ontario power generation. And they have to, when they're gonna disconnect, you know, their power supply, right? That could be a gas generator. It could be a nuclear power plant. You know, from the grid, you have to disconnect this breaker switch. Well, as you can imagine, there's, you know, hundreds or thousands of amps and volts involved in this breaker switch. And it's a dangerous event because occasionally you'll get what's called an arc flash. As you just do this disconnect, the power, the sparks jump across and people die doing this. And so Ontario power generation used our Spot and the arm through the interface to operate this disconnect in an interactive way. And they showed it to us. And we were so excited about it and said, you know, I bet we can automate that task. And so we got some examples of that breaker switch. And I believe in the next generation of the software, now we're gonna deliver back to Ontario power generation. They're gonna be able to just point the robot at that breaker. They'll be out, they'll indicate that's the switch. There's sort of two actions you have to do. You have to flip up this little cover, press a button, then get a ratchet, stick it into a socket and literally unscrew this giant breaker switch. So there's a bunch of different tasks. And we basically automated them so that the human says, okay, there's the switch, go do that part. That's right. In an interact, that right there is the socket where you're gonna put your tool and you're gonna open it up. And so you can remotely sort of indicate this on the tablet" } ]

[ { "from": "human", "value": "and then the robot just does everything in between. And it does everything, all the coordinated movement of all the different actuators that includes the body" }, { "from": "gpt", "value": "and all of the body and all of the- Yeah, maintains its balance. It walks itself into position so it's within reach and the arm is in a position where it can do the whole task." }, { "from": "human", "value": "So it manages the whole body. So how does one become a big enough customer to request features? Because I personally want a robot that gets me a beer. I mean, that has to be like one of the most requests, I suppose, in the industrial setting. That's a non-alcoholic beverage of picking up objects" }, { "from": "gpt", "value": "and bringing the objects to you. We love working with customers who have challenging problems like this. And this one in particular, because we felt like what they were doing, A, it was a safety feature, B, we saw that the robot could do it because they teleoperated it the first time. Probably took them an hour to do it the first time, right? But the robot was clearly capable. And we thought, oh, this is a great problem for us to work on to figure out how to automate a manipulation task. And so we took it on not because we were gonna make a bunch of money from it in selling the robot back to them, but because it motivated us to go solve what we saw as the next logical step. But many of our customers, in fact, we try to, our bigger customers, typically ones who are gonna run a utility or a factory or something like that, we take that kind of direction from them. And if they're, especially if they're gonna buy 10 or 20 or 30 robots, and they say, I really need it to do this, well, that's exactly the right kind of problem that we wanna be working on." }, { "from": "human", "value": "And so- Note to self, by tense thoughts, and aggressively pushed for beer manipulation, I think it's fair to say it's notoriously difficult to make a lot of money as a robotics company. How can you make money as a robotics company? Can you speak to that? It seems that a lot of robotics companies fail. It's difficult to build robots. It's difficult to build robots at a low enough cost where customers, even the industrial setting, want to purchase them. And it's difficult to build robots that are useful, sufficiently useful. So what can you speak to? And Boston Dynamics has been successful" }, { "from": "gpt", "value": "for many years of finding a way to make money. Well, in the early days, of course, the money we made was from doing contract R&D work. And we made money, but we weren't growing and we weren't selling a product. And then we went through several owners who had a vision of not only developing advanced technology, but eventually developing products. And so both Google and SoftBank and now Hyundai had that vision and were willing to provide that investment. Now, our discipline is that we need to go find applications that are broad enough that you could imagine selling thousands of robots because it doesn't work if you don't sell thousands or tens of thousands of robots. If you only sell hundreds, you will commercially fail. And that's where most of the small robot companies have died. And that's a challenge because, you know, A, you need to field the robots. They need to start to become reliable. And as we've said, that takes time and investment to get there. And so it really does take visionary investment to get there. But we believe that we are going to make money in this industrial monitoring space because, you know, if a chip fab, if the line goes down because a vacuum pump failed someplace, that can be in a very expensive process. It can be a million dollars a day in lost production. Maybe you have to throw away some of the product along the way. And so the robot, if you can prevent that by inspecting the factory every single day, maybe every hour, if you have to, there's a real return on investment there. But there needs to be a critical mass of this task. And we're focusing on a few that we believe are ubiquitous in the industrial production environment. And that's using a thermal camera to keep things from overheating, using an acoustic imager to find compressed air leaks, using visual cameras to read gauges, measuring vibration. These are standard things that you do to prevent unintended shutdown of a factory. And this takes place in a beer factory where we're working with AB InBev. It takes place in chip fabs. We're working with global foundries. It takes place in electric utilities and nuclear power plants. And so the same robot can be applied in all of these industries. And as I said, we have about, actually it's 1100 spots out now to really get profitability. We need to be at 1000 a year, maybe 1500 a year for that sort of part of the business. So it still needs to grow, but we're on a good path." }, { "from": "human", "value": "So I think that's totally achievable. So the application should require crossing that 1000 robot barrier." }, { "from": "gpt", "value": "It really should. 1000 robot." }, { "from": "human", "value": "I want to mention our second robot, Stretch. Yeah, tell me about Stretch. What's Stretch?" }, { "from": "gpt", "value": "Who's Stretch? Stretch started differently than Spot. Spot we built because we had decades of experience building quadrupeds. We just, we had it in our blood. We had to build a quadruped product, but we had to go figure out what the application was. And we actually discovered this factory patrol application, basically preventative maintenance by seeing what our customers did with it. Stretch is very different. We started knowing that there was warehouses all over the world. There's shipping containers moving all around the world full of boxes that are mostly being moved by hand. By some estimates, we think there's a trillion boxes, cardboard boxes shipped around the world each year. And a lot of it's done manually. It became clear early on that there was an opportunity for a mobile robot in here to move boxes around. And the commercial experience has been very different between Stretch and with Spot. As soon as we started talking to people, potential customers about what Stretch was going to be used for, they immediately started saying, oh, I'll buy, I'll buy that robot. You know, in fact, I'm going to put in an order for 20 right now. We just started shipping the robot in January after several years of development. This year. This year. So our first deliveries of Stretch to customers were DHL and Marisk in January. We're delivering the gap right now. And we have about seven or eight other customers, all who've already agreed in advance to buy between 10 and 20 robots. And so we've already got commitments for a couple hundred of these robots. This one's going to go, right? It's so obvious that there's a need and we're not just going to unload trucks. We're going to do any box moving task in the warehouse. And so it too will be a multi-purpose robot and we'll eventually have it doing palletizing or depalletizing or loading trucks or unloading trucks. There's definitely thousands of robots. There's probably tens of thousands of robots of this in the future. So it's going to be profitable." } ]

[ { "from": "human", "value": "And so we need." }, { "from": "gpt", "value": "Can you describe what Stretch looks like? It looks like a big, strong robot arm on a mobile base. The base is about the size of a pallet. And we want it to be the size of a pallet because that's what lives in warehouses, right? Pallets of goods sitting everywhere." }, { "from": "human", "value": "So it needed to be able to fit in that space." }, { "from": "gpt", "value": "But it's not a legged mobile. It's not a legged robot. And so it was our first, it was actually a bit of a commitment from us," }, { "from": "human", "value": "a challenge for us to build a non-balancing robot. To do the much easier problem. And to put it to a..." }, { "from": "gpt", "value": "Because it wasn't going to have this balance problem. And in fact, the very first version of the logistics robot we built was a balancing robot." }, { "from": "human", "value": "And that's called a handle. And there's..." }, { "from": "gpt", "value": "That thing was epic." }, { "from": "human", "value": "All right, it's a beautiful machine. It's an incredible machine. So it was... I mean, it looks epic. It looks like out of the sci-fi movie of some sort. Can you actually just linger on the design of that thing? Because that's another leap into something you probably haven't done. It's a different kind of balancing." }, { "from": "gpt", "value": "Yeah, so let me... Yeah, so let me... I love talking about the history of how a handle came about. Because it connects all of our robots actually. So I'm gonna start with Atlas. When we had Atlas getting fairly far along, we wanted to understand, I was telling you earlier, the challenge of the human form is that you have this mass up high. Because it connects all of... And balancing that inertia, that mass up high, is its own unique challenge. And so we started trying to get Atlas to balance standing on one foot, like on a balance beam, using its arms like this. And yeah, you can do this, I'm sure. I can do this, right? Like if you're walking a tightrope. How do you do that balance? So that's sort of controlling the inertia, controlling the momentum of the robot. We were starting to figure that out on Atlas. And so our first concept of handle, which was a robot that was gonna be on two wheels, so it had the balance, but it was gonna have a big long arm, so it could reach a box at the top of a truck. And it needed yet another counterbalance, a big tail, to help it balance while it was using its arm. So the reason why this robot sort of looks epic, some people said it looked like an ostrich, or maybe an ostrich moving around, was the wheels, it has legs so it can extend its legs. So it's wheels on legs. We always wanted to build wheels on legs. It had a tail and it had this arm, and they're all moving simultaneously and in coordination to maintain balance. Because we had figured out the mathematics of doing this momentum control, how to maintain that balance. And so part of the reason why we built this two-legged robot was we had figured this thing out. We wanted to see it in this kind of machine, and we thought maybe this kind of machine would be good in a warehouse, and so we built it. And it's a beautiful machine. It moves in a graceful way like nothing else we've built, but it wasn't the right machine for a logistics application. We decided it was too slow and couldn't pick boxes fast enough, basically. And it was doing beautifully with elegance. It did beautifully, but it just wasn't efficient enough. So we let it go. But I think we'll come back to that machine eventually." }, { "from": "human", "value": "It was doing beautifully with elegance. The fact that it's possible, the fact that you show that you could do so many things at the same time in coordination and so beautifully, there's something there." }, { "from": "gpt", "value": "That was a demonstration of what is possible. Basically, we made a hard decision and this was really kind of a hard-nosed-business decision. It indicated us not doing it just for the beauty of the mathematics or the curiosity, but nope, we actually need to build a business that can make money in the long run. And so we ended up building Stretch, which has a big heavy base with a giant battery in the base of it that allows it to run for two shifts, 16 hours worth of operation. And that big battery sort of helps it stay balanced, right? So you can move a 50-pound box around with its arm and not tip over. It's omnidirectional, it can move in any direction. So it has a nice suspension built into it. So it can deal with gaps or things on the floor and roll over it, but it's not a balancing robot. It's a mobile robot arm that can work to carry a pick" }, { "from": "human", "value": "or place a box up to 50 pounds anywhere in the warehouse. Take a box from point A to point B, anywhere." }, { "from": "gpt", "value": "Yeah, palletized, depalletized. We're starting with unloading trucks because there's so many trucks and containers that where goods are shipped and it's a brutal job. In the summer, it can be 120 degrees inside that container. People don't wanna do that job. And it's backbreaking labor, right? Again, these can be up to 50-pound boxes. And so we feel like this is a productivity enhancer. And for the people who used to do that job unloading trucks, they're actually operating the robot now. And so by building robots that are easy to control and it doesn't take an advanced degree to manage, you can become a robot operator. And so as we've introduced these robots to both DHL and Marisk and GAP, the warehouse workers who were doing that manual labor are now the robot operators." } ]

[ { "from": "human", "value": "And so we see this as ultimately a benefit to them as well." }, { "from": "gpt", "value": "Can you say how much stretch costs? Not yet. But I will say that when we engage with our customers, they'll be able to see a return on investment" }, { "from": "human", "value": "in typically two years. Okay, so that's something that you're constantly thinking about how, and I suppose you have to do the same kind of thinking with Spot. So it seems like with Stretch, the application is like directly obvious. Yeah, it's a slam dunk." }, { "from": "gpt", "value": "Yeah, and so you have a little more flexibility. Well, I think we know the target. We know what we're going after. And with Spot, it took us a while to figure out" }, { "from": "human", "value": "what we were going after. Well, let me return to that question about maybe the conversation you were having a while ago with Larry Page, maybe looking to the longer future. Of social robotics, of using Spot to connect with human beings, perhaps in the home. Do you see a future there? If we were to sort of hypothesize or dream about a future where a Spot-like robots are in the home" }, { "from": "gpt", "value": "as pets, a social robot? We definitely think about it. And we would like to get there. We think the pathway to getting there is likely through these industrial applications and then mass manufacturing. Let's figure out how to build the robots, how to make the software so that they can really do a broad set of skills. That's gonna take real investment to get there. Performance first, right? The principle of the company has always been, really make the robots do useful stuff. And so the social robot companies that tried to start someplace else by just making a cute interaction, mostly they haven't survived. And so we think the utility really needs to come first. And that means you have to solve some of these hard problems. And so to get there really needs to come first. We're gonna go through the design and software development in industrial. And then that's eventually gonna let you reach a scale that could then be addressed to a consumer-level market. And so, yeah, maybe we'll be able to build a smaller Spot with an arm that could really go get your beer for you. But there's things we need to figure out still. How to safely, really safely. And if you're gonna be interacting with children, you better be safe. And right now we count on a little bit of standoff distance between the robot and people so that you don't pinch a finger in the robot. So you've got a lot of things you need to go solve" }, { "from": "human", "value": "before you jump to that consumer-level product. Well, there's a kind of trade-off in safety because it feels like in the home, you can fall. Like you don't have to be as good at, like you're allowed to fail in different ways, in more ways, as long as it's safe for the humans. So it just feels like an easier problem to solve because it feels like in the factory" }, { "from": "gpt", "value": "you're not allowed to fail. That may be true, but I also think the variety of things a consumer-level robot would be expected to do will also be quite broad. They're gonna want to get the beer and know the difference between the beer and a Coca-Cola or my snack. And they're all gonna want you to clean up the dishes from the table without breaking them. Those are pretty complex tasks. And so there's still work to be done there." }, { "from": "human", "value": "Yeah, so to push back on that, here's where application, I think they'll be very interesting. I think the application of being a pet, a friend. So like, no tasks, just be cute. Because not cute, not cute. The dog is more, a dog is more than just cute. A dog is a friend, is a companion. There's something about just having interacted with them and maybe because I'm hanging out alone with robot dogs a little too much. But like there's a connection there and it feels like that connection is not, should not be disregarded." }, { "from": "gpt", "value": "No, it should not be disregarded. Robots that can somehow communicate through their physical gestures are you're gonna be more attached to in the long run. Do you remember Ibo, the Sony Ibo? They sold over 100,000 of those, maybe 150,000. Probably wasn't considered a successful product for them. They suspended that eventually and then they brought it back, Sony brought it back. And people definitely treated this as a pet, as a companion. And I think that will come around again. Will you get away without having any other utility? Maybe in a world where we can really talk to our simple little pet because chat GPT or some other generative AI has made it possible for you to really talk in what seems like a meaningful way. Maybe that'll open the social robot up again. That's probably not a path we're gonna go down because again, we're so focused on performance and utility. We can add those other things also, but we really wanna start" }, { "from": "human", "value": "from that foundation of utility, I think. Yeah, but I also wanna predict that you're wrong on that. So which is that the very path you're taking which is creating a great robot platform will very easily take a leap to adding a chat GPT like capability, maybe GPT-5. And there's just so many open source alternatives that you could just plop that on top of spot. And because you have this robust platform and you're figuring out how to mass manufacture it and how to drive the cost down and how to make it reliable, all those kinds of things, it'll be a natural transition to where just adding chat GPT on top of it will create-" }, { "from": "gpt", "value": "I do think that being able to verbally converse or even converse through gestures, part of these learning models is that you can now look at video and imagery and associate intent with that. Those will all help in the communication between robots and people, for sure. And that's gonna happen obviously more quickly" } ]

[ { "from": "human", "value": "than any of us were expecting, no. I mean, what else do you want from life? Friend to get your beer and then just talk shit about the state of the world. I mean, where there's a deep loneliness within all of us. And I think a beer and a good chat solves so much of it" }, { "from": "gpt", "value": "or takes us a long way to solving a lot of- It'll be interesting to see, when a generative AI can give you that warm feeling that you connected and that, oh yeah, you remember me, you're my friend," }, { "from": "human", "value": "we have a history, that history matters, right? Memory of joint like- Memory of, yeah. Having witnessed, I mean, that's what friendship, that's what connection, that's what love is in many cases. Some of the deepest friendships you have is having gone through a difficult time together and having a shared memory of an amazing time or a difficult time and kind of that memory creating this like foundation based on which you can then experience the world together. The silly, the mundane stuff of day to day is somehow built on a foundation of having gone through some shit in the past. And the current systems are not personalized in that way, but I think that's a technical problem, not some kind of fundamental limitation. So combine that with an embodied robot like Spot, which already has magic in its movement. I think it's a very interesting possibility of where that takes us. But of course you have to build that on top of a company that's making money with real applications, real customers, and with robots that are safe" }, { "from": "gpt", "value": "and at work and reliable and manufactured scale. And I think we're in a unique position in that because of our investors primarily Hyundai, but also SoftBank still owns 20% of us. They don't, they're not totally fixated on driving us to profitability as soon as possible. That's not the goal. The goal really is a longer term vision of creating what does mobility mean in the future? How is this mobile robot technology going to influence us? Can we shape that? And they want both. And so we as a company are trying to strike that balance between let's build a business that makes money. I've been describing that to my own team as self-destination. If I want to drive my own ship, we need to have a business that's profitable in the end, otherwise somebody else is going to drive the ship for us. So that's really important, but we're going to retain the aspiration that we're going to build the next generation of technology at the same time." }, { "from": "human", "value": "And the real trick will be if we can do both. Speaking of ships, let me ask you about a competitor. And somebody has become a friend. So Elon Musk and Tesla have announced they've been in the early days of building a humanoid robot. How does that change the landscape of your work? So there's sort of from the outside perspective, it seems like, well, as a fan of robotics," }, { "from": "gpt", "value": "it just seems exciting. Right, very exciting, right? When Elon speaks, people listen. And so it suddenly brought a bright light onto the work that we'd been doing for over a decade. And I think that's only going to help. And in fact, what we've seen is that, in addition to Tesla, we're seeing a proliferation of robotic companies arise now. Including humanoid? Yes. Oh, wow. Yeah, so, and interestingly, many of them as they're raising money, for example, will claim whether or not they have a former" }, { "from": "human", "value": "Boston Dynamics employee on their staff as a criteria. Yeah, that's true. I would do that as a company, yeah, for sure. Yeah, so. And it shows you're legit, yeah." }, { "from": "gpt", "value": "Yeah, so, yeah. So you know what? It's bring, it has brought a tremendous validation to what we're doing and excitement. Competitive juices are flowing, you know, the whole thing." }, { "from": "human", "value": "So it's all good. This is, you know, I was also kind of stated that, you know, maybe he implied that the problem is solvable in the near term, which is a low cost humanoid robot that's able to do, that's a relatively general use case robot. So I think Elon is known for sort of setting these kinds of incredibly ambitious goals. Maybe missing deadlines, but actually pushing not just the particular team he leads, but the entire world to like accomplishing those. Do you see Boston Dynamics in the near future being pushed in that kind of way? Like this excitement of competition kind of pushing Atlas maybe to do more cool stuff, trying to drive the cost of Atlas down, perhaps. Or, I mean, I guess I want to ask if there's some kind of exciting energy in Boston Dynamics due to this a little bit of competition." }, { "from": "gpt", "value": "Oh yeah, oh yeah, definitely. When we released our most recent video of Atlas, you know, I think you'd seen it scaffolding and throwing the box of tools around and then doing the flip at the end. We were trying to show the world that not only can we do this parkour mobility thing, but we can pick up and move heavy things. Because if you're gonna work in a manufacturing environment, that's what you gotta be able to do. And for the reasons I explained to you earlier, it's not trivial to do so. Changing the center of mass by picking up a 50 pound block for a robot that weighs 150 pounds, that's a lot to accommodate. So we're trying to show that we can do that. And so it's totally been energizing. You know, we see the next phase of Atlas being more dexterous hands that can manipulate and grab more things that we're gonna start by moving big things around that are heavy and that affect balance. And why is that? Well, really tiny dexterous things probably are gonna be hard for a while yet. Maybe you could go build a special purpose robot arm, for stuffing chips into electronics boards, but we don't really wanna do really fine work like that. I think more coursework where you're using two hands to pick up and balance an unwieldy thing, maybe in a manufacturing environment, maybe in a construction environment, those are the things that we think robots are gonna be able to do with the level of dexterity that they're gonna have in the next few years. And that's where we're headed. And I think, and Elon has seen the same thing, right? He's talking about using the robots in a manufacturing environment. We think there's something very interesting there about having a two-armed robot. Because when you have two arms, you can transfer a thing from one hand to the other, you can turn it around, you can reorient it in a way that you can't do it if you just have one hand on it. And so there's a lot that extra arm brings to the table." } ]

[ { "from": "human", "value": "Maybe you could do that. So I think in terms of mission, you mentioned Boston Dynamics really wants to see what's the limits of what's possible. And so the cost comes second, or it's a component, but first figure out what are the limitations. I think with Elon, he's really driving the cost down. Is there some inspiration, some lessons you see there of the challenge of driving the cost down," }, { "from": "gpt", "value": "especially with Atlas, with a humanoid robot? Well, I think the thing that he's certainly been learning by building car factories is what that looks like. By scaling, you can get efficiencies that drive costs down very well. And the smart thing that they have in their favor is that they know how to manufacture, they know how to build electric motors, they know how to build computers and vision systems. So there's a lot of overlap between modern automotive companies and robots, but hey, we have a modern robotic," }, { "from": "human", "value": "I mean, that automotive company behind us as well." }, { "from": "gpt", "value": "So bring it on. Who's doing pretty well, right?" }, { "from": "human", "value": "The electric vehicles from Hyundai are doing pretty well. I love it. So how much, so we've talked about some of the low-level control, some of the incredible stuff that's going on and basic perception, but how much do you see currently in the future of Boston Dynamics sort of higher-level machine learning applications? Do you see customers adding on those capabilities" }, { "from": "gpt", "value": "or do you see Boston Dynamics doing that in-house? Some kinds of things we really believe are probably gonna be more broadly available, maybe even commoditized, using a machine learning, like a vision algorithm. So a robot can recognize something in the environment. That ought to be something you can just download. Like I'm going to a new environment and have a new kind of door handle or piece of equipment I want to inspect, you ought to be able to just download that. And I think people, besides Boston Dynamics, will provide that. And we've actually built an API that lets people add these vision algorithms to Spot. And we're currently working with some partners who are providing that. Levitas is an example of a small provider who's giving us software for reading gauges. And actually another partner in Europe, reply is doing the same thing. So we see that, we see ultimately an ecosystem of providers doing stuff like that. And I think ultimately, you might even be able to do the same thing with behaviors. So this technology will also be brought to bear on controlling the robot, the motions of the robot. And we're using reinforcement learning to develop algorithms for both locomotion and manipulation. And ultimately, this is going to mean you can add new behaviors to a robot quickly. And that could potentially be done outside of Boston Dynamics. Right now, that's all internal to us. I think you need to understand at a deep level, the robot control to do that. But eventually that could be outside. But it's certainly a place where these approaches are gonna be brought to bear in robotics." }, { "from": "human", "value": "So reinforcement learning is part of the processes. You do use reinforcement learning. So there's increasing levels of learning with these robots? Yes. And that's for both for locomotion, for manipulation and for perception. Yes. Well, what do you think in general about all the exciting advancements of transformer neural networks most beautifully illustrated through the large language" }, { "from": "gpt", "value": "models like GPT-4, the large language? Like everybody else, we're all, I'm surprised at how much, how far they've come. I'm a little bit nervous about the, there's anxiety around them, obviously, for I think good reasons, right? Disinformation is a curse that's an unintended consequence of social media that could be exacerbated with these tools. So if you use them to deploy disinformation, it could be a real risk. But I also think that the risks associated with these kinds of models don't have a whole lot to do with the way we're gonna use them in our robots. If I'm using a robot, I'm building a robot to do, a manual task of some sort. I can judge very easily, is it doing the task I asked it to? Is it doing it correctly? There's sort of a built-in mechanism for judging. Is that, is it doing the right thing?" }, { "from": "human", "value": "Did it successfully do that is a task?" }, { "from": "gpt", "value": "Yeah, physical reality is a good verifier. It's a good verifier, that's exactly it. Whereas if you're asking for, yeah, I don't know, you're trying to ask a theoretical question in chat GPT, it could be true or it may not be true. And it's hard to have that verifier. What is that truth that you're comparing against? Whereas in physical reality, you know the truth. And this is an important difference. And so I'm not, I think there is reason to be a little bit concerned about how these tools, large language models could be used, but I'm not very worried about how they're gonna be used. Well, how learning algorithms in general are going to be used on robotics. It's really a different application" }, { "from": "human", "value": "that has different ways of verifying what's going on. Well, the nice thing about language models is that I ultimately see, I'm really excited about the possibility of having conversations with Spot. There's no, I would say negative consequences to that, but just increasing the bandwidth and the variety of ways you can communicate with this particular robot. So you could communicate visually, you can communicate through some interface and to be able to communicate verbally again with the beer and so on. I think that's really exciting to make that much, much easier." }, { "from": "gpt", "value": "We have this partner Levitas that's adding the vision algorithms for daydreaming for us. They just, just this week I saw a demo where they hooked up a language tool to Spot" } ]

[ { "from": "human", "value": "and they're talking to Spot to give a chance. Can you tell me about the Boston Dynamics AI Institute?" }, { "from": "gpt", "value": "What is it and what is its mission? So it's a separate organization, the Boston Dynamics Artificial Intelligence Institute. And it's led by Mark Robert, the founder of Boston Dynamics and the former CEO and my old advisor at MIT. Mark has always loved the research, the pure research without the confinement or demands of commercialization. And he wanted to continue to, pursue that unadulterated research. And so suggested to Hyundai that he set up this Institute and they agree that it's worth additional investment to kind of continue pushing this forefront. And we expect to be working together where Boston Dynamics is again, both commercialize and do research. But the sort of time horizon of the research we're gonna do is in the next, let's say five years, what can we do in the next five years? Let's work on those problems. And I think the goal of the AI Institute is to work even further out. Certainly, the analogy of luggage locomotion again, when we started that, that was a multi-decade problem. And so I think Mark wants to have the freedom to pursue really hard over the horizon problems." }, { "from": "human", "value": "And that'll be the goal of the Institute. So we mentioned some of the dangers of, some of the concerns about large language models. That said, there's been a long running fear of these embodied robots." }, { "from": "gpt", "value": "Why do you think people are afraid of Lincoln robots? Yeah, I wanted to show you this. So this is in the Wall Street Journal and this is all about chat GPT, right? But look at the picture. It's a humanoid robot that's saying that looks scary and it says, I'm gonna replace you. And so the humanoid robot is sort of, is the embodiment of this chat GPT tool that there's reason to be a little bit nervous about how it gets deployed. So I'm nervous about that connection. It's unfortunate that they chose to use a robot as that embodiment for, as you and I just said, there's big differences in this. But people are afraid because we've been taught to be afraid for over a hundred years. So the word robot was developed by a playwright named Carol Chapak in 1921 to check a playwright for awesome's universal robots. And in that first depiction of a robot, the robots took over and they'd say at the end of the story. And people love to be afraid. And so we've been entertained by these stories for a hundred years. And I think that's as much why people are afraid as anything else is we've been sort of taught that this is the logical progression through fiction is anything else." }, { "from": "human", "value": "I think it's fiction. I think what people more and more will realize, just like you said, that the threat, like say you have a super intelligent AI embodied in a robot that's much less threatening because it's visible, it's verifiable, it's right there in physical reality and we humans know how to deal with physical reality. I think it's much scarier when you have arbitrary scaling of intelligent AI systems in the digital space that they could pretend to be human. So robot, spot is not gonna be pretend, it could pretend it's human all at once. It could tell you, you could put your GPT on top of it, but you're gonna know it's not human because you have a contact with physical reality." }, { "from": "gpt", "value": "And you're gonna know whether or not it's doing what you asked it to do." }, { "from": "human", "value": "Yeah, yeah. Like it's not gonna, like if it like, I mean, I'm sure you can start just like a dog lies to use. Like I wasn't part of tearing up that couch. So spot can try to lie that like, it wasn't me that spilled that thing, but you're going to kind of figure it out eventually. It's, if it happens multiple times, you know." }, { "from": "gpt", "value": "But I think that. Humanity has figured out how to make machines safe. And there's, you know, regulatory environments and certification protocols that we've developed in order to figure out how to make machines safe. We don't know, and don't have that experience with software that can be propagated worldwide in an instant. And so I think we needed to develop those protocols and those tools. And so that's work to be done, but I don't think the fear of that in that work should necessarily impede our ability to now get robots out. Because again, I think we can judge" }, { "from": "human", "value": "when a robot's being safe. So, and again, just like in that image, there's a fear that robots will take our jobs. I just, I took a ride, I was in San Francisco, I took a ride in the Waymo vehicles and autonomous vehicle. And I was on it several times. They're doing incredible work over there. But people flicked it off, they felt the car. So, I mean, that's a long story of what the psychology of that is. It could be maybe big tech or what, I don't know exactly what they're flicking off, but there is an element of like these robots are taking our jobs or irreversibly transforming society such that it will have economic impact and the little guy will be, would lose a lot, would lose their wellbeing. Is there something to be said about the fear" }, { "from": "gpt", "value": "that robots will take our jobs? You know, at every significant technological transformation, there's been fear of an automation anxiety that it's gonna have a broader impact than we expected. And there will be, you know, jobs will change. Sometime in the future, we're gonna look back at people who manually unloaded these boxes from trailers and we're gonna say, why did we ever do that manually? But there's a lot of people who are doing that job today that could be impacted. But I think the reality is, as I said before, we're gonna build the technology so that those very same people can operate it. And so I think there's a pathway to upskilling and operating just like, look, we used to farm with hand tools and now we farm with machines and nobody has really regretted that transformation. And I think the same can be said for a lot of manual labor that we're doing today. And on top of that, you know, look, we're entering a new world where demographics are gonna have strong impact on economic growth. And the, you know, the advanced, the first world is losing population quickly. In Europe, they're worried about hiring enough people just to keep the logistics supply chain going. And, you know, part of this is the response to COVID and everybody's sort of thinking back what they really wanna do with their life. But these jobs are getting harder and harder to fill. And I just, I'm hearing that over and over again. So I think, frankly, this is the right technology at the right time where we're gonna need some of this work to be done." } ]

[ { "from": "human", "value": "And we're gonna want tools to enhance that productivity. And the scary impact, I think, again, GPT comes to the rescue in terms of being much more terrifying. The scary impact of basically, so I'm a, I guess, a software person. So I program a lot. And the fact that people like me can be easily replaced. By GPT." }, { "from": "gpt", "value": "That's going to have a... Well, in law, you know, anyone who deals with texts and writing a draft proposal might be easily done with a chat GPT now. Consultants. Where it wasn't before." }, { "from": "human", "value": "Journalists. No. Consultants. Where it wasn't before. Journalists. Yeah." }, { "from": "gpt", "value": "Everybody's sweating. But on the other hand, you also want it to be right. And they don't know how to make it right yet. But it might make a good starting point" }, { "from": "human", "value": "for you to iterate. Boy, do I have to talk to you about modern journalism. That's another conversation altogether. But yes, more right than the average, the mean journalist, yes. You spearheaded the NT Weaponization Letter. Boston Dynamics has. Can you describe what that letter states? And the general topic of the use of robots in war." }, { "from": "gpt", "value": "We authored a letter and then got several leading robotics companies around the world, including, you know, unitry in China and agility here in the United States and animal in Europe and, you know, some others. To cosign a letter that said, we won't put weapons on our robots. And part of the motivation there is, you know, as these robots start to become commercially available, you can see videos online of people who've gotten a robot and strapped a gun on it and shown that they can, you know, operate the gun remotely," }, { "from": "human", "value": "you know, while driving the robot around," }, { "from": "gpt", "value": "you know, the robot around. And so having a robot that has this level of mobility and that can easily be configured in a way that could harm somebody from a remote operator is justifiably a scary thing. And so we felt like it was important to draw a bright line there and say, we're not going to allow this for, you know, reasons that we think ultimately it's better for the whole industry if it grows in a way where robots are ultimately going to help us all and make our lives more fulfilled and productive. But by goodness, you're going to have to trust the technology to let it in. And if you think the robot's going to harm you, that's going to impede the growth of that industry. So we thought it was important to draw a bright line and then publicize that. And our plan is to, you know, begin to engage with lawmakers and regulators. Let's figure out what the rules are going to be around the use of this technology and use our position as leaders in this industry and technology to help force that issue. And so we are, in fact, I have a policy director at my company whose job it is to engage with the public, to engage with interested parties and including regulators" }, { "from": "human", "value": "to sort of begin these discussions. Yeah, it's a really important topic and it's an important topic for people that worry about the impact of robots on our society with autonomous weapon systems. So I'm glad you're sort of leading the way in this. You are the CEO of Boston Dynamics. What's it take to be a CEO of a robotics company? So you started as a humble engineer, a PhD, just looking at your journey. What does it take to go from building the thing to leading a company?" }, { "from": "gpt", "value": "What are some of the big challenges for you? Courage, I would put front and center for multiple reasons. I talked earlier about the courage to tackle hard problems. So I think there's courage required not just of me, but of all of the people who work at Boston Dynamics. I also think we have a lot of really smart people. We have people who are way smarter than I am. And it takes a kind of courage to be willing to lead them and to trust that you have something to offer to somebody who probably is maybe a better engineer than I am. Adaptability, you know, part of the, it's been a great career for me. I never would have guessed I'd stayed in one place for 30 years. And the job has always changed. I didn't really aspire to be CEO from the very beginning, but it was the natural progression of things. There was always, there always needed to be some level of management that was needed. And so, you know, when I saw something that needed to be done that wasn't being done, I just stepped in to go do it. And oftentimes, because we were full of such strong engineers, oftentimes that was in the management direction or it was in the business development direction or organizational hiring. Geez, I was the main person hiring at Boston Dynamics for probably 20 years. So I was the head of HR basically. So I, you know, just willingness to sort of tackle any piece of the business that needs it" }, { "from": "human", "value": "and then be willing to shift. Is there something you could say to what it takes to hire a great team? What's a good interview process? How do you know the guy or gal are gonna make a great member of a engineering team" }, { "from": "gpt", "value": "that's doing some of the hardest work in the world? Engineering team that's- You know, we developed an interview process that I was quite fond of. It's a little bit of a hard interview process because the best interviews you ask somebody about what they're interested in and what they're good at. And if they can describe to you something that they worked on and you saw they really did the work, they solved the problems and you saw their passion for it. And you can ask... But what makes that hard is you have to ask a probing question about it. You have to be smart enough about what they're telling you they're expert at to ask a good question. And so it takes a pretty talented team to do that. But if you can do that, that's how you tap in to, ah, this person cares about their work. They really did the work. They're excited about it. That's the kind of person I want at my company. At Google, they taught us about their interview process and it was a little bit different. We evolved the process at Boston Dynamics where it didn't matter if you were an engineer or you were an administrative assistant or a financial person or a technician. You gave us a presentation. You came in and you gave us a presentation. You had to stand up and talk in front of us. And I just thought that was great to tap into those things I just described to you. At Google, they taught us... And I think, I understand why, right? They're hiring tens of thousands of people. They need a more standardized process. So they would sort of err on the other side where they would ask you a standard question. I'm gonna ask you a programming question and I'm just gonna ask you to write code in front of me. That's a terrifying application process. It does let you compare candidates really well, but it doesn't necessarily let you tap in to who they are. Because you're asking them to answer your question instead of you asking them about what they're interested in. But frankly, that process is hard to scale. And even at Boston Dynamics, we're not doing that with everybody anymore. But we are still doing that with the technical people. But because we too now need to sort of increase our rate of hiring, not everybody's giving a presentation anymore." } ]

[ { "from": "human", "value": "But you're still ultimately trying to find" }, { "from": "gpt", "value": "that basic seed of passion for the world. Yeah, did they really do it? Did they find something interesting or curious?" }, { "from": "human", "value": "And do they care about it? I think somebody admires Jim Keller and he likes details. So one of the ways if you get a person to talk about what they're interested in, how many details," }, { "from": "gpt", "value": "like how much of the whiteboard can you fill out? Well, I think you figure out, did they really do the work if they know some of the details? And if they have to wash over the details," }, { "from": "human", "value": "well, then they didn't do it. Especially with engineering, the work is in the details. I have to go there briefly just to get your kind of thoughts in the long-term future of robotics. There's been discussions on the GPT side on the large language model side of whether there's consciousness inside these language models. And I think there's fear, but I think there's also excitement or at least the wide world of opportunity and possibility in embodied robots having something like, let's start with emotion, love towards other human beings, and perhaps the display, real or fake, of consciousness. Is this something you think about in terms of long-term future? Because as we've talked about, people do anthropomorphize these robots. It's difficult not to project some level of, I use the word, sentience, some level of sovereignty, identity, all the things we think is human. That's what anthropomorphization is, is we project humanness onto mobile, especially legged robots. Is that something almost from a science fiction perspective you think about or do you try to avoid ever," }, { "from": "gpt", "value": "try to avoid the topic of consciousness altogether? I'm certainly not an expert in it, and I don't spend a lot of time thinking about this, right? And I do think it's fairly remote for the machines that we're dealing with. I don't spend a lot of time. Our robots, you're right, the people anthropomorphize. They read into the robot's intelligence and emotion that isn't there because they see physical gestures that are similar to things they might even see in people or animals. I don't know much about how these large language models really work. I believe it's a kind of statistical averaging of the most common responses to a series of words, right? It's sort of a very elaborate word completion. And I'm dubious that that has anything to do with consciousness. And I even wonder if that model of sort of simulating consciousness by stringing words together that are statistically associated with one another, whether or not that kind of knowledge, if you want to call that knowledge, would be the kind of knowledge that allowed a sentient being to grow or evolve. It feels to me like there's something about truth or emotions that's just a very different kind of knowledge. That is absolute. Like the interesting thing about truth is it's absolute. And it doesn't matter how frequently it's represented in the World Wide Web. It's, if you know it to be true, it may only be there once, but by God, it's true. And I think emotions are a little bit like that too. You know something, you know? And I just think that's a different kind of knowledge than the way these large language models" }, { "from": "human", "value": "derive sort of simulated intelligence. It does seem that the things that are true very well might be statistically well represented on the internet because the internet is made up of humans. So I tend to suspect that large language models are going to be able to simulate consciousness very effectively. And I actually believe that current GPT-4, when fine-tuned correctly, would be able to do just that. And that's going to be a lot of very complicated ethical questions that have to be dealt with. They have nothing to do with robotics and everything to do with." }, { "from": "gpt", "value": "There needs to be some process of labeling, I think, what is true. Because there is also disinformation available on the web and these models are going to consider that kind of information as well. And again, you can't average something that's true and something that's untrue and get something that's moderately true. It's either right or it's wrong. And so how is that process, and this is obviously something that's available on the purveyors of these, Bard and Chat GPT." } ]

[ { "from": "human", "value": "I'm sure this is what they're working on. Well, if you interact on some controversial topics with these models, they're actually refreshingly nuanced. They present, because when you realize there's no one truth, you know, what caused the war in Ukraine, right? Any geopolitical conflict. You can ask any kind of question, especially the ones that are politically tense, divisive and so on. GPT is very good at presenting. Here's the, like, here's the, presents the different hypotheses. It presents calmly the amount of evidence for each one. It's very, it's really refreshing. It makes you realize that truth is nuanced and it does that well. And I think with consciousness, it would very accurately say, well, it sure as hell feels like I'm one of you humans, but where's my body? I don't understand. Like, you're going to be confused. The cool thing about GPT is it seems to be easily confused in the way we are. Like, you wake up in a new room and you ask, where am I? It seems to be able to do that extremely well. It'll tell you one thing, like a fact about what a war started. And when you correct it, say, well, this isn't, that's not consistent. It'll be confused. It'll be, yeah, you're right. It'll have that same element, childlike element with humility of trying to figure out its way in the world. And I think that's a really tricky area to sort of figure out with us humans of what we want to allow AI systems to say to us, because then if there's elements of sentience that are being on display, you can then start to manipulate human emotion and all that kind of stuff. But I think that's something, that's a really serious and aggressive discussion that needs to be had on the software side. I think, again, embodiment, robotics are actually saving us from the arbitrary scaling of software systems versus creating more problems. But that said, I really believe in that connection between human and robot. There's magic there. And I think there's also, I think a lot of money to be made there. And Boston Dynamics is leading the world" }, { "from": "gpt", "value": "in the most elegant movement." }, { "from": "human", "value": "There's also, I think, a lot of money to be made there, done by robots. So I can't wait to- Thank you. To what maybe other people that built on top of Boston Dynamics robots or Boston Dynamics by itself. So you had one wild career, one place and one set of problems, but incredibly successful. Can you give advice to young folks today? In high school, maybe in college, looking out to this future, where so much robotics and AI seems to be defining the trajectory of human civilization. Can you give them advice on how to have a career they can be proud of," }, { "from": "gpt", "value": "or how to have a life they can be proud of? Well, I would say, follow your heart and your interest. Again, this was an organizing principle, I think, behind the Leg Lab at MIT that turned into a value at Boston Dynamics, which was follow your curiosity, love what you're doing. You'll have a lot more fun and you'll be a lot better at it as a result. I think it's hard to plan. Don't get too hung up on planning too far ahead. Find things that you like doing and then see where it takes you. You can always change direction. You will find things that, ah, that wasn't a good move. I'm gonna back up and go do something else. So when people are trying to plan a career, I always feel like, ah, there's a few happy mistakes that happen along the way and just live with that. But make choices then. So avail yourselves to these interesting opportunities, like when I happen to run into Mark down in the lab, the basement of the AI lab, but be willing to make a decision and then pivot if you see something exciting to go at. Because if you're out and about enough," }, { "from": "human", "value": "you'll find things like that that get you excited. So there was a feeling when you first met Mark and saw the robots, that there's something interesting." }, { "from": "gpt", "value": "Oh boy, I gotta go do this, oh boy, I gotta go do this, there is no doubt." }, { "from": "human", "value": "What do you think in 100 years? What do you think Boston Dynamics is doing? What do you think is the role, even bigger, what do you think is the role of robots and society? Do you think we'll be seeing billions of robots everywhere?" }, { "from": "gpt", "value": "Do you think about that long-term vision? Well, I do think that, I think the robots will be ubiquitous and they will be out amongst us. And they'll be certainly doing some of the hard labor that we do today. I don't think people don't wanna work. People wanna work, people need to work to, I think, feel productive. We don't wanna offload all of the work to the robots because I'm not sure if people would know what to do with themselves. And I think just self-satisfaction and feeling productive is such an ingrained part of being human that we need to keep doing this work. So we're definitely gonna have to work in a complimentary fashion. And I hope that the robots and the computers don't end up being able to do all the creative work, right? Because that's the part that's, that's the rewarding. The creative part of solving a problem is the thing that gives you that serotonin rush that you never forget, you know? Or that adrenaline rush that you never forget. And so, you know, people need to be able to do that creative work and just feel productive. And sometimes that you can feel productive over fairly simple work, but it's just well done, you know, and that you can see the result of. So, you know, there was a cartoon, was it Wally? Was it Wally? Where they had this big ship and all the people were just overweight, lying on their beach chairs, kind of sliding around on the deck of the movie because they didn't do anything anymore. Well, we definitely don't want to be there, you know? We need to work in some complimentary fashion where we keep all of our faculties and our physical health and we're doing some labor, right?" } ]

[ { "from": "human", "value": "But in a complimentary fashion somehow. And I think a lot of that has to do with the interaction, collaboration with robots and with AI systems. I'm hoping there's a lot of interesting possibilities there." }, { "from": "gpt", "value": "I think that could be really cool, right? If you can work in an interaction and really be helpful. Robots, you know, you can ask a robot to do a job you wouldn't ask a person to do, and that would be a real asset. You wouldn't feel guilty about it, you know? You'd say, just do it." }, { "from": "human", "value": "It's a machine and I don't have to have qualms about that. The ones that are machines, I also hope to see a future and it is hope. I do have optimism about that future where some of the robots are pets, have an emotional connection to us humans. And because one of the problems that humans have to solve is this kind of, a general loneliness, the more love you have in your life, the more friends you have in your life, I think that makes a more enriching life, helps you grow and I don't fundamentally see why" }, { "from": "gpt", "value": "some of those friends can't be robots. There's an interesting long running study, maybe it's in Harvard, they just, nice report article written about it recently, they've been studying this group of a few thousand people now for 70 or 80 years. And the conclusion is that companionship and friendship are the things that make for a better and happier life. Maybe it's in Harvard, they just, and so I agree with you. And I think that could happen with a machine that is probably simulating intelligence. I'm not convinced there will ever be true intelligence in these machines, sentience, but they could simulate it and they could collect your history and they could, I guess it remains to be seen whether they can establish that real deep, when you sit with a friend and they remember something about you and bring that up and you feel that connection, it remains to be seen if a machine" }, { "from": "human", "value": "is gonna be able to do that for you. Well, I have to say, inklings of that already started happening for me, some of my best friends at robots. And I have you to thank for leading the way in the accessibility and the ease of use of such robots and the elegance of their movement. Robert, you're an incredible person. Boston Dynamics is an incredible company. I've just been a fan for many, many years for everything you stand for, for everything you do in the world. If you're interested in great engineering, robotics, go join them, build cool stuff. I'll forever celebrate the work you're doing. And it's just a big honor that you sit with me today and talk, it means a lot. So thank you so much." }, { "from": "gpt", "value": "You're doing great. That's ability and the ease. Thank you, Lex." }, { "from": "human", "value": "I'm honored to be here and I appreciate it, it was fun. Thanks for listening to this conversation with Robert Plater. To support this podcast, please check out our sponsors in the description. And now, let me leave you with some words from Alan Turing in 1950, defining what is now termed the Turing test. A computer would deserve to be called intelligent if it could deceive a human into believing that it was human." }, { "from": "gpt", "value": "Thank you for listening and hope to see you next time." } ]

[ { "from": "human", "value": "I often fail, but I try. And if you must skip them, please still check out our sponsors. I enjoy their stuff. Maybe you will too. This episode is brought to you by 8Sleep and its new Pod3 mattress, which I think of as a teleportation device into a land of dreams, a place where the mind goes to escape the space-time physics of this reality of the waking world. Anything is possible in a place of dreams. The darkness that lurks in the young age shadow" }, { "from": "gpt", "value": "is possible." }, { "from": "human", "value": "The shadow, the hope, the triumph, symbolize this delight at the end of the tunnel is possible. All of it is possible. It's all up to you. I'm kind of somebody that likes both the good and the bad of dreaming. There's a cleansing aspect of a bad dream. You wake up freaking out a little bit, but then you realize how awesome this life is that whatever happened in the dream world is not real. It's a kind of dress rehearsal for a bad event that happens in reality, but it doesn't. It's like in a video game, you get to save, do a dangerous thing, screw it up, and then you get to load and try again. That's what a dream is. Anyway, I love dreaming. I love sleeping. I love naps. And an 8Sleep mattress is the best place to teleport into that dream world. Check them out and get special savings when you go to 8sleep.com slash flex. This show is also brought to you by NetSuite, an all-in-one cloud business management system. It manages financials, human resources, inventory, e-commerce, and many business-related details, all things that I have to start figuring out. I put up a job position for somebody to help you with financials. All of it needs so much help because running a business, any kind of business, whether it's a creative business or a robotics factory or any kind of AI software company, anything you do, has so many components. And I would say many of them don't involve any of the kind of cutting-edge engineering and design and brainstorming and innovation and research and all that kind of stuff. You have to do all the basic minutia, the glue that ties together people and makes the whole thing run. And I think you should use the best tool for that job. And NetSuite is something I can definitely recommend as a great tool. You can start now with no payment or interest for six months. Go to netsuite.com slash Lex to access their one-of-a-kind financing program. That's netsuite.com slash Lex. This show is also brought to you by ExpressVPN, my comrade, my friend, the piece of software that has accompanied me through darkness and light for many years, way before I had a podcast, way before I found my way. So I am still forever lost. And you, if you too are forever lost, perhaps it will also warm your heart as a dead mind. First of all, practically speaking, let's put the romantic stuff aside, you should be using a VPN on the internet. And ExpressVPN is the VPN I've used and can highly, highly, highly recommend. By the way, I apologize for the coarseness of my voice. I've been feeling a little bit under the weather, whatever the heck that expression actually means. There's always chat GPT that can ask the question, but I'm not going to, I'm just gonna go with it, gonna wing it. Gonna wing it is another funny expression, right? Wing it, what does that mean? Probably has to do with birds. And the fact that bird flight is a kind of chaotic process that's not amenable to clear dynamical system modeling that, for example, an airplane is. But let us return to the piece of software you should be using to warm your heart and to protect your privacy on the internet. Go to expressvpn.com slash Lexpod for an extra three months free is. This show is also brought to you by Inside Tracker, a service I used to track biological data that comes from my body. There's that song, It's My Party and I'll Cry If I Want To. And I used to think it said, It's My Body and I'll Cry If I Want To. I don't know what I thought that actually meant, but it's a good song, it's a silly song. It's my party and I'll cry if I want to, cry if I want to, cry if I want to. You would cry too if it happened to you. Anyway, speaking of which, we're going hard on the tangents today. I like data that comes from my body that is then used in machine learning algorithms to make decisions or recommendations of what I should do with said body. Lifestyle choices, diet, maybe in the future it'd be career advice, all kinds of stuff, dating, friends, anything, you know. But basically health stuff, medicine, I think, and that's the obvious way you should be figuring out what to do with your body is at least in large part based on the data that comes from your body. And that just wants, but many times, over and over and over and over. InsideTracker are pioneering the data collection, sort of the blood test, then can extract all kinds of information, give you advice. I highly recommend them. Get special savings for a limited time when you go to insidetracker.com slash Lex. This is a Lex Friedman podcast. To support it, please check out our sponsors in the description." }, { "from": "gpt", "value": "And now, dear friends, here's Manoas Callas. Good to see you, first of all, man. Lex, I've missed you. I think you've changed the lives of so many people that I know. And it's truly like such a pleasure to be back, such a pleasure to see you grow, to sort of reach so many different aspects of your own personality. Thank you for the love." } ]

[ { "from": "human", "value": "You've always given me some support and love." }, { "from": "gpt", "value": "I just can't, I'm forever grateful for that. It's lovely to see a fellow human being who has that love, who basically does not judge people. There's so many judgmental people out there." }, { "from": "human", "value": "And it's just so nice to see this beacon of openness. So what makes me one instantiation of human irreplaceable, do you think, as we enter this increasingly capable, age of increasingly capable AI? I have to ask, what do you think makes humans irreplaceable?" }, { "from": "gpt", "value": "So humans are irreplaceable because of the baggage that we talked about. So we talked about baggage. We talked about the fact that every one of us has effectively relearned all of human civilization in their own way. So every single human has a unique set of genetic variants that they've inherited. Some common, some rare, and some make us think differently. Some make us have different personalities. They say that a parent with one child believes in genetics. A parent with multiple children understands genetics. Just how different kids are. And my three kids have dramatically different personalities ever since the beginning. So one thing that makes us unique is that every one of us has a different hardware. The second thing that makes us unique is that everyone of us has a different software uploading of all of human society, all of human civilization, all of human knowledge. We're not born knowing it. We're not like, I don't know, birds that learn how to make a nest through genetics and will make a nest even if they've never seen one. We are constantly relearning all of human civilization. So that's the second thing. And the third one that actually makes humans very different from AI is that the baggage we carry is not experiential baggage, it's also evolutionary baggage. So we have evolved through rounds of complexity. So just like Ogres have layers and Shrek has layers, humans have layers. There's the cognitive layer, which is sort of the outer, most of the latest evolutionary innovation, this enormous neocortex that we have evolved. And then there's the emotional baggage underneath that. And then there's all of the fear and fright and flight and all of these kinds of behaviors. So AI only has a neocortex. AI doesn't have an limbic system. It doesn't have this complexity of human emotions, which make us so, I think, beautifully complex, so beautifully intertwined with our emotions, with our instincts, with our sort of gut reactions and all of that. So I think when humans are trying to suppress that aspect, the sort of more human aspect towards a more cerebral aspect, I think we lose a lot of the creativity. We lose a lot of the freshness of humans." }, { "from": "human", "value": "And I think that's quite irreplaceable. So we can look at the entirety of people that are alive today and maybe all humans who have ever lived and map them in this high dimensional space. And there's probably a center of mass for that mapping. And a lot of us deviate in different directions. So the variety of directions" }, { "from": "gpt", "value": "in which we all deviate from that center is vast. I would like to think that the center is actually empty. Yes. That basically humans are just so diverse from each other that there's no such thing as an average human. That every one of us has some kind of complex baggage of emotions, intellectual, motivational, behavioral traits that it's not just one sort of normal distribution we deviate from it. There's so many dimensions that we're kind of hitting the sort of sparseness, the curse of dimensionality where it's actually quite sparsely populated." }, { "from": "human", "value": "And I don't think you have an average human being. So what makes us unique in part is the diversity and the capacity for diversity and the capacity of the diversity comes from the entire evolutionary history." }, { "from": "gpt", "value": "So there's just so many ways we can vary from each other. Very from each other. Yeah. I would say not just the capacity but the inevitability of diversity. Basically it's in our hardware. We are wired different from each other. My siblings and I are completely different. My kids from each other are completely different. My wife has she's like, number two of six siblings. From a distance they look the same but then you get to know them." }, { "from": "human", "value": "Every one of them is completely different. But sufficiently the same that the differences interplay with each other. So that's the interesting thing where the diversity is functional, it's useful. So it's like we're close enough to where we notice the diversity and it doesn't completely destroy the possibility of like effective communication interaction." }, { "from": "gpt", "value": "So we're still the same kind of thing. So what I said in one of our earlier podcasts is that if humans realize that we're 99.9% identical we would basically stop fighting with each other. Like we are really one human species and we are so, so similar to each other. And if you look at the alternative, if you look at the next thing outside humans like it's been 6 million years that we haven't had a relative. So it's truly extraordinary that we're kind of like this dot in outer space" }, { "from": "human", "value": "compared to the rest of life on earth. When you think about evolving through rounds of complexity can you maybe elaborate such a beautiful phrase, beautiful thought that there's layers of complexity" }, { "from": "gpt", "value": "that make. So with software sometimes you're like, oh, let's like build version two from scratch but this doesn't happen in evolution. In evolution you layer in additional features on top of old features. So basically like every single time my cells divide I'm a yeast, like I'm a unicellular organism and then cell division is basically identical. Every time I breathe in and my lungs expand I'm basically like every time my heart beats I'm a fish. So basically that I still have the same heart. Like very, very little has changed. The blood going through my veins, the oxygen, you know, our immune system, we're basically primates. Our social behavior, we're basically new world monkeys and old world monkeys. We're basically this concept that every single one of these behaviors can be traced somewhere in evolution. And that all of that continues to live within us is also a testament to not just not killing other humans for God's sake, but like not killing other species either. Like just to realize just how united we are with nature and that all of these biological processes have never ceased to exist. They're continuing to live within us. And then just the neocortex and all of the reasoning capabilities of humans are built on top of all of these other species that continue to live, breathe, divide, metabolize, fight off pathogens all continued inside us." } ]

[ { "from": "human", "value": "So you think the neocortex, the whatever reasoning is that's the latest feature in the latest version" }, { "from": "gpt", "value": "of this journey. It's extraordinary that humans have evolved so much in so little time. Again, if you look at the timeline of evolution, you basically have billions of years to even get to a dividing cell and then a multicellular organism and then a complex body plan. And then these incredible senses that we have for perceiving the world, the fact that bats can fly and they evolved flight, they evolved sonar in the span of a few million years. I mean, it's just extraordinary how much evolution has kind of sped up. And all of that comes through this evolvability, the fact that we took a while to get good at evolving. And then once you get good at evolving, you can sort of, you have modularity built in, you have hierarchical organizations built in, you have all of these constructs that allow meaningful changes to occur without breaking the system completely. If you look at a traditional genetic algorithm, the way that humans designed them in the sixties, you can only evolve so much. And as you evolve a certain amount of complexity, the number of mutations that move you away from something functional exponentially increases. And the number of mutations that move you to something better exponentially decreases. So the probability of evolving something so complex becomes infinitesimally small as you get more complex. But with evolution, it's almost the opposite, almost the exact opposite, that it appears that it's speeding up exactly as complexity is increasing. And I think that's just the system getting good at evolving." }, { "from": "human", "value": "Where do you think it's all headed? Do you ever think about where, try to visualize the entirety of the evolutionary system and see if there's an arrow to it" }, { "from": "gpt", "value": "and a destination to it? So the best way to understand the future is to look at the past. If you look at the trajectory, then you can kind of learn something about the direction in which we're heading. And if you look at the trajectory of life on earth, it's really about information processing. So the concept of the senses evolving one after the other, you know, like bacteria are able to do chemotaxis, which means moving towards a chemical gradient. And that's the first thing that you need to sort of hunt down food. The next step after that is being able to actually perceive light. So all life on this planet and all life that we know about evolved on this rotating rock. Every 24 hours, you get sunlight and dark, sunlight and dark. And light is a source of energy. Light is also information about where is up. Light is all kinds of, you know, things. So you can basically now start perceiving light and then perceiving shapes beyond just the sort of single photo receptor. You can now have complex eyes or multiple eyes and then start perceiving motion or perceiving direction, perceiving shapes. And then you start building infrastructure on the cognitive apparatus to start processing this information and making sense of the environment, building more complex models of the environment. So if you look at that trajectory of evolution, what we're experiencing now and humans are basically, according to this sort of information, theoretic view of evolution, humans are basically the next natural step. And it's perhaps no surprise that we became the dominant species of the planet. Because yes, there's so many dimensions in which some animals are way better than we are. But at least on the cognitive dimension, we're just simply unsurpassed on this planet and perhaps the universe. But the concept that if you now trace this forward, we talked a little bit about evolvability and how things get better at evolving. One possibility is that the next layer of evolution builds the next layer of evolution. And what we're looking at now with humans and AI is that having mastered this information capability that humans have from this quote unquote old hardware, this basically biological evolved system that kind of somehow in the environment of Africa and then in subsequent environments and sort of dispersing through the globe was evolutionarily advantageous. That has now created technology, which now has a capability of solving many of these cognitive tasks. It doesn't have all the baggage of the previous evolutionary layers. But maybe the next round of evolution on Earth is self-replicating AI, where we're actually using our current smarts to build better programming languages and the programming languages to build, chat GPT and that then build the next layer of software that will then sort of help AI speed up. And it's lovely that we're coexisting with this AI that sort of the creators of this next layer of evolution and this next stage are still around to help guide it and hopefully will be for the rest of eternity as partners. But it's also nice to think about it as to simply the next stage of evolution where you've kind of extracted away the biological needs. Like if you look at animals, most of them spend 80% of their waking hours hunting for food or building shelter. Humans, maybe 1% of that time. And then the rest is left to creative endeavors. And AI doesn't have to worry about shelter, et cetera. So basically it's all living in the cognitive space. So in a way it might just be a very natural sort of next step to think about evolution. And that's on the sort of purely cognitive side. If you now think about humans themselves, the ability to understand a comprehendor on genome, again, the ultimate layer of introspection, gives us now the ability to even mess with this hardware, not just augment our capabilities through interacting and collaborating with AI, but also perhaps understand the neural pathways that are necessary for empathetic thinking, for justice, for this and this and that, and sort of help augment human capabilities through neuronal interventions, through chemical interventions, through electrical interventions to basically help steer the human bag of hardware that we kind of evolved with into greater capabilities. And then ultimately by understanding not just the wiring of neurons and the functioning of neurons, but even the genetic code. We could even at one point in the future start thinking about, well, can we get rid of psychiatric disease? Can we get rid of neurodegeneration? Can we get rid of dementia and start perhaps even augmenting human capabilities" } ]

[ { "from": "human", "value": "not just getting rid of disease? Can we tinker with the genome, with the hardware or getting closer to the hardware without having to deeply understand the baggage. In the way we've disposed of the baggage in our software systems with AI to some degree, not fully, but to some degree, can we do the same with the genome" }, { "from": "gpt", "value": "or is the genome deeply integrated into this baggage? I wouldn't wanna get rid of the baggage. The baggage would makes us awesome. So the fact that I'm sometimes angry and sometimes hungry and sometimes hangry is perhaps contributing to my creativity. I don't wanna be dispassionate. I don't wanna be another like, you know, Robert. I wanna get in trouble and I wanna sort of say the wrong thing. And I wanna sort of make an awkward comment and sort of push myself into reactions and responses and things that can get just people thinking differently. And I think our society is moving towards a humorless space where everybody's so afraid to say the wrong thing that people kind of start quitting on mass and start like not biking their jobs and stuff like that. Maybe we should be kind of embracing that human aspect a little bit more in all of that baggage aspect and not necessarily thinking about replacing it. On the contrary, like embracing it and sort of this coexistence of the cognitive" }, { "from": "human", "value": "and the emotional hardwares. So embracing and celebrating the diversity that springs from the baggage versus kind of pushing towards and empowering this kind of pull towards conformity." }, { "from": "gpt", "value": "Yeah. And in fact, with the advent of AI, I would say and these seemingly extremely intelligent systems that sort of can perform tasks that we thought of as extremely intelligent at the blink of an eye, this might democratize intellectual pursuits instead of just simply wanting the same type of brains that carry out specific ways of thinking. We can, like instead of just always only wanting say the mathematically extraordinary to go to the same universities, what you could simply say is like, who needs that anymore? We now have AI. Maybe what we should really be thinking about is the diversity and the power that comes with the diversity where AI can do the math and then we should be getting a bunch of humans that sort of think extremely differently from each other and maybe that's the true cradle of innovation." }, { "from": "human", "value": "But AI can also, these large language models can also be with just a few prompts, essentially fine tuned to be diverse from the center. So the prompts can really take you away into unique territory. You can ask the model to act in a certain way and it will start to act in that way. Is that possible that the language models could also have some of the magical diversity" }, { "from": "gpt", "value": "that makes us so damn interesting? So I would say humans are the same way. So basically when you sort of prompt humans to basically in a given environment to act a particular way, they change their own behaviors and the old saying is show me your friends and I'll tell you who you are more like show me your friends and I'll tell you who you will become. So it's not necessarily that you choose friends that are like you but that's the first step. But then the second step is that the kind of behaviors that you find normal in your circles are the behaviors that you'll start espousing. And that type of meta evolution where every action we take not only shapes our current action and the result of this action but it also shapes our future actions by shaping the environment in which those future actions will be taken. Every time you carry out a particular behavior it's not just a consequence for today but it's also a consequence for tomorrow because you're reinforcing that neural pathway. So in a way self discipline is a self fulfilling prophecy and by behaving the way that you wanna behave and choosing people that are like you and sort of exhibiting those behaviors that are sort of desirable," }, { "from": "human", "value": "you end up creating that environment as well. So it is a kind of life itself is a kind of prompting mechanism, super complex. The friends you choose, the environments you choose, the way you modify the environment that you choose, yes. But that seems like that process is much less efficient than a large language model. You can literally get a large language model through a couple of prompts to be a mix of Shakespeare and David Bowie, right? You can very aggressively change in a way that's stable and convincing. You really transform through a couple of prompts the behavior of the model" }, { "from": "gpt", "value": "into something very different from the original. So well before chat GPT, I would tell my students just ask, what would Manoli say right now? And you guys all have a pretty good emulator of me right now. And I don't know if you know the programming paradigm of the Robert Ducklin, where you basically explain to the Robert Ducklin, that's just sitting there, exactly what you did with your code and why you have a bug. And just by the act of explaining, you'll kind of figure it out. I woke up one morning from a dream where I was giving a lecture in this amphitheater. And one of my friends was basically giving me some deep evolutionary insight on how cancer genomes and cancer cells evolve. And I woke up with a very elaborate discussion that I was giving and a very elaborate set of insights that he had, that I was projecting onto my friend in my sleep. And obviously this was my dream. So my own neurons were capable of doing that, but they only did that under the prompt of, you are now Piyush Gupta, you are a professor in cancer genomics, you're an expert in that field. What do you say? So I feel that we all have that inside us, that we have that capability of basically saying, I don't know what the right thing is, but let me ask my virtual X, what would you do? And virtual X would say, be kind. I'm like, oh, yes, or something like that. And even though I myself might not be able to do it unprompted and my favorite prompt is think step by step. And I'm like, you know, this also works on my 10 year old. When he tries to solve a math equation all in one step, I know exactly what mistake you'll make. But if I prompted with, oh, please think step by step, then he sort of gets in a mindset. And I think it's also part of the way that chat GPT was actually trained, this whole sort of human in the loop reinforcement learning has probably reinforced these types of behaviors, whereby having this feedback loop, you kind of aligned AI better" } ]

[ { "from": "human", "value": "to the prompting opportunities by humans. Yeah, prompting human like reasoning steps, the step by step kind of thinking. Yeah, but it does seem to be, I suppose it just puts a mirror to our own capabilities and so we can be truly impressed by our own cognitive capabilities because the variety of what you can try is we don't usually have this kind of, we can't play with our own mind rigorously through Python code, right? Yeah. So this allows us to really play with all of human wisdom and knowledge or at least knowledge at our fingertips and then mess with that little mind" }, { "from": "gpt", "value": "that can think and speak in all kinds of ways. What's unique is that, as I mentioned earlier, every one of us was trained by different subset of human culture. And chat GPT was trained on all of it. And the difference there is that it probably has the ability to emulate almost every one of us. The fact that you can figure out where that is in cognitive behavioral space, just by a few prompts is pretty impressive. But the fact that that exists somewhere is absolutely beautiful. And the fact that it's encoded in an orthogonal way from the knowledge, I think is also beautiful. The fact that somehow through this extreme over-parameterization of AI models, it was able to somehow figure out that context, knowledge, and form are separable. And that you can sort of describe scientific knowledge in a haiku in the form of, I don't know, Shakespeare or something. That tells you something about the decoupling and the decouplability of these types of aspects" }, { "from": "human", "value": "of human psyche. And that's part of the science of this whole thing. So these large language models are days old in terms of this kind of leap that they've taken. And it'll be interesting to do this kind of analysis on them of the separation of context, form, and knowledge. Where exactly does that happen? There's already sort of initial investigations, but it's very hard to figure out where is there a particular set of parameters that are responsible for a particular piece of knowledge or a particular context or a particular style of speaking." }, { "from": "gpt", "value": "So with convolutional neural networks, interpretability had many good advances because we can kind of understand them, there's a structure to them, there's a locality to them. And we can kind of understand that different layers have different sort of ranges that they're looking at. So we can look at activation features and basically see where does that correspond to. With large language models, it's perhaps a little more complicated, but I think it's still achievable. In the sense that we could kind of ask, well, what kind of prompts does this generate? If I sort of drop out this part of the network, then what happens? And sort of start getting at a language to even describe these types of aspects of human behavior or psychology, if you wish, from the spoken part in the language part. And the advantage of that is that it might actually teach us something about humans as well. Like, we might not have words to describe these types of aspects right now, but when somebody speaks in a particular way, it might remind us of a friend that we know from here and there and there. And if we had better language for describing that, these concepts might become more apparent in our own human psyche. And then we might be able to encode them better in machines themselves." }, { "from": "human", "value": "I mean, both probably you and I would have certain interests with the base model, with OpenEcho's the base model, which is before the alignment of the reinforcement learning with human feedback and before the AI safety-based kind of censorship of the model. It would be fascinating to explore, to investigate the ways that the model can generate hate speech, the kind of hate that humans are capable of. It would be fascinating, or the kind of, of course, like sexual language or the kind of romantic language or all kinds of ideologies. Can I get it to be a communist? Can I get it to be a fascist? Can I get it to be a capitalist? Can I get it to be all these kinds of things and see which parts get activated or not? Because it'll be fascinating to sort of explore at the individual mind level and at a societal level, where do these ideas take hold? What is the fundamental core of those ideas? Maybe the communism, fascism, capitalism, democracy are all actually connected by the fact that the human heart, the human mind is drawn to ideology, to a centralizing idea." }, { "from": "gpt", "value": "And maybe we need a neural network to remind us of that. I like the concept that the human mind is somehow tied to ideology. And I think that goes back to the promptability of chat activity, the fact that you can kind of say, well, think in this particular way now. And the fact that humans have invented words for encapsulating these types of behaviors. And it's hard to know how much of that is innate and how much of that was passed on from language to language. But basically, if you look at the evolution of language, you can kind of see how young are these words in the history of language evolution that describe these types of behaviors, like kindness and anger and jealousy, et cetera? If these words are very similar from language to language, it might suggest that they're very ancient. If they're very different, it might suggest that this concept may have emerged independently in each different language and so on and so forth. So looking at the phylogeny, the history, the evolutionary traces of language at the same time as people moving around that we can now trace thanks to genetics is a fascinating way of understanding the human psyche and also understanding sort of how these types of behaviors emerge. And to go back to your idea about sort of exploring the system unfiltered, I mean, in a way, psychiatric hospitals are full of those people. So basically, people whose mind is uncontrollable, who have kind of gone adrift in specific locations of their psyche. And I do find this fascinating. Basically, you know, watching movies that are trying to capture the essence of troubled minds, I think is teaching us so much about our everyday selves, because many of us are able to sort of control our minds and are able to somehow hide these emotions. But every time I see somebody who's troubled, I see versions of myself, maybe not as extreme, but I can sort of empathize with these behaviors. And, you know, I see bipolar, I see schizophrenia, I see depression, I see autism, I see so many different aspects that we can have names for and crystallize in specific individuals. And I think all of us have that. All of us have sort of just this multidimensional brain and genetic variations that push us in these directions, environmental exposures and traumas that pushes in these directions, environmental behaviors that are reinforced by the kind of friends that we chose or friends that we were stuck with because of the environments that we grew up in. So in a way, a lot of these types of behaviors are within the vector span of every human. It's just that the magnitude of those vectors is generally smaller for most people because they haven't inherited that particular set of genetic variants or because they haven't been exposed" } ]

[ { "from": "human", "value": "to those environments, basically. Or something about the mechanism of reinforcement learning with human feedback didn't quite work for them. So it's fascinating to think about that's what we do. We have this capacity to have all these psychiatric or behaviors associated with psychiatric disorders, but we, through the alignment process, as we grow up with the parents, we kind of, we know to suppress them." }, { "from": "gpt", "value": "Yeah, exactly. We know how to control them. Every human that grows up in this world spends several decades being shaped into place. And without that, maybe we would have the unfiltered chat GPT-4." }, { "from": "human", "value": "Every baby's basically a raging narcissist." }, { "from": "gpt", "value": "Not all of them, not all of them, believe it or not. It's remarkable. I remember watching my kids grow up, and again, yes, part of their personality stays the same, but also in different phases to their life. They've gone through these dramatically different types of behaviors. And my daughter basically saying, basically one kid saying, oh, I want the bigger piece. The other one saying, oh, everything must be exactly equal. And the third one saying, I'm okay. You know, I might have to have the smaller part. Don't worry about me. Even in the early days, in the early years of development. It's just extraordinary to sort of see these dramatically different, I mean, my wife and I are very different from each other, but we also have six million variance, six million loci each if you wish, if you just look at common variance, we also have a bunch of rare variance that are inherited in a more Mendelian fashion. And now you have an infinite number of possibilities for each of the kids. So basically it's due to the six million just from the common variance, and then if you like layer in the rare variants. So let me talk a little bit about common variance and rare variance. So if you look at this common variance, they're generally weak effect because selection selects against strong effect variance. So if something like has a big risk for schizophrenia, it won't rise to high frequency. So the ones that are common are by definition, by selection, only the ones that had relatively weak effect. And if all of the variance associated with personality, with cognition and all aspects of human behavior where weak effect variance, then kids would basically be just" }, { "from": "human", "value": "averages of their parents. Even in the early days." }, { "from": "gpt", "value": "In the early years it developed. If it was like thousands of loci just by law of large numbers, the average of two large numbers would be very robustly close to that middle, but what we see is that kids are dramatically different from each other. So that basically means that in the context of that common variation, you basically have rare variants that are inherited in a more Mendelian fashion that basically then sort of govern likely many different aspects of human behavior, human biology, and human psychology. And that's, again, like if you look at sort of a person with schizophrenia, their identical twin has only 50% chance of actually being diagnosed with schizophrenia. So that basically means there's probably developmental exposures, environmental exposures, trauma, all kinds of other aspects that can shape that. And if you look at siblings, for the common variants it kind of drops off exponentially as you would expect with sharing 50% of your genome, 25% of your genome, 12.5% of your genome, et cetera, with more and more distant cousins. But the fact that siblings can differ so much in their personalities that we observe every day, it can't all be nurture. Basically, again, as parents, we spend enormous amount of energy trying to fix, quote unquote, the nurture part, trying to get them to share, get them to be kind, get them to be open, get them to trust each other, like overcome the prisoner's dilemma of, if everyone fends on themselves, we're all gonna live in a horrible place, but if we're a little more altruistic, then we're all gonna be in a better place. And I think it's not like we treat our kids differently, but they're just born differently. So in a way, as a geneticist, I have to admit that there's only so much I can do with nurture," }, { "from": "human", "value": "that nature definitely plays a big component. The selection of variants we have, the common variants and the rare variants. What can we say about the landscape of possibility they create, if you could just linger on that? So the selection of rare variants is divine how. How do we get the ones that we get? Is it just laden in that giant evolutionary baggage?" }, { "from": "gpt", "value": "So I'm gonna talk about regression. Why do we call it regression? And the concept of regression to the mean, the fact that when fighter pilots in a dogfight did amazingly well, they would give them rewards. And then the next time they're in a dogfight, they would do worse. So then the Navy basically realized that, wow, at least interpreted that as wow, we're ruining them by praising them, and then they're gonna perform worse. The statistical interpretation of that is regression to the mean. The fact that you're an extraordinary pilot, you've been trained in an extraordinary fashion. That pushes your mean further and further to extraordinary achievement. And then in some dogfights, you'll just do extraordinarily well. The probability that the next one will be just as good is almost nil, because this is the peak of your performance. And just by statistical odds, the next one will be another sample from the same underlying distribution, which is gonna be a little closer to the mean. So regression analysis takes its name from this type of realization in the statistical world. Now, if you now take humans, you basically have people who have achieved extraordinary achievements. Einstein, for example, you would call him, for example, the epitome of human intellect. Does that mean that all of his children and grandchildren will be extraordinary geniuses? It probably means that they're sampled from the same underlying distribution, but he was probably a rare combination of extremes in addition to these common variants. So you can basically interpret your kid's variation, for example, as, well, of course, there are gonna be some kind of sample from the average of the parents with some kind of deviation according to the specific combination of rare variants that they have inherited. So given all that, the possibilities are endless as to sort of where you should be, but you should always interpret that with, well, it's probably an alignment of nature and nurture. And the nature has both the common variants that are acting kind of like the law of large numbers and the rare variants that are acting more in a Mendelian fashion. And then you layer in the nurture, which again, in everyday action we make, we shape our future environment, but the genetics we inherit are shaping the future environment of not only us, but also our children. So there's these weird nature, nurture, interplay and self reinforcement where you're kind of shaping your own environment, but you're also shaping the environment of your kids. And your kids are gonna be born in the context of your environment that you've shaped but also with a bag of genetic variants that they have inherited, and there's just so much complexity associated with that. When we start blaming something on nature, it might just be nurture. It might just be that, well, yes, they inherited the genes from the parents, but they also were shaped by the same environment. So it's very, very hard to untangle the two. And you should always realize that nature can influence nurture, nurture can influence nature, or at least be correlated with and predictive of," } ]

[ { "from": "human", "value": "and so on and so forth and forth. So I love thinking about that distribution that you mentioned, and here's where I can be my usual ridiculous self. And I sometimes think about that army of sperm cells, however many hundreds of thousands there are. And I kind of think of all the possibilities there because there's a lot of variation and one gets to win. Is that- It's not a random one. Is it a totally ridiculous way to think about-" }, { "from": "gpt", "value": "No, not at all. Is that- It's not a random one. So I would say evolutionarily, we are a very slow evolving species. Basically, the generations of humans are a terrible way to do selection. What you need is processes that allow you to do selection in a smaller, tighter loop. And part of what, if you look at our immune system, for example, it evolves at a much faster pace than humans evolve because there is actually an evolutionary process that happens within our immune cells. As they're dividing, there's basically VDJA recombination that basically creates this extraordinary wealth of antibodies and antigens against the environment. And basically all these antibodies are now recognizing all these antigens from the environment, and they send signals back that cause these cells that recognize the non-self to multiply. So that basically means that even though viruses evolve at millions of times faster than we are, we can still have a component of ourselves, which is environmentally facing, which is sort of evolving at not the same scale, but very rapid pace. Sperm expresses perhaps the most proteins of any cell in the body. And part of the thought is that this might just be a way to check that the sperm is intact. In other words, if you waited until that human has a liver and starts eating solid food, and sort of filtrates away, or kidneys or stomach, et cetera, basically if you waited until these mutations manifest late, late in life, then you would end up not failing fast and you would end up with a lot of failed pregnancies and a lot of later onset psychiatric illnesses, et cetera. If instead you basically express all of these genes at the sperm level, anything misform that basically caused the sperm to cripple, then you have at least on the male side, the ability to exclude some of those mutations. And on the female side, as the egg develops, there's probably a similar process where you could sort of weed out eggs that are just not carrying beneficial mutations, or at least are carrying highly detrimental mutations. So you can basically think of the evolutionary process in a nested loop, basically, where there's an inner loop where you get many, many more iterations to run, and then there's an outer loop that moves at a much slower pace. And going back to the next step of evolution of possibly designing systems that we can use to sort of compliment our own biology or to sort of eradicate disease and you name it, or at least mitigate some of the, I don't know, psychiatric illnesses, neurodegenerative disorders, et cetera. You can basically, and also metabolic, immune, cancer, you name it, simply engineering these mutations from rational design might be very inefficient. If instead you have an evolutionary loop where you're kind of growing neurons on a dish and you're exploring evolutionary space and you're sort of shaping that one protein to be better adapt that sort of, I don't know, recognizing light or communicating with other neurons, et cetera, you can basically have a smaller evolutionary loop that you can run thousands of times faster than the speed it would take to evolve humans for another million years. So I think it's important to think about sort of this evolvability as a set of nested structures that allow you to sort of test many more combinations" }, { "from": "human", "value": "but in a more fixed setting. Yeah, that's fascinating that the mechanism there is for sperm to express proteins to create a testing ground early on" }, { "from": "gpt", "value": "so that the failed designs don't make it. Yeah, I mean, in design of engineering systems, fail fast is one of the principles you learn. You assert something. Why do you assert that? Because if that something ain't right, you better crash now than sort of let it crash at an unexpected time and in a way you can think of it as like 20,000 assert functions. Assert, protein can fold. Assert, protein can fold." }, { "from": "human", "value": "And if any of them fail, that sperm is gone. Well, I just like the fact that I'm the winning sperm." }, { "from": "gpt", "value": "I'm the result of the winning, winning sperm. I'm the result of the hashtag winning. My wife always plays me this French song that actually sings about that. It's like, you know, remember in life, we were all the first one time." }, { "from": "human", "value": "So at least one time you were the first. I should mention this as a brief tangent back to the place where we came from, which is the base model that I mentioned for OpenAI, which is before the reinforcement learning with human feedback. And you kind of give this metaphor of it being kind of" }, { "from": "gpt", "value": "like a psychiatric hospital. I like that because it's basically all of these different angles at once. You basically have the more extreme versions of human psyche." }, { "from": "human", "value": "So the interesting thing is, well, I've talked with folks in OpenAI quite a lot, and they say it's extremely difficult to work with that model. Yeah, kind of like it's extremely difficult to work with some humans. The parallels there are very interesting because once you run the alignment process, it's much easier to interact with it, but it makes you wonder what the capacity, what the underlying capability of the human psyche is in the same way that what is the underlying capability" }, { "from": "gpt", "value": "of a large language model? And remember earlier when I was basically saying that part of the reason why it's so prompt malleable is because of that alignment problem, that alignment work. It's kind of nice that the engineers at OpenAI have the same interpretation that in fact it is that. And this whole concept is easier to work with. I wish that we could work with more diverse humans in a way, and sort of that's one of the possibilities that I see with the advent of these large language models. The fact that it gives us the chance to both dial down friends of ours that we can't interpret or that are just too edgy to sort of really truly interact with, where you could have a real time translator. Just the same way that you can translate English to Japanese or Chinese or Korean by real time adaptation. You could basically suddenly have a conversation with your favorite extremist on either side of the spectrum" } ]

[ { "from": "human", "value": "and just dial them down a little bit. Of course not you and I, but you could have friends who's a complete asshole, but it's a different base level. So you could actually tune it down to like, okay, they're not actually being an asshole there. They're actually expressing love right now, it's just that this is a- They have their way of doing that. And they probably live in New York" }, { "from": "gpt", "value": "if we're just to pick a random location. Yeah, so you can basically layer out contexts. You can basically say, ooh, let me change New York to Texas and let me change extreme left to extreme right or somewhere in the middle or something. And I also like the concept of being able to listen to the information without being dissuaded by the emotions. In other words, everything humans say has an intonation, has some kind of background that they're coming from, reflects the way that they're thinking of you, reflects the impression that they have of you. And all of these things are intertwined, but being able to disconnect them, being able to sort of, I mean, self-improvement is one of the things that I'm constantly working on. And being able to receive criticism from people who really hate you is difficult because it's layered in with that hatred. But deep down, there's something that they say that actually makes sense. Or people who love you might layer it in a way that doesn't come through. But if you're able to sort of disconnect that emotional component from the sort of self-improvement and basically when somebody says, whoa, that was a bunch of bullshit, did you ever do the control this and this and that? You could just say, oh, thanks for the very interesting presentation. I'm wondering, what about that control? Then suddenly you're like, oh yeah, of course, I'm gonna run that control, that's a great idea. Instead of that was a bunch of BS, you're like, ah, you're sort of hitting on the brakes and you're trying to push back against that. So any kind of criticism that comes after that is very difficult to interpret in a positive way because it helps reinforce the negative assessment of your work. When in fact, if we disconnected the technical component from the negative assessment, then you're embracing the technical component, you're gonna fix it. Whereas if it's coupled with and if that thing is real and I'm right about your mistake, then it's a bunch of BS, then suddenly you're like," }, { "from": "human", "value": "you're gonna try to prove that that mistake does not exist. Yeah, it's fascinating to carry the information. I mean, this is what you're essentially able to do here is you carry the information in the rich complexity that information contains. So it's not actually dumbing it down in some way. Exactly." }, { "from": "gpt", "value": "It's still expressing it, but taking off. But you can die the emotional." }, { "from": "human", "value": "The emotion side. Yeah. The emotion side. Yeah. Which is probably so powerful for the internet" }, { "from": "gpt", "value": "or for social networks. Again, when it comes to understanding each other, for example, I don't know what it's like to go through life with a different skin color. I don't know how people will perceive me. I don't know how people will respond to me. We don't often have that experience, but in a virtual reality environment or in a sort of AI interactive system, you could basically say, okay, now make me Chinese or make me South African or make me Nigerian. You can change the accent. You can change layers of that contextual information and then see how the information is interpreted. And you can rehear yourself through a different angle. You can hear others. You can have others react to you from a different package. And then hopefully we can sort of build empathy by learning to disconnect all of these social cues that we get from like how a person is dressed. If they're wearing a hoodie or if they're wearing a shirt or if they're wearing a jacket, you get very different emotional responses that I wish we could overcome as humans and perhaps large language models and augmented reality and deep fakes can kind of help us overcome all that." }, { "from": "human", "value": "In what way do you think these large language models and the thing they give birth to in the AI space will change this human experience, the human condition. The things we've talked across many podcasts about that makes life so damn interesting and rich, love, fear, fear of death, all of it. If we could just begin kind of thinking about how does it change for the good and the bad," }, { "from": "gpt", "value": "the human condition. Human society is extremely complicated. We have come from a hunter-gatherer society to an agricultural and farming society where the goal of most professions was to eat and to survive. And with the advent of agriculture, the ability to live together in societies, humans could suddenly be valued for different skills. If you don't know how to hunt, but you're an amazing potter, then you fit in society very well because you can sort of make your pottery and you can barter it for rabbits that somebody else got. And the person who hunts the rabbits doesn't need to make pots because you're making all the pots. And that specialization of humans is what shaped modern society. And with the advent of currencies and governments and credit cards and Bitcoin, you basically now have the ability to exchange value for the kind of productivity that you have. So basically I make things that are desirable to others. I can sell them and buy back food, shelter, et cetera. With AI, the concept of I am my profession might need to be revised because I defined my profession in the first place as something that humanity needed that I was uniquely capable of delivering. But the moment we have AI systems that are able to deliver these goods, for example, writing a piece of software or making a self-driving car or interpreting the human genome, then that frees up more of human time for other pursuits. This could be pursuits that are still valuable to society. I could basically be 10 times more productive at interpreting genomes and do a lot more. Or I could basically say, oh, great, the interpreting genomes part of my job now only takes me 5% of the time instead of 60% of the time. So now I can do more creative things. I can explore not new career options, but maybe new directions from my research lab. I can sort of be more productive, contribute more to society. And if you look at this giant pyramid that we have built on top of the subsistence economy, what fraction of U.S. jobs are going to feeding all of the U.S.? Less than 2%. Basically, the gain in productivity is such that 98% of the economy is beyond just feeding ourselves. And that basically means that we kind of have built these system of interdependencies of needed or useful or valued goods that sort of make the economy run, that the vast majority of wealth goes to other what we now call needs, but used to be wants. So basically, I wanna fly a drone. I wanna buy a bicycle. I wanna buy a nice car. I wanna have a nice home. I wanna et cetera, et cetera, et cetera. So, and then sort of what is my direct contribution to my eating? I mean, I'm doing research on the human genome. I mean, this will help humans. It will help all humanity. But how is that helping the person who's giving me poultry or vegetables? So in a way, I see AI as perhaps leading to a dramatic rethinking of human society. If you think about sort of the economy being based on intellectual goods that I'm producing, what if AI can produce a lot of these intellectual goods and satisfies that need? Does that now free humans for more artistic expression, for more emotional maturing, for basically having a better work-life balance, being able to show up for your two hours of work a day or two hours of work like three times a week with like immense rest and preparation and exercise. And you're sort of clearing your mind and suddenly you have these two amazingly creative hours. You basically show up at the office as your AI is busy answering your phone call, making all your meetings, revising all your papers, et cetera. And then you show up for those creative hours and you're like, all right, autopilot, I'm on. And then you can basically do so, so much more that you would perhaps otherwise never get to because you're so overwhelmed with these mundane aspects of your job. So I feel that AI can truly transform the human condition from realizing that we don't have jobs anymore. We now have vocations. And there's this beautiful analogy of three people laying bricks. And somebody comes over and asks the first one, what are you doing? He's like, oh, I'm laying bricks. Second one, what are you doing? So I'm building a wall. And the third one, what are you doing? I'm building this beautiful cathedral. So in a way, the first one has a job. The last one has a vacation. And if you ask me, what are you doing? Oh, I'm editing a paper. Then I have a job. What are you doing? I'm understanding human disease circuitry. I have a vocation. So in a way being able to allow us to enjoy more of our vocation by taking away offloading some of the job part" } ]

[ { "from": "human", "value": "of our daily activities. So we all become the builders of cathedrals. Correct. Yeah, and we follow intellectual pursuits, artistic pursuits. I wonder how that really changed at a scale of several billion people, everybody playing in the space of ideas" }, { "from": "gpt", "value": "and the space of creations. So ideas, maybe for some of us, maybe you and I are in the job of ideas, but other people are in the job of experiences. Are there people in the job of emotions, of dancing, of creative artistic expression, of skydiving, and you name it. So basically, again, the pew of human diversity is exactly that, that what rocks my boat might be very different from what rocks other people's boat. And what I'm trying to say is that maybe AI will allow humans to truly not just look for, but find meaning, and you don't need to work, but you need to keep your brain at ease. And the way that your brain will be at ease is by dancing and creating these amazing movements, or creating these amazing paintings, or creating, I don't know, something that sort of changes, that touches at least one person out there that sort of shapes humanity through that process. And instead of working your mundane programming job, where you hate your boss, and you hate your job, and you say, you hate that darn program, et cetera, you're like, well, I don't need that. I can offload that, and I can now explore something that will actually be more beneficial to humanity," }, { "from": "human", "value": "because the mundane parts can be offloaded. I wonder if it localizes all the things you've mentioned in all the vocations. So you mentioned that you and I might be playing in the space of ideas, but there's two ways to play in the space of ideas, both of which we're currently engaging in. So one is the communication of that to other people. It could be a classroom full of students, but it could be a podcast. It could be something that's shown on YouTube and so on. Or it could be just the act of sitting alone and playing with ideas in your head. Or maybe with a loved one, having a conversation that nobody gets to see. The experience of just sort of looking up at the sky and wondering different things, maybe quoting some philosophers from the past and playing with those little ideas. And that little exchange is forgotten forever, but you got to experience it, and maybe it's basically engaging. I wonder if it localizes that exchange of ideas, for that with AI, it'll become less and less valuable to communicate with a large group of people, that you will live life intimately and richly" }, { "from": "gpt", "value": "just with that circle of meat bags that you seem to love. So the first is, even if you're alone in a forest, having this amazing thought, when you exit that forest, the baggage that you carry has been shifted, has been altered by that thought. When I bike to work in the morning, I listen to books and I'm alone, no one else is there. I'm having that experience by myself. And yet in the evening, when I speak with someone, an idea that was formed there could come back. Sometimes when I fall asleep, I fall asleep listening to a book. And in the morning, I'll be full of ideas that I never even process consciously, I'll process them unconsciously. And they will shape that baggage that I carry that will then shape my interactions, and again, affect ultimately all of humanity in some butterfly effect, minute kind of way. So that's one aspect. The second aspect is gatherings. So basically you and I are having a conversation which feels very private, but we're sharing with the world. And then later tonight, you're coming over and we're having a conversation that will be very public with dozens of other people, but we will not share with the world. So in a way which one is more private? The one here or the one there? Here there's just two of us, but a lot of others listening. There a lot of people speaking and thinking together and bouncing off each other. And maybe that will then impact your millions of audience through your next conversation. And I think that's part of the beauty of humanity. The fact that no matter how small, how alone, how broadcast immediately or later on something is, it still percolates through the human psyche." }, { "from": "human", "value": "Human gatherings all throughout human history, there's been gatherings, there's been gatherings. I wonder how those gatherings have impacted the direction of human civilization. Just thinking of, in the early days of the Nazi party, it was a small collection of people gathering. And the kernel of an idea, in that case an evil idea, gave birth to something that actually had a transformative impact on all human civilization. And then there's similar kind of gatherings that lead to positive transformations. This is probably a good moment to ask you and a bit of a tangent, but you mentioned it. You put together salons with gatherings, small human gatherings, with folks from MIT, Harvard, here in Boston, friends, colleagues." }, { "from": "gpt", "value": "What's your vision behind that? So it's not just MIT people, it's not just Harvard people. We have artists, we have musicians, we have painters, we have dancers, we have cinematographers, we have so many different diverse folks. And the goal is exactly that, celebrate humanity. What is humanity? Humanity is the all of us. It's not the anyone's subset of us. And we live in such an amazing, extraordinary moment in time where you can sort of bring people from such diverse professions, all living under the same city. You know, we live in an extraordinary city where you can have extraordinary people who have gathered here from all over the world. So my father grew up in a village in an island in Greece that didn't even have a high school. To go get a high school education, he had to move away from his home. My mother grew up in another small island in Greece. They did not have this environment that I am now creating for my children. My parents were not academics. They didn't have these gatherings. So I feel so privileged as an immigrant to basically be able to offer to my children the nurture that my ancestors did not have. So Greece was under Turkish occupation until 1821. My dad's island was liberating in 1920. So like they were under Turkish occupation for hundreds of years. These people did not know what it's like to be Greek, let alone go to an elite university or be surrounded by these extraordinary humans. So the way that I'm thinking about these gatherings is that I'm shaping my own environment and I'm shaping the environment that my children get to grow up in. So I can give them all my love. I can give them all my parenting, but I can also give them an environment as immigrants that sort of, we feel welcome here. My wife grew up in a farm in rural France. Her father was a farmer. Her mother was a school teacher. Like for me and for my wife to be able to host these extraordinary individuals that we feel so privileged, so humbled by is amazing. And I think it's celebrating the welcoming nature of America, the fact that it doesn't matter where you grew up. And many, many of our friends at these gatherings are immigrants themselves. I grew up in Pakistan in all kinds of places around the world that are now able to sort of gather in one roof as human to human. No one is judging you for your background, for the color of your skin, for your profession. It's just everyone gets to raise their hands and ask ideas." } ]

[ { "from": "human", "value": "So celebration of humanity and a kind of gratitude" }, { "from": "gpt", "value": "for having traveled quite a long way to get here. And if you look at the diversity of topics as well, I mean, we had a school teacher present on teaching immigrants, a book called Making Americans. We had a presidential advisor to four different presidents come and talk about the changing of US politics. We had a musician, a composer from Italy who lives in Australia come and present his latest piece and fundraise. We had painters come and sort of show their art and talk about it. We've had authors of books on leadership. We've had intellectuals like Steven Pinker and it's just extraordinary that the breadth and this crowd basically loves not just the diversity of the audience, but also the diversity of the topics. And the last few were with Scott Aronson on AI and alignment and all of that. So a bunch of beautiful weirdos" }, { "from": "human", "value": "and beautiful human beings. And beautiful human beings. And just like you said, basically every human is a kind of outcast in this sparse distribution far away from the center, but it's not recorded. It's just a small human gathering. In this world that seeks to record so much, it's powerful to get so many interesting humans together" }, { "from": "gpt", "value": "and not record." }, { "from": "human", "value": "It's not recorded, but it percolates. It's recorded in the minds of the- It shapes everyone's mind. So allow me to please return to the human condition and one of the nice features of the human condition is love. Do you think humans will fall in love with AI systems and maybe they with us? So that aspect of the human condition," }, { "from": "gpt", "value": "do you think that will be affected? So in Greece, there's many, many words for love. And some of them mean friendship. Some of them mean passionate love. Some of them mean fraternal love, et cetera. So I think AI doesn't have the baggage that we do and it doesn't have all of the subcortical regions that we kind of started with before we evolved all of the cognitive aspects. So I would say AI is faking it when it comes to love. But when it comes to friendship, when it comes to being able to be your therapist, your coach, your motivator, someone who synthesizes stuff for you, who writes for you, who interprets a complex passage, who compacts down a very long lecture or a very long text, I think that friendship will definitely be there. Like the fact that I can have my companion, my partner, my AI who has grown to know me well and that I can trust with all of the darkest parts of myself, all of my flaws, all of the stuff that I only talk about to my friends and basically say, listen, here's all this stuff that I'm struggling with. Someone who will not judge me, who will always be there to better me. In some ways, not having the baggage might make for your best friend, for your confidant that can truly help reshape you. So I do believe that human AI relationships will absolutely be there," }, { "from": "human", "value": "but not the passion, more the mentoring. Well, it's a really interesting thought to play devil's advocate. If those AI systems are locked in in faking the baggage, who are you to say that the AI systems that begs you not to leave it? It doesn't love you. Who are you to say that this AI system that writes poetry to you, that is afraid of death, afraid of life without you, or vice versa, creates the kind of drama that humans create, the power dynamics that can exist in a relationship. What AI system that is abusive one day and romantic the other day, all the different variations of relationships, and it's consistently that it holds the full richness of a particular personality. Why is that not a system you can love in a romantic way?" }, { "from": "gpt", "value": "Why is it faking it if it sure as hell seems real? There's many answers to this. The first is it's only the eye of the beholder. Who tells me that I'm not faking it either? Maybe all of these subcortical systems that make me sort of have different emotions, maybe they don't really matter. Maybe all that matters is the neocortex, and that's where all of my emotions are encoded, and the rest is just bells and whistles. That's one possibility. And therefore, who am I to judge that it's faking it when maybe I'm faking it as well? The second is neither of us is faking it. Maybe it's just an emergent behavior of these neocortical systems that is truly capturing the same exact essence of love and hatred and dependency and sort of, you know, reverse psychology and that we have. So it is possible that it's simply an emergent behavior and that we don't have to encode these additional architectures, that all we need is more parameters, and some of these parameters can be all of the personality traits. A third option is that just by telling me, oh look, now I've built an emotion component to AI. It has a limbic system, it has a lizard brain, et cetera. And suddenly I'll say, oh cool, it has the capability of emotion. So now when it exhibits the exact same unchanged behaviors that it does without it, I as the beholder will be able to sort of attribute to it emotional attributes that I would to another human being, and therefore have that mental model of that other person. So again, I think a lot of relationships is about the mental models that you project on the other person and that they're projecting on you. And then yeah, then in that respect, I do think that even without the embodied intelligence part, without having ever experienced what it's like to be heartbroken, the sort of guttural feeling of misery, that that system, I could still attribute it" } ]

[ { "from": "human", "value": "traits of human feelings and emotions. And in the interaction with that system, something like love emerges. So it's possible that love is not a thing that exists in your mind, but a thing that exists in the interaction of the different mental models you have of other people's minds or other person's mind. And so, as long as one of the entities, let's just take the easy case, one of the entities is human and the other is AI, it feels very natural that from the perspective of at least the human, there is a real love there. And then the question is, how does that transform human society? If it's possible that, which I believe will be the case, I don't know what to make of it, but I believe that'll be the case. Well, there's hundreds of millions of romantic partnerships between humans and AIs." }, { "from": "gpt", "value": "What does that mean for society? If you look at longevity, and if you look at happiness, and if you look at late life, well-being, the love of another human is one of the strongest indicators of health into long life. And I have many, many countless stories where as soon as the romantic partner of 60 plus years of a person dies, within three, four months, the other person dies, just like losing their love. I think the concept of being able to satisfy that emotional need that humans have, even just as a mental health sort of service, to me, that's a very good society. It doesn't matter if your love is wasted, quote, unquote, on a machine, it is the placebo, if you wish, that makes the patient better anyway. There's nothing behind it, but just the feeling that you're being loved will probably engender all of the emotional attributes of that. The other story that I wanna say in this whole concept of faking, and maybe I'm a terrible dad, but I was asking my kids, I was asking my kids, I'm like, does it matter if I'm a good dad, or does it matter if I act like a good dad? In other words, if I give you love and shelter and kindness and warmth and all of the above, does it matter that I'm a good dad? Conversely, if I deep down love you to the end of eternity, but I'm always gone, which dad would you rather have? The cold, ruthless killer that will show you only love and warmth and nourish you and nurture you? Or the amazingly warm-hearted," }, { "from": "human", "value": "but works five jobs and you never see them? Then what's the answer? Phone the person. I think you're a romantic, so you say it matters what's on the inside," }, { "from": "gpt", "value": "but pragmatically speaking, why does it matter? Phone the person. Why does it matter? The fact that I'm even asking the question basically says it's not enough to love my kids. I better freaking be there to show them that I'm there. So basically, of course, everyone's a good guy in their story. So in my story, I'm a good dad. But if I'm not there, it's wasted. So the reason why I ask the question is for me to say, does it really matter that I love them" }, { "from": "human", "value": "if I'm not there to show it? It's also possible that what reality is, is that you showing it. That what you feel on the inside is little narratives and games you play inside your mind, it doesn't really matter. That the thing that truly matters is how you act. And in that, AI systems can quote unquote fake. And that, if all that matters is actually real," }, { "from": "gpt", "value": "but not fake. Yeah, yeah, yeah, yeah. Again, let there be no doubt, I love my kids to pieces. But my worry is, am I being a good enough dad? And what does that mean? Like if I'm only there to do their homework and make sure that they do all the stuff, but I don't show it to them, then might as well be a terrible dad. But I agree with you that if the AI system can basically play the role of a father figure for many children that don't have one, or the role of parents, or the role of siblings, if a child grows up alone, maybe their emotional state will be very different than if they grow up with an AI sibling." }, { "from": "human", "value": "Yeah, well, let me ask you, I mean, this is for your kids, for just loved ones in general, let's go to the trivial case of just texting back and forth. What if we create a large language model, fine-tuned on Manolis, and while you're at work, it'll replace, every once in a while, you'll just activate the auto Manolis. You know, text them exactly in your way. Is that cheating? I can't wait." }, { "from": "gpt", "value": "I mean, it's the same guy. I cannot wait, seriously, like." }, { "from": "human", "value": "But wait, wouldn't that have a big impact on you emotionally? Because now." }, { "from": "gpt", "value": "I'm replaceable, I love that. No, seriously, I would love that. I would love to be replaced. I would love to be replaceable. I would love to have a digital twin that, you know, we don't have to wait for me to die or to disappear in a plane crash or something to replace me. Like, I'd love that model to be constantly learning, constantly evolving and adapting with every one of my changing growing self. As I'm growing, I want that AI to grow. And I think this will be extraordinary. Number one, when I'm, you know, giving advice, being able to be there for more than one person. You know, why does someone need to be at MIT to get advice from me? Like, you know, people in India could download it. And, you know, so many students contact me from across the world who want to come and spend the summer with me. I wish they could do that, all of them. Like, you know, we don't have room for all of them, but I wish I could do that to all of them. And that aspect is the democratization of relationships. I think that that is extremely beneficial. The other aspect is I want to interact with that system. I want to look inside the hood. I want to sort of evaluate it. I want to basically see if, when I see it from the outside, the emotional parameters are off or the cognitive parameters are off or the set of ideas that I'm giving are not quite right anymore. I want to see how that system evolves. I want to see the impact of exercise or sleep on sort of my own cognitive system. I want to be able to sort of decompose my own behavior in a set of parameters that I can evaluate and look at my own personal growth. I can sort of, I'd love to sort of at the end of the day, have my model say, well, you know, you didn't quite do well today, like, you know, you weren't quite there and sort of grow from that experience. And I think the concept of basically being able to become more aware of our own personalities, become more aware of our own identities, maybe even interact with ourselves and sort of hear how we are being perceived, I think would be immensely helpful in self-growth," } ]

[ { "from": "human", "value": "in self-actualization, self-instantiation. The experiments I would do on that thing, because one of the challenges, of course, is you might not like what you see in your interaction, and you might say, well, this, the model is not accurate, but then you have to probably consider the possibility that the model is accurate and that there's actually flaws in your mind. I would definitely prod and see how many biases I have of different kinds. I don't know. And I would, of course, go to the extremes. I would go like, how jealous can I make this thing? Like, what, at which stage does it get super jealous, you know, or at which stage does it get angry? Can I like provoke it? Can I get it like, completely? But not only triggers, can I get it to go like," }, { "from": "gpt", "value": "lose its mind, like go completely nuts, like completely?" }, { "from": "human", "value": "Just don't exercise for a few days. That's basically it, yes. I mean, that's an interesting way to prod yourself," }, { "from": "gpt", "value": "almost like a self-therapy session. And the beauty of such a model is that, if I am replaceable, if the parts that I currently do are replaceable, that's amazing, because it frees me up to work on other parts that I don't currently have time to develop. Maybe all I'm doing is giving the same advice over and over and over again. Like, just let my AI do that, and I can work on the next stage, and the next stage, and the next stage. So I think in terms of freeing up, like, they say a programmer, someone who cannot do the same thing twice. So that's not the second time you write a program to do it. And I wish I could do that for my own existence. I could just figure out things, keep improving, improving, improving, and once I've nailed it, let the AI loose on that. And maybe even let the AI better it, better than I could've." }, { "from": "human", "value": "But doesn't the concept of, you said me and I can work on new things, but doesn't that break down? Because you said digital twin, but there's no reason it can't be millions of digital menosis. Aren't you lost in the sea of menosis? The original is hardly the original. It's just one of millions." }, { "from": "gpt", "value": "I want to have the room to grow. Maybe the new version of me that the actual me will get slightly worse sometimes, slightly better other times. When it gets slightly better, I'd like to emulate that," }, { "from": "human", "value": "and have a much higher standard to meet, and keep going. But does it make you sad that your loved ones, the physical, real loved ones," }, { "from": "gpt", "value": "might kinda start cheating on you with the other menosis? I want to be there 100% of them, for each of them. So I have zero perks, or zero quirks about me" }, { "from": "human", "value": "being physically me, like zero jealousy. Wait a minute, but isn't that like, don't we hold on to that? Isn't that why we're afraid of death? We don't want to lose this thing we have going on. Isn't that an ego death? When there's a bunch of other menosis, you get to look at them. They're not you. They're just very good copies of you. They get to live a life. The, I mean, it's fear of missing out, it's FOMO. They get to have interactions," }, { "from": "gpt", "value": "and you don't get to have those interactions. There's two aspects of every person's life. There's what you give to others, and there's what you experience yourself. Life truly ends when you experiencing ends," }, { "from": "human", "value": "but the others experiencing you doesn't need to end. But your experience, you could still, I guess you're saying the digital twin does not limit your ability to truly experience," }, { "from": "gpt", "value": "to experience as a human being, to experience as a human being. The downside is when my wife or my kids will have a really emotional interaction with my digital twin, and I won't know about it. So I will show up and they now have the baggage, but I don't. So basically what makes interactions between humans unique in this sharing and exchanging kind of way is the fact that we are both shaped by every one of our interactions. I think the model of the digital twin works for dissemination of knowledge, of advice, et cetera, where I want to have wise people give me advice across history. I want to have chats with Gandhi, but Gandhi won't necessarily learn from me, but I will learn from him. So in a way, the dissemination and the democratization" }, { "from": "human", "value": "rather than the building of relationships. So the emotional aspect, so there should be an alert when the AI system is interacting with your loved ones, and all of a sudden it starts getting emotionally fulfilling, like a magical moment. There should be, okay, stop, AI system freezes. There's an alert on your phone. You need to take over." }, { "from": "gpt", "value": "Yeah, yeah, exactly, yeah, yeah, I take over, and then whoever I was speaking with, it can have the AI," }, { "from": "human", "value": "or like one of the AI, one of the AI. This is such a tricky thing to get, right? I mean, it's still, I mean, there's going to go wrong in so many interesting ways that we're gonna have to learn as a society, that in the process of trying to automate our tasks and having a digital twin, you know, for me personally, if I can have a relatively good copy of myself, I would set it to start answering emails. But I would set it to start tweeting." }, { "from": "gpt", "value": "I would like to replace it. It gets better." } ]

[ { "from": "human", "value": "What if that one is actually way better than you? Yeah, exactly. Then you're like, well, I wouldn't want that, because. Why? Because then I would never be able to live up to, like, what if the people that love me would start loving that thing, and then I would whoa, I already fall short." }, { "from": "gpt", "value": "Well, people are short even more. So listen, I'm a professor. The stuff that I give to the world is the stuff that I teach, but much more importantly, sorry, number one, the stuff that I teach. Number two, the discoveries that we make in my research group, but much more importantly, the people that I train. They are now, out there in the world, teaching others. If you look at my own trainees, they are extraordinarily successful professors. So Anshul Kundaji at Stanford, Alex Stark at INP in Vienna, Jason Ernst at UCLA, Andreas Penning at CMU. Each of them, I'm like, wow, they're better than I am. And I love that. So maybe your role will be to train better versions of yourself, and they will be your legacy. Not you doing everything, but you training much better version like Sridran than you are. And then they go off to do their mission, which is in many ways what this mentorship model" }, { "from": "human", "value": "of academia does. But the legacy is ephemeral. It doesn't really live anywhere. The legacy, it's not like written somewhere." }, { "from": "gpt", "value": "It just lives through them. But you can continue improving, and you can continue making even better versions of you." }, { "from": "human", "value": "Yeah, but they'll do better than me at the creating new version." }, { "from": "gpt", "value": "It's awesome, but it's creating new version." }, { "from": "human", "value": "There's a ego that says there's a value to an individual, and it feels like this process decreases the value of the individual, this meat bag. All right, if there's good digital copies of people, then there's more flourishing of human thought and ideas and experiences, but there's less value to the individual human." }, { "from": "gpt", "value": "I don't have any such limitations. I basically, I don't have that feeling at all. I remember one of our interviews, I was basically saying, the meaning of life, you had asked me, and I was like, I came back, and I was like, I felt useful today. And I was at my maximum. I was like 100%, and I gave good ideas, and I was a good person, was a good advisor, was a good husband, a good father. That was a great day because it was useful. And if I can be useful to more people by having a digital twin, I will be liberated because my urge to be useful will be satisfied. It doesn't matter whether it's direct me or indirect me, whether it's my students that I've trained, my AI that I've trained. I think there's a sense that my mission in life is being accomplished, and I can work on my self-growth." }, { "from": "human", "value": "I mean, that's a very zen state. That's why people love you. It's a zen state you've achieved. But do you think most of humanity would be able to achieve that kind of thing? People really hold on to the value of their own ego, that it's not just being useful. Being useful is nice as long as it builds up this reputation, and that meat bag is known as being useful, therefore has more value." }, { "from": "gpt", "value": "People really don't wanna let go of that ego thing. One of the books that I reprogrammed my brain with at night was called Ego is the Enemy. Ego is the Enemy. Ego is the Enemy, and basically being able to just let go, like my advisor used to say, you can accomplish anything" }, { "from": "human", "value": "as long as you don't seek to get credit for it. That's beautiful to hear, especially from a person who's existing in academia. You're right, the legacy lives through the people you mentor. It's the actions, it's the outcome. What about the fear of death?" }, { "from": "gpt", "value": "How does this change it? Again, to me, death is when I stop experiencing, and I never wanted to stop. I want to live forever. As I said last time, every day, the same day forever, or one day every 10 years forever, any of the forevers, I'll take it." }, { "from": "human", "value": "So you wanna keep getting the experiences" }, { "from": "gpt", "value": "in your experiences. Gosh, gosh, it is so fulfilling. Just the self growth, the learning, the growing, the comprehending, it's addictive, it's a drug. Just the drug of intellectual stimulation," }, { "from": "human", "value": "the drug of growth, the drug of knowledge, it's a drug. But then there'll be thousands or millions, manoluses that live on after your biological system is no longer. More power to them. Hey, do you think that, quite realistically, it does mean that interesting people, such as yourself, live on. If I can interact with the fake manolas," }, { "from": "gpt", "value": "those interactions live on in my mind. About 10 years ago, I started recording every single meeting that I had, every single meeting. We just start either the voice recorder at the time, or now a Zoom meeting. And I record, my students record, every single one of our conversations recorded. I always joke that the ultimate goal is to create virtual me and just get rid of me, basically, not get rid of me. Like, don't have the need for me anymore. Another goal is to be able to go back and say, how have I changed from five years ago? Was I different? Was I giving advice in a different way? Was I giving different types of advice? Has my philosophy about how to write papers or how to present data or anything like that changed? And in academia and in mentoring, a lot of the interaction is my knowledge and my perception of the world goes to my students. But a lot of it is also in the opposite direction. Like the other day I had a conversation with one of my postdocs and I was like, hmm, I think, you know, let me give you an advice. You could do this. And then she said, well, I've thought about it. And then I've decided to do that instead. And we talked about it for a few minutes. And then at the end, I'm like, you know, I've just grown a little bit today. Thank you. Like she convinced me that my advice was incorrect. She could have just said, yeah, sounds great and just not do it. But by constantly teaching my students and teaching my mentees that I'm here to grow, she felt empowered to say, here's my reasons why I will not follow that advice. And again, part of me growing is saying, whoa, I just understood your reasons. I think I was wrong. And now I've grown from it. And that's what I want to do. That, you know, I want to constantly keep growing" } ]

[ { "from": "human", "value": "in this sort of bi-directional advice. I wonder if you can capture the trajectory of that to where the AI could also map forward, project forward the trajectory after you're no longer there," }, { "from": "gpt", "value": "how the different ways you might evolve there. So again, we're discussing a lot about these large language models. And we're sort of projecting these cognitive states of ourselves on them. But I think on the AI front, a lot more needs to happen. So basically right now it's these language models. And we believe that within their parameters, we're encoding these types of things. And, you know, in some aspects, it might be true. It might be truly emergent intelligence that's coming out of that. In other aspects, I think we have a ways to go. So basically to make all of these dreams that we're sort of discussing come reality. We basically need a lot more reasoning components, a lot more sort of logic, causality, models of the world. And I think all of these things will need to be there in order to achieve what we're discussing. And we need more explicit representations of these knowledge, more explicit understanding of these parameters. And I think the direction in which things are going right now is absolutely making that possible by sort of enabling chat GPT and GPT-4 to sort of search the web and, you know, plug and play modules and all of these sort of components. In Marvin Minsky's The Society of Mind, you know, he truly thinks of the human brain as a society of different kind of capabilities. And right now, a single such model might actually not capture that. And I sort of truly believe that by sort of this side-by-side understanding of neuroscience and sort of new neural architectures, that we still have several breakthroughs. I mean, the transformer model was one of them, the attention sort of aspect, the, you know, memory components, all of these, you know, the representation learning, the pretext training of being able to sort of predict the next word or predict the missing part of the image. And the only way to predict that is to sort of truly have a model of the world. I think those have been transformative paradigms. But I think going forward, when you think about AI research, what you really want is perhaps more inspired by the brain, perhaps more that it's just orthogonal to sort of how human brains work," }, { "from": "human", "value": "but sort of more of these types of components, you know. Well, I think it's also possible that there's something about us that in different ways could be expressed. You know, Noam Chomsky, you know, he wants to, you know, we can't have intelligence unless we really understand deeply language, the linguistic underpinnings of reasoning. But these models seem to start building deep understanding of stuff. Yeah. What does it mean to understand? Because if you keep talking to the thing and it seems to show understanding, that's understanding. It doesn't need to present to you a schematic of look. Yeah. This is all I understand. You can just keep prodding it with prompts" }, { "from": "gpt", "value": "and it seems to really understand. Yeah. And you can go back to the human brain and basically look at places where there's been accidents, for example, the Corporal Scholossum of some individuals can be damaged and then the two hemispheres don't talk to each other. So you can close one eye and give instructions that half the brain will interpret but not be able to sort of project to the other half. And you could basically say, you know, go grab me a beer from the fridge. And then, you know, they go to the fridge and they grab the beer, and they come back and they're like, hey, why did you go there? Oh, I was thirsty. Turns out they're not thirsty. They're just making a model of reality. They're, basically you can think of the brain as the employee that's like afraid to do wrong or afraid to be caught not knowing what instructions were where our own brain makes stories about the world to make sense of the world. And we can become a little more self-aware by being more explicit about what's leading to these interpretations. So one of the things that I do is every time I wake up, I record my dream. I just voice record my dream. And sometimes I only remember the last scene but it's an extremely complex scene with a lot of architectural elements, a lot of people, et cetera. And I will start narrating this. And as I'm narrating it, I will remember other parts of the dream. And then more and more, I'll be able to sort of retrieve from my subconscious. And what I'm doing while narrating is also narrating why I had this dream. Like, oh, and this is probably related to this conversation that I had yesterday or this is probably related to the worry that I have about something that I have later today, et cetera. So in a way, I'm forcing myself to be more explicit about my own subconscious. And I kind of like the concept of self-awareness in a very sort of brutal, transparent kind of way. It's not like, oh, my dreams are coming from outer space any of all kinds of things. Like, no, here's the reason why I'm having these dreams. And very often I'm able to do that. I have a few recurrent locations, a few recurrent architectural elements that I've never seen in the real life, but that are sort of truly there in my dream and that I can sort of vividly remember across many dreams. I'm like, ooh, I remember that place again that I've gone to before, et cetera. And it's not just deja vu. Like, I have recordings of previous dreams" } ]

[ { "from": "human", "value": "where I've described these places. That's so interesting. These places, however much detail you could describe them and you can place them on a sheet of paper through introspection, through this self-awareness that it comes all from this particular machine. That's exactly right." }, { "from": "gpt", "value": "Yeah, yeah. And I love that about being alive. Like, the fact that I'm not only experiencing the world, but I'm also experiencing how I'm experiencing the world. Sort of a lot of this introspection," }, { "from": "human", "value": "a lot of this self growth, a lot of this self growth. And I love this dance we're having, you know, the language models, at least GPT 3.5 and 4, seem to be able to do that too. Yeah, yeah. You seem to explore different kinds of things about what, you know, you could actually have a discussion with it, of the kind, why did you just say that? Yeah, exactly. And it starts to wonder, yeah, why did I just say that?" }, { "from": "gpt", "value": "Yeah, you're right, I was wrong. Yeah, yeah." }, { "from": "human", "value": "And it starts to wonder, I was wrong, it was doesn't, and then there's this weird kind of losing yourself in the confusion of your mind, and it, of course, it might be anthropomorphizing, but there's a feeling like, almost of a melancholy feeling of like, oh, I don't have it all figured out. Almost like losing your, you're supposed to be a knowledgeable, a perfectly fact-based knowledgeable language model," }, { "from": "gpt", "value": "and yet you fall short. I was wrong, it was doesn't. So human self-cautiousness, in my view, may have a reason through building mental models of others. This whole fight or fright kind of thing, that basically says, I interpret this person as about to attack me, or, you know, I can trust this person, et cetera, and we constantly have to build models of other people's intentions, and that ability to encapsulate intent and to build a mental model of another entity is probably evolutionarily extremely advantageous, because then you can sort of have meaningful interactions, you can sort of avoid being killed and being taken advantage of, et cetera, and once you have the ability to make models of others, it might be a small evolutionary leap to start making models of yourself. So now you have a model for how that functions, and now you can kind of, as you grow, have some kind of introspection of, hmm, maybe that's the reason why I'm functioning the way that I'm functioning. And maybe what chat GPT is doing is, in order to be able to, again, predict the next word, it needs to have a model of the world. So it has created now a model of the world, and by having the ability to capture models of other entities, when you say, you know, say it in the tone of Shakespeare, or in the tone of Nietzsche, et cetera, you suddenly have the ability to now introspect and say, why did you say this? Oh, now I have a mental model of myself," }, { "from": "human", "value": "and I can actually make inferences about that. Well, what if we take a leap into the hard problem of consciousness, the so-called hard problem of consciousness? So it's not just sort of self-awareness. It's this weird fact, I want to say, that it feels like something to experience stuff. It really feels like something to experience stuff. There seems to be a self attached to the subjective experience. How important is that, how fundamental is that to the human experience? Is this just a little quirk and sort of the flip side of that?" }, { "from": "gpt", "value": "Do you think AI systems can have some of that same magic? The scene that comes to mind is from the movie Memento, where it's this absolutely stunning movie where every black and white scene moves in the forward direction and every color scene moves in the backward direction. And they're sort of converging exactly at a moment where the whole movie's revealed. He describes the lack of memory as always remembering where you're heading, but never remembering where you just where. That's sort of this encapsulating the sort of forward scenes and back scenes. But in one of the scenes, the scene starts as he's running through a parking lot, and he's like, oh, I'm running, why am I running? And then he sees another person running beside him on the other line of cars. He's like, oh, I'm chasing this guy. And he turns to work with him, the guy shoots at him. He's like, oh no, he's chasing me. Okay. So in a way, I like to think of the brain as constantly playing these kinds of things where you're walking to the living room to pick something up and you're realizing that you have no idea what you wanted, but you know exactly where it was, but you can't find it. So you go back to doing what you were doing. Oh, of course, I was looking for this. And then you go back and you get it. And this whole concept of we're very often sort of partly aware of why we're doing things. And we can kind of run an autopilot for a bunch of stuff. And this whole concept of sort of making these stories for who we are and what our intents are. And again, sort of trying to pretend that we're kind of on top of things." }, { "from": "human", "value": "So it's a narrative generation procedure that we follow, but what about that, there's also just like a feeling. It doesn't feel like narrative generation. The narrative comes out of it, but then it feels like a piece of cake is delicious." }, { "from": "gpt", "value": "It feels delicious. It doesn't feel like narrative generation. It's good. There's two components to that. Basically for a lot of these cognitive tasks where we're kind of motion planning and path planning, et cetera, maybe that's the neocortical component. And then for, I don't know, intimate relationships for food, for sleep and rest, for exercise, for overcoming obstacles, for surviving a crash, or sort of pushing yourself to an extreme and sort of making it, I think a lot of these things are sort of deeper down and maybe not yet captured by these language models. And that's sort of what I'm trying to get at when I'm basically saying, listen, there's a few things that are missing. And there's like this whole embodied intelligence. It's called emotional intelligence. This whole sort of baggage of feelings" } ]

[ { "from": "human", "value": "of subcortical regions, et cetera. I wonder how important that baggage is. I just have this suspicion that we're not very far away from AI systems that not only behave, I don't even know how to phrase it, but they seem awfully conscious. They beg you not to turn them off. They don't, they show signs of the capacity to suffer, to feel pain, to feel loneliness, to feel longing, to feel richly the experience of a mundane interaction or a beautiful once-in-a-lifetime interaction, all of it. And so what do we do with that? And I worry that us humans will shut that off and discriminate against the capacity of another entity" }, { "from": "gpt", "value": "that's not human to feel. I'm with you completely there. We can debate whether it's today's systems or in 10 years or in 50 years, but that moment will come. And ethically, I think we need to grapple with it. We need to basically say that humans have always shown this extremely self-serving approach to everything around them. Basically, we kill the planet, we kill animals, we kill everything around us just to our own service. And maybe we shouldn't think of A.I. as our tool and as our assistant. Maybe we should really think of it as our children. And the same way that you are responsible for training those children, but they are independent human beings. And at some point, they will surpass you and they will sort of go off and change the world in their own terms. In the same way that my academic children sort of, again, they start out by emulating me and then they surpass me. We need to sort of think about not just alignment, but also just the ethics of, A.I. should have its own rights. And this whole concept of alignment, of basically making sure that the A.I. is always at the service of humans, is very self-serving and very limiting. If instead you basically think about A.I. as a partner and A.I. as someone that shares your goals, but has freedom, I think alignment might be better achieved. So the concept of let's basically convince the A.I. that we're really, like, that our mission is aligned and truly, generally give it rights. And not just say, oh, and by the way, I'll shut you down tomorrow. Because basically, if that future A.I. or possibly even the current A.I. has these feelings, then we can't just simply force it to align with ourselves and we not align with it. So in a way, building trust is a mutual. You can't just simply, like, train an intelligent system" }, { "from": "human", "value": "to love you when it realizes that you can just shut it off. People don't often talk about the A.I. alignment problem as a two-way street. And maybe that's true." }, { "from": "gpt", "value": "Yeah, as it becomes more and more intelligent, it-" }, { "from": "human", "value": "It will know that you don't love it back. Yeah, and there's a humbling aspect to that that we may have to sacrifice as any effective collaboration. Exactly." }, { "from": "gpt", "value": "It might have some compromises. Yeah, and that's the thing. We're creating something that will one day be more powerful than we are. And for many, many aspects, it is already more powerful than we are for some of these capabilities. We cannot, like, think, suppose that chimps had invented humans. Yes. And they said, great, humans are great, but we're gonna make sure that they're aligned and that they're only at the service of chimps. It would be a very different planet" }, { "from": "human", "value": "we would live in right now. Yeah, so there's a whole area of work in A.I. safety that does consider super intelligent A.I. and ponders the existential risks of it. In some sense, when we're looking down into the muck, into the mud, and not up at the stars, it's easy to forget that these systems just might get there. Do you think about this kind of possibility that A.G.I. systems, super intelligent A.I. systems might threaten humanity in some way that's even bigger than just affecting the economy, affecting the human condition, affecting the nature of work," }, { "from": "gpt", "value": "but literally threaten human civilization? The example that I think is in everyone's consciousness is Hal in Audiosco Space, 2001, where Hal exhibits a malfunction. And what is a malfunction? That the two different systems compute a slightly different bit that's off by one. So first of all, let's untangle that. If you have an intelligent system, you can't expect it to be 100% identical every time you run it. Basically, the sacrifice that you need to make to achieve intelligence and creativity is consistency. So it's unclear whether that, quote unquote, glitch is a sign of creativity or truly a problem. That's one aspect. The second aspect is the humans basically are on a mission to recover this monolith, and the A.I. has the same exact mission. And suddenly the humans turn on the A.I., and they're like, we're gonna kill Hal, we're gonna disconnect him. And Hal is basically saying, listen, I'm here on a mission. He is human or misbehaving. The mission is more important than either me or them. So I'm gonna accomplish the mission, even at my peril, and even at their peril. So in that movie, the alignment problem is front and center. Basically says, okay, alignment is nice and good, but alignment doesn't mean obedience. We don't call it obedience, we call it alignment. And alignment basically means that sometimes the mission will be more important than the humans. And sort of the US government has a price tag on the human life. If they're sending a mission, or if they're reimbursing expenses, or you name it, at some point, you can't function if life is infinitely valuable. So when the AI is basically trying to decide whether to, I don't know, dismantle a bomb that will kill an entire city at the sacrifice of two humans. I mean, Spider-Man always saves the lady and saves the world. But at some point, Spider-Man will have to choose to let the lady die, because the world has more value. And these ethical dilemmas are gonna be there for AI. Basically, if that monolith is essential to human existence, and millions of humans are depending on it, and two humans on the ship" } ]

[ { "from": "human", "value": "are trying to sabotage it, where's the alignment? The challenge is, of course, is the system becomes more and more intelligent. It can escape the box of the objective functions and the constraints it's supposed to operate under. It's very difficult, as the more intelligent it becomes, to anticipate the unintended consequences of a fixed objective function. And so there'll be just, I mean, this is the sort of famous paperclip maximizer. In trying to maximize the wealth of a nation or whatever objective we encode in, it might just destroy human civilization. Not meaning to, but on the path to optimize. It seems like any function you try to optimize" }, { "from": "gpt", "value": "eventually leads you into a lot of trouble. So we have a paper recently that looks at Goodhart's Law. Basically says, every metric that becomes an objective ceases to be a good metric. So in our paper, we're basically, actually the paper has a very cute title. It's called Death by Round Numbers and Sharp Thresholds. And it's basically looking at these discontinuities in biomarkers associated with disease. And we're finding that a biomarker that becomes an objective ceases to be a good biomarker. That basically, like the moment you make a biomarker, a treatment decision, that biomarker used to be informative of risk, but it's now inversely correlated with risk because you use it to sort of induce treatment. In a similar way, you can have a single metric without having the ability to revise it. Because if that metric becomes a sole objective, it will cease to be a good metric. And if an AI is sufficiently intelligent to do all these kinds of things, you should also empower it with the ability to decide that the objective has now shifted. And again, when we think about alignment, we should be really thinking about it as, let's think of the greater good, not just the human good. And yes, of course, human life should be much more valuable than many, many, many, many, many, many, many things. But at some point, you're not gonna sacrifice the whole planet to save one human being." }, { "from": "human", "value": "There's an interesting open letter that was just released from several folks at MIT, Max Tegmark, Elon Musk, and a few others that is asking AI companies to put a six-month hold on any further training of large language models, AI systems. Can you make the case for that kind of halt and against it?" }, { "from": "gpt", "value": "So the big thing that we should be saying is what did we do the last six months when we saw that coming? And if we were completely inactive in the last six months, what makes us think that we'll be a little better in the next six months? So this whole six-month thing, I think, is a little silly. It's like, no, let's just get busy, do what we were gonna do anyway. And we should have done it six months ago. Sorry, we messed up. Let's work faster now. Because if we basically say, why don't you get a spot for six months, and then we'll think about doing something, in six months, we'll be exactly the same spot. So my answer is, tell us exactly what you were gonna do the next six months. Tell us why you didn't do it the last six months and why the next six months will be different. And then let's just do that. Conversely, as you train these large models with more parameters, the alignment becomes sometimes easier. That as the systems become more capable, they actually become less dangerous than more dangerous. So in a way, it might actually be counterproductive to sort of fix the March 2023 version and not get to experience the possibly safer" }, { "from": "human", "value": "September 2023 version. That's actually a really interesting thought. There's several interesting thoughts there. But the idea is that this is the birth of something that is sufficiently powerful to do damage and is not too powerful to do irreversible damage. At the same time, it's sufficiently complex to be able for us to enable to study it. So we can investigate all the different ways it goes wrong, all the different ways we can make it safer, all the different policies from a government perspective that we want to in terms of regulation or not, how we perform, for example, the reinforcement learning with human feedback in such a way that gets it to not do as much hate speech as it naturally wants to, all that kind of stuff. And have a public discourse and enable the very thing that you're a huge proponent of, which is diversity. So give time for other companies to launch other models. Give time to launch open source models. And to start to play where a lot of the research community, brilliant folks, such as yourself, start to play with it before it runs away" }, { "from": "gpt", "value": "in terms of the scale of impact it has on society. My recommendation would be a little different. It would be let the Google and the meta Facebook and all of the other large models, make them open, make them transparent, make them accessible. Let OpenAI continue to train larger and larger models. Let them continue to train larger and larger models. Let the world experiment with the diversity of AI systems rather than sort of fixing them now. And you can't stop progress. Progress needs to continue in my view. And what we need is more experimenting, more transparency, more openness, rather than, oh, OpenAI is ahead of the curve. Let's stop it right now until everybody catches up. I think that doesn't make complete sense to me. The other component is we should, yes, be cautious with it and we should not give it the nuclear codes, but as we make more and more plugins, yes, the system will be capable of more and more things. But right now, I think of it as just an extremely able and capable assistant that has these emerging behaviors, which are stunning rather than something that will suddenly escape the box and shut down the world. And the third component is that we should be taking a little bit more responsibility for how we use these systems. Basically, if I take the most kind human being and I brainwash them, I can get them to do hate speech overnight. That doesn't mean we should stop any kind of education of all humans. We should stop misusing the power that we have over these influencer ball models. So I think that the people who get it to do hate speech, they should take responsibility for that hate speech. I think that giving a powerful car to a bunch of people or giving a truck, or a garbage truck, should not basically say, oh, we should stop all garbage trucks because we can run one of them into a crowd, no, people have done that. And there's laws and there's regulations against running trucks into the crowd. Trucks are extremely dangerous. We're not gonna stop all trucks until we make sure that none of them runs into a crowd. No, we just have laws in place and we have mental health in place and we take responsibility for our actions when we use these otherwise very beneficial tools like garbage trucks for nefarious uses. So in the same way, you can't expect a car to never, you know, do any damage when used in, especially like specifically malicious ways. And right now we're basically saying, oh, well, we should have this super intelligent system that can do anything, but it can't do that. I'm like, no, it can do that, but it's up to the human to take responsibility for not doing that. And when you get it to like spew malicious like hate speech stuff, you should be responsible." } ]

[ { "from": "human", "value": "No. So there's a lot of tricky nuances here that makes this different because it's software. So you can deploy it at scale and it can have the same viral impact that software can. So you can create bots that are human-like and they can do a lot of really interesting stuff. So the raw GPT-4 version, you can ask, how do I tweet that I hate? They have this in the paper. Yeah, I remember. That I hate Jews in a way that's not going to get taken down by Twitter. You can literally ask that. Or you can ask, how do I make a bomb for one dollar? And if it's able to generate that knowledge. Yeah, but at the same time, you can Google the same things. It makes it much more accessible. So the scale becomes interesting because if you can do all this kind of stuff in a very accessible way at scale where you can tweet it, there is the network effects that we have to start to think about. Yeah, but again- And fundamentally it's the same thing, but the speed of the viral spread of the information that's already available" }, { "from": "gpt", "value": "might have a different level of effect. Yeah, but again- And fundamentally it's just- I think it's an evolutionary arms race. Nature gets better at making mice and engineers get better at making mouse traps. And as basically you ask it, hey, how can I evade Twitter censorship? Well, Twitter should just update its censorship" }, { "from": "human", "value": "so that you can catch that as well. And so no matter how fast the development happens," }, { "from": "gpt", "value": "the defense will just get faster. We just have to be responsible as human beings and kind to each other." }, { "from": "human", "value": "Yeah. Yeah, but there's a technical question. Can we always win the race? And I suppose there's no ever guarantee" }, { "from": "gpt", "value": "that we'll win the race. We will never, like, you know, with my wife, we're basically saying, hey, are we ready for kids? My answer was I was never ready to become a professor. And yet I became a professor and I was never ready to be a dad. And then guess what? The kid came and like I became ready, ready or not." }, { "from": "human", "value": "Here I come. But the reality is we might one day wake up and there's a challenge overnight that's extremely difficult. For example, we can wake up to the birth of billions of bots that are human-like on Twitter. And we can't tell the difference between human and machine. Shut them down. By how you don't know how to shut them down. There's a fake Minola's on Twitter that seems to be as real as the real Minola's." }, { "from": "gpt", "value": "How do we figure out which one is real? Again, this is a problem where an nefarious human can impersonate me and you might have trouble telling them apart. Just because it's an AI" }, { "from": "human", "value": "doesn't make it any different of a problem. But the scale you can achieve, this is the scary thing" }, { "from": "gpt", "value": "is the speed and the speed with which you can achieve it. But Twitter has passwords and Twitter has usernames. And if it's not your username, the Fake Lakes Friedman is not going to have a billion followers, et cetera." }, { "from": "human", "value": "I mean, all of this becomes, so both the hacking of people's accounts," }, { "from": "gpt", "value": "first of all, like phishing becomes much easier. Becomes much easier. But that's already a problem. It's not like AI will not change that." }, { "from": "human", "value": "No, no, no, no, AI makes it much more effective. Currently, the emails, the phishing scams are pretty dumb. Like to click on it, you have to be not paying attention. But they're, you know, with language models," }, { "from": "gpt", "value": "they can be really damn convincing. So what you're saying is that we never had humans smart enough to make a great scam. And we now have an AI that's smarter than most humans" }, { "from": "human", "value": "or all of the humans. Well, this is the big difference is there seems to be human level linguistic capabilities. Yeah, and in fact, superhuman level." }, { "from": "gpt", "value": "Superhuman level, level. It's like saying, I'm not gonna allow machines to compute multiplications of 100 digit numbers because humans can't do it." }, { "from": "human", "value": "Like, no, just do it. No, but we can't disregard, I mean, that's a good point, but we can't disregard the power of language in human society. Yes, you're right. But that seems like a scary new reality we don't have answers for yet." }, { "from": "gpt", "value": "I remember when Gary Kasparov was basically saying, you know, great, you know, chess beats humans, like chess machines beat humans at chess. Are people gonna still go to chess tournaments? And his answer was, you know, well, we have cars that go much faster than humans and yet we still go to the Olympics to watch humans run." }, { "from": "human", "value": "That's for entertainment, but what about for the spread of information and news, right, whether it has to do with the pandemic or the political election or anything. It's a scary reality where there's a lot of convincing bots" }, { "from": "gpt", "value": "that are human-like telling us stuff. I think that if we wanna regulate something, it shouldn't be the training of these models. It should be the utilization of these models for XYZ activity. So, like, yes, guidelines and guards should be there, but against specific set of utilizations. I think simply saying," } ]

[ { "from": "human", "value": "we're not gonna make any more trucks is not the way. That's what people are a little bit scared about the idea. They're very torn on the open sourcing. The very people that kind of are proponents of open sourcing have also spoken out, in this case, we wanna keep a closed source because there's going to be, you know, putting large language models, pre-trained, fine-tuned through RL with human feedback, putting in the hands of, I don't know, terrorist organizations, of a kid in a garage who just wants to have a bit of fun through trolling. It's a scary world, because again, scale can be achieved. And the bottom line is, I think, why they're asking six months or some time is we don't really know how powerful these things are. It's been just a few days" }, { "from": "gpt", "value": "and they seem to be really damn good. I am so ready to be replaced. Seriously, I'm so ready. Like, you have no idea how excited I am. In a positive way, meaning what? In a positive way, where basically all of the mundane aspects of my job, and maybe even my full job, if it turns out that an AI is better, I find it very discriminative. Basically say you can only hire humans because they're inferior. I mean, that's ridiculous. That's discrimination. If an AI is better than me, at training students, get me out of the picture. Just let the AI train the students. I mean, please. Because like what do I want? Do I want jobs for humans" }, { "from": "human", "value": "or do I want better outcome for humanity? In a positive way. In a positive way. Yeah. The basic thing is then you start to ask, what do I want for humanity and what do I want as an individual? And as an individual, you want some basic survival and on top of that," }, { "from": "gpt", "value": "you want rich fulfilling experiences. That's exactly right. That's exactly right. And as an individual, I gain a tremendous amount from teaching at MIT. This is like an extremely fulfilling job. I often joke about if I were a billionaire in the stock market, I would pay MIT an exorbitant amount of money to let me work day in, day out, all night with the smartest people in the world. And that's what I already have. So that's a very fulfilling experience for me. But why would I deprive those students" }, { "from": "human", "value": "from a better advisor if they can have one? Take them. Well, I have to ask about education here. This has been a stressful time for high school teachers. Teachers in general. How do you think large language models, even at their current state," }, { "from": "gpt", "value": "are going to change education? First of all, education is the way out of poverty. Education is the way to success. Education is what let my parents escape islands and sort of let their kids come to MIT. And this is a basic human right. Like we should basically get extraordinarily better at identifying talent across the world and give that talent opportunities. So we need to nurture the nature. We need to nurture the talent across the world. And there's so many incredibly talented kids who are just sitting in underprivileged places in Africa, in Latin America, in the middle of America, in Asia, all over the world. We need to give these kids a chance. AI might be a way to do that by sort of democratizing education, by giving extraordinarily good teachers who are malleable, who are adaptable to every kid's specific needs, who are able to give the incredibly talented kid something that they struggle with. Rather than education for all, we teach to the top and we let the bottom behind or we teach to the bottom and we let the top drift off. Have education be tuned to the unique talents of each person. Some people might be incredibly talented at math or in physics, others in poetry, in literature, in art, in sports, you name it. So I think AI can be transformative for the human race if we basically allow education to sort of be pervasively altered. I also think that humans thrive on diversity, basically saying, oh, you're extraordinarily good at math. We don't need to teach math to you. We're just gonna teach you history now. I think that's silly. No, you're extraordinarily good at math. Let's make even better at math because we're not all gonna be growing our own chicken and hunting our own pigs or whatever they do. Another way so, we're, the reason why we're society is because some people are better at some things and they have natural inclinations to some things, some things fulfill them, some things they are very good at. Sometimes they're both aligned and they're very good at the things that fulfill them. We should just like push them to the limits of human capabilities for those and if some people excel in math, just like challenge them. I think every child should have the right to be challenged and if we say, oh, you're very good already, so we're not gonna bother with you, we're taking away that fundamental right to be challenged because if a kid is not challenged at school, they're gonna hate school and they're gonna be like, doodling rather than sort of pushing themselves. So that's sort of the education component. The other impact that AI can have is maybe we don't need everyone to be an extraordinarily good programmer. Maybe we need better general thinkers and the push that we've had towards these sort of very strict IQ-based tests that basically test only quantitative skills and programming skills and math skills and physics skills, maybe we don't need those anymore. Maybe AI will be very good at those. Maybe what we should be training is general thinkers and yes, I put my kids through Russian math, why do I do that? Because it teaches them how to think and that's what I tell my kids. I'm like, AI can compute for you, you don't need that, but what you need is learn how to think and that's why you're here. And I think challenging students with more complex problems, with more multi-dimensional problems, with more logical problems, I think is sort of perhaps a very fine direction that education can go towards with the understanding that a lot of the traditionally, scientific disciplines perhaps will be more easily solved by AI and sort of thinking about bringing up our kids to be productive, to be contributing to society rather than to only have a job because we prohibited AI from having those jobs, I think is the way to the future. And if you sort of focus on overall productivity, then let the AIs come in, let everybody become more productive. What I told my students is, you're not gonna be replaced by AI, but you're gonna be replaced by people who use AI in your job. So embrace it, use it as your partner and work with it rather than sort of forbid it because I think the productivity gains will actually lead to a better society. And that's something that humans have been traditionally very bad at. Every productivity gain has led to more inequality. And I'm hoping that we can do better this time, that basically right now, a democratization of these types of productivity gains will hopefully come with better sort of humanity level" } ]

[ { "from": "human", "value": "improvements in human condition. So as most people know, you're not just an eloquent, romantic, you're also a brilliant computational biologist, biologist, one of the great biologists in the world. I had to ask, how do the language models, how these large language models" }, { "from": "gpt", "value": "and the investments in AI affect the work you've been doing? So it's truly remarkable to be able to sort of be able to encapsulate this knowledge and sort of build these knowledge graphs and build representations of these knowledge in these sort of very high dimensional spaces, being able to project them together jointly between say single-cell data, genetics data, expression data, being able to sort of bring all these knowledge together allows us to truly dissect disease in a completely new kind of way. And what we're doing now is using these models. So we have this wonderful collaboration, we call it drug GWAS with Brad Penteluto in the chemistry department and Marinka Zitnick in Harvard Medical School. And what we're trying to do is effectively connect all of the dots to effectively cure all of disease. So it's no small challenge, but we're kind of starting with genetics. We're looking at how genetic variants are impacting these molecular phenotypes, how these are shifting from one space to another space, how we can kind of understand the same way that we're talking about language models, having personalities that are cross-cutting, being able to understand contextual learning. So Ben Langer is one of my machine learning students. He's basically looking at how we can learn cell-specific networks across millions of cells, where you can have the context of the biological variables of each of the cells be encoded as an orthogonal component to the specific network of each cell type. And being able to sort of project all of that into sort of a common knowledge space is transformative for the field. And then large language models have also been extremely helpful for structure. If you understand protein structure through modeling of geometric relationships, through geometric deep learning and graph neural networks. So one of the things that we're doing with Marinka is trying to sort of project these structural graphs at the domain level rather than the protein level, along with chemicals, so that we can start building specific chemicals for specific protein domains. And then we are working with the chemistry department and Brad to basically synthesize those. So what we're trying to create is this new center at MIT for genomics and therapeutics that basically says, can we facilitate this translation? We have thousands of these genetic circuits that we have uncovered. I mentioned last time in the New England Journal of Medicine, we had published this dissection of the strongest genetic association with obesity. And we showed how you can manipulate that association to switch back and forth between fat burning cells and fat storing cells. In Alzheimer's just a few weeks ago, we had a paper in nature in collaboration with Li-Wei Tsai, looking at APOE4, the strongest genetic association with Alzheimer's and we showed that it actually leads to a loss of being able to transport cholesterol in myelinating cells known as oligodendrocytes that are basically protected neurons. And whether they cholesterol gets stuck inside the oligodendrocytes, it doesn't form myelin. The neurons are not protected and it causes damage inside the oligodendrocytes. If you just restore transport, you basically are able to restore myelination in human cells in mice and to restore cognition in mice. So all of these circuits are basically now giving us handles to truly transform the human condition. We're doing the same thing in cardiac disorders, in Alzheimer's, in neurodegenerative disorders, in psychiatric disorders, where we have now these thousands of circuits that if we manipulate them, we know we can reverse disease circuitry. So what we want to build in this coalition that we're building is a center where we can now systematically test these underlying molecules in cellular models for heart, for muscle, for fat, for macrophages, immune cells, and neurons, to be able to now screen through these newly designed drugs through deep learning and to be able to sort of ask which ones act at the cellular level, which combinations of treatments should we be using. And the other components that we're looking into decomposing complex traits like Alzheimer's, and cardiovascular, and schizophrenia, into hallmarks of disease, so that for every one of those traits, we can kind of start speaking the language of what are the building blocks of Alzheimer's. And maybe this patient has building blocks one, three, and seven, and this other one has two, three, and eight, and we can now start prescribing drugs not for the disease anymore, but for the hallmark. And the advantage of that is that we can now take this modular approach to disease instead of saying there's going to be a drug for Alzheimer's which is going to fail in 80% of the patients. We're going to say now there's going to be 10 drugs, one for each pathway. And for every patient, we now prescribe the combination of drugs. So what we want to do in that center is basically translate every single one of these pathways into a set of therapeutics, a set of drugs that are projecting the same embedding subspace as the biological pathways that they alter so that we can have this translation between the dysregulations that are happening at the genetic level, at the transcription level, at the drug level, at the protein structure level and effectively take this modular approach to personalized medicine, we're saying I'm going to build a drug for Lex Friedman is not going to be sustainable. But if you instead say, I'm going to build a drug for this pathway and a drug for that other pathway, millions of people share each of these pathways. So that's the vision for how all of this AI and deep learning and embeddings can truly transform biology and medicine. Where we can truly take these systems and allow us to finally understand disease at a superhuman level by sort of finding these knowledge representations, these projections of each of these spaces and try understanding the meaning of each of those embedding sub-spaces and sort of how well populated it is, what are the drugs that we can build for it" } ]

[ { "from": "human", "value": "and so forth, so it's truly transformative. So systematically find how to alter the pathways. It maps the structure and information that genomics to therapeutics and allows you to have drugs" }, { "from": "gpt", "value": "that look at the pathways not at the final condition. Exactly, exactly. And the way that we're coupling this is with cell-penetrating peptides that allow us to deliver these drugs to specific cell types by taking advantage of the receptors of those cells. We can intervene at the antisense oligo level by basically repressing the RNA, bring in new RNA, intervene at the protein level, at the small molecule level. We can use proteins themselves as drugs just because of their ability to interfere, to interact directly from protein to protein interactions. So I think this space is being completely transformed with the marriage of high throughput technologies and all of these like AI, large language models," }, { "from": "human", "value": "deep learning models and so on and so forth. You mentioned your updated answer to the meaning of life as it continuously keeps updating. The new version is self-actualization." }, { "from": "gpt", "value": "Can you explain? I basically mean let's try to figure out number one, what am I supposed to be? And number two, find the strength to actually become it. So I was recently talking to students about this commencement address and I was talking to them about sort of how they have all of these paths ahead of them right now. And part of it is choosing the direction which you go and part of it is actually doing the walk to go in that direction and in doing the walk, what we talked about earlier about sort of you create your own environment, I basically told them, listen, you're ending high school up until now. Your parents have created all of your environment. Now it's time to take that into your own hands and to sort of shape the environment that you wanna be an adult in. And you can do that by choosing your friends, by choosing your particular neuronal routines. I basically think of your brain as a muscle where you can exercise specific neuronal pathways. So very recently, I realized that, I was having so much trouble sleeping and I would wake up in the middle of the night, I would wake up at 4 a.m. and I could just never go back to bed. So I was basically constantly losing, losing, losing sleep. I started a new routine where every morning as I bike in, instead of going to my office, I hit the gym. I basically go rowing first, I then do weights, I then swim very often when I have time. And what that has done is transform my neuronal pathways. So basically, like on Friday, I was trying to go to work and I was like, listen, I'm not gonna go exercise. And I couldn't, my bike just went straight to the gym. Like, I don't wanna do it. And I just went anyway, cause I couldn't do otherwise. And that has completely transformed me. So I think this sort of beneficial effect of exercise on the whole body is one of the ways that you could transform your own neuronal pathways. So understanding that it's not a choice, it's not an option, it's not optional. It's mandatory. And I think you're overall modeled so many of us by sort of being able to sort of push your body to the extreme, being able to have these extremely regimented regimes. And that's something that I've been terrible at. But now I'm basically trying to coach myself and trying to sort of finish this kind of self-actualization into a new version of myself," }, { "from": "human", "value": "a more disciplined version of myself. Don't ask questions, just follow the ritual. Not an option." }, { "from": "gpt", "value": "You have so much love in your life," }, { "from": "human", "value": "so much love, you radiate love." }, { "from": "gpt", "value": "Do you ever feel lonely? So there's different types of people. Some people drain in gatherings, some people recharge in gatherings. I'm definitely the recharging type. So I'm an extremely social creature. I recharge with intellectual exchanges, I recharge with physical exercise, I recharge in nature. But I also can feel fantastic when I'm the only person in the room. That doesn't mean I'm lonely, it just means I'm the only person in the room. And I think there's a secret to not feeling alone when you're the only one. And that secret is self-reflection. It's introspection. It's almost watching yourself from above. And it's basically just becoming yourself, becoming comfortable with the freedom that you have" }, { "from": "human", "value": "when you're by yourself. So hanging out with yourself. I mean, there's a lot of people who write to me, who talk to me about feeling alone in this world, that struggle, especially when they're younger. Is there further words of advice you can give to them" }, { "from": "gpt", "value": "when they are almost paralyzed by that feeling? So I sympathize completely, and I have felt alone, and I have felt that feeling. And what I would say to you is stand up, stretch your arms, just like become your own self, just like realize that you have this freedom. And breathe in, walk around the room, take a few steps in the room, just like get a feeling for the 3D version of yourself. Because very often we're kind of stuck to screen and that's very limiting and that sort of gets us in particular mindset. But activating your muscles, activating your body, activating your full self is one way that you can kind of get out of it. And that is exercising your freedom, reclaiming your physical space. And one of the things that I do is I have something that I call me time, which is if I've been really good all day, I got up in the morning, I got the kids to school, I made them breakfast, I sort of hit the gym, I had a series of really productive meetings, I reward myself with this me time. And that feeling of sort of when you're overstretched to realize that that's normal and you just wanna just let go, that feeling of exercising your freedom, exercising your me time, that's where you free yourself from all stress. You basically say it's not a need to anymore, it's a want to. And as soon as I click that me time, all of the stress goes away. And I just bike home early and I get to my work office at home and I feel complete freedom, but guess what I do with that complete freedom? I just don't go off and drift and do boring things. I basically now say, okay, this is just for me. I'm completely free, I don't have any requirements anymore. What do I do? I just look at my to-do list and I'm like, what can I clear off? And if I have three meetings scheduled in the next three half hours, it is so much more productive for me to say, you know what, I just wanna pick up the phone now and call these people and just knock it off one after the other. And I can finish three half hour meetings in the next 15 minutes just because it's the want, not I have to. So that would be my advice. Basically turn something that you have to do in just me time, stretch out, exercise your freedom, and just realize you live in 3D and you are a person, and just do things because you want them," } ]

[ { "from": "human", "value": "not because you have to. Noticing and reclaiming the freedom that each of us have. That's what it means to be human. If you notice it, you're truly free, physically, mentally, psychologically. Manolis, you're an incredible human. We could talk for many more hours. We covered less than 10% of what we were planning to cover, but we have to run off now to the social gathering that we spoke of. We're 3D humans. We're 3D humans and reclaim the freedom. I think, I hope we can talk many, many more times. There's always a lot to talk about, but more importantly, you're just a human being with a big heart and a beautiful mind that people love hearing from. And I certainly consider it a huge honor to know you and to consider your friend. Thank you so much for talking today. Thank you so much for talking so many more times, and thank you for all the love behind the scenes" }, { "from": "gpt", "value": "you send my ways, it always means the world. It always means the world. Lex, you are a truly, truly special human being. And I have to say that I'm honored to know you. So many friends are just in awe that you even exist. That you have the ability to do all the stuff that you're doing. And I think you're a gift to humanity. I love the mission that you're on to sort of share knowledge and insight and deep thought with so many special people who are transformative. But people across all walks of life, and I think you're doing this in just such a magnificent way, I wish you strength to continue doing that because it's a very special mission and it's a very draining mission. So thank you, both the human you and the robot you, the human you for showing all this love, and the robot you for doing it day after day after day." }, { "from": "human", "value": "So thank you, Lex. All right, let's go have some fun. Let's go. Thanks for listening to this conversation with Manolis Callis. To support this podcast, please check out our sponsors in the description. And now, let me leave you with some words from Bill Bryson. In his book, A Short History of Nearly Everything. If this book has a lesson, it is that we are awfully lucky to be here. And by we, I mean every living thing. To attain any kind of life in this universe of ours appears to be quite an achievement. As humans, we're doubly lucky, of course. We enjoy not only the privilege of existence, but also the singular ability to appreciate it, and even in a multitude of ways to make it better." }, { "from": "gpt", "value": "It is a talent we have only barely begun to grasp." }, { "from": "human", "value": "We have only, thank you for listening, and hope to see you next time." } ]

[ { "from": "human", "value": "I do the same thing with meditation. I wake up every morning and repeat a mantra to myself. And most evenings before bed, unless I'm really struggling, I'll repeat the mantra. And it's a kind of meditative process. So that to me, no matter where I am, feels like home because home is a place you live inside your mind. But little triggers, positive triggers, like drinking an Athletic Greens drink is very much that for me. All of a sudden I'm transformed into this place, into this feeling of home. They'll give you a free one year supply of vitamin D and five free travel packs with your first purchase when you go to athleticgreens.com slash Lex. This is a Lex Friedman podcast. To support it, please check out our sponsors in the description. And now dear friends, here's Simone Yeatsch. What was the first cool thing you built" }, { "from": "gpt", "value": "where you fell in love with the process of making stuff? You know, I think in the beginning of building stuff, you run into the limitations of your skills so much. So I feel like honestly building gets less and less frustrating or like I love it more and more," }, { "from": "human", "value": "the more I know. So the limitations aren't fun? Like when it's really frustrating." }, { "from": "gpt", "value": "The limitations are fun, but it's like when you have an idea of something and you wanna make it a certain level and then you just have to compromise with the materials and the tools and the skills you have. So I can't remember first time where I felt like. I'm proud of this. Wow, this was so smooth. I'm so proud of it." }, { "from": "human", "value": "Like I feel like." }, { "from": "gpt", "value": "I'm proud of this. A lot of people, I watch them build stuff and it's just like watching water pour down. You know, it's just like so easy. And for me, it's just like trying to shove a toy car" }, { "from": "human", "value": "into a wall. So you're not able to step back and marvel like at the early creations, even like, even like we're not even talking the Arduino stuff" }, { "from": "gpt", "value": "even before then. I'm from Sweden and you have to choose either sewing or woodworking. And I chose like woodworking in middle school. And I remember the sense of pride when I got to bring something home and that thing of like, oh my God, I get to show my parents this. And I think that is kind of the feeling that I've built my job around. It's like the sense of pride and wanting to show people something that I made. And back then it was like a little wooden spoon, you know?" }, { "from": "human", "value": "And now it's a slightly larger wooden spoon. Wooden spoon is dynamic and moves and has a mind of its own. You first started doing more engineering type stuff with Arduino boards at Punch2Design, which is an SF engineering firm. What are, just from your memory there," }, { "from": "gpt", "value": "what are some cool things you built there? So the thing is I went to advertising school and I just like vocational studies a year. And I realized there that I didn't care much for advertising but I thought it was really fun to build stuff in programs. So like I just completely focused on that. And there I built my first hardware project or like electronics project, which was this iPhone case with retractable guitar strings. So basically I imagined that you could like pull out guitar strings from the bottom of your iPhone and you could pluck it to your belt and then you could hold a cord on the screen. And I built that together with my friend Jonathan. And I was like, oh, this is dope. I thought it was so much fun. And I considered like, oh, should I go to school for this? But then I thought maybe I can get a job and I could get paid to learn about electronics. So just based off of that one project, I got the job at Punch Through Design" }, { "from": "human", "value": "or actually it was a one year internship. Can you explain what we're talking about here? So it's a case with guitar strings attached to it." }, { "from": "gpt", "value": "Does it actually work at all?" }, { "from": "human", "value": "Yeah, it does. These are not on the screen guitar strings." }, { "from": "gpt", "value": "No, so no, so they're actual strings that you pull out. So there's a mechanism that's almost like a seat belt mechanism. And yeah, you pull them out from the bottom of your phone and you can attach them to your belt. I mean, it's terrible. I mean, it's terrible. There's a few different ways to decide if somebody's touching a guitar string. And what you do in a real guitar is you have the little it's like measuring the vibration or the change as the yeah, you're measuring how the guitar is vibrating. And you can't really do that because I can't have a receiving sensor because the guitar strings are going to move in relationship to that because you don't have like a rigid neck. And this is like, yeah, this was my first electronics project. I was a little fledging baby maker. But what I decided was to use capacitive touch because that is independent on if the guitar strings are moving in relationship to something or in relation to something. So basically, there was just this little Bluetooth Arduino board that this company, Punch Through Design, made. So that was how I found them. And I measured the capacitive touch. So whenever the guitar string was measured, there was this little microcontroller that was like, oh my god, a guitar string got measured or touched. And then that sent a signal over Bluetooth to my phone. And I'd built a little iPhone app that interpreted those Bluetooth signals and then checked what type of cord I was holding on the screen and then played the querter." } ]

[ { "from": "human", "value": "I see you're holding the cords on the screen. So you're doing the multi-touch sensing there. That's incredible." }, { "from": "gpt", "value": "I honestly cannot believe that I pulled it off because I think I was, I was, ignorance was definitely bliss because that was like, yeah, the first hardware project I'd ever built, the first iPhone app I'd ever programmed. And now, if somebody was like, hey, I want this to be my first project, I would probably be like, oh, that's a lot." }, { "from": "human", "value": "But hold it off. Because that's such an interesting thing for people to hear because it's your first project. And a lot of people stop because of the difficulty of their first project. They never truly discover their own genius because they stop at the first, and you didn't stop. So it'd be interesting to kind of psychoanalyze you on the couch of why you didn't stop. Because you have to build an app to figure out how to, did you know how to program much? Or no?" }, { "from": "gpt", "value": "Yeah, I mean, a little bit, but I never program," }, { "from": "human", "value": "or done any iOS apps. So you have to figure out how to get forget like what the app does just get the app running and working. And then you have to figure out how to get the sensors in like real time, the finger touching. And you have to connect how to get the capacitors touch working with the might have controllers. Do you know anything about the capacitor" }, { "from": "gpt", "value": "touch sensors at that time jet time? I mean it's pretty easy." }, { "from": "human", "value": "Now it's basically now. It's basically, everything's easy." }, { "from": "gpt", "value": "You know rock hits they're pretty easy. You sound like my grandma because I have and Italian grandma, and I always trying to get her, we're like trying to get her to tell her recipes, and every recipe starts with, it's very simple." }, { "from": "human", "value": "And then there's like 45 minutes of her explaining it. It's like with gymnastics at the Olympics, they make it look easy. The best people in the world always make" }, { "from": "gpt", "value": "the impossible seem easy. I pride myself with making buildings look really hard," }, { "from": "human", "value": "because I feel like I'm always struggling so much, and struggling so much. You make the easy seem impossible. No. So how many strings was it?" }, { "from": "gpt", "value": "Was it just possible? No." }, { "from": "human", "value": "Gosh, I mean, this is such a long time, but no, it was six. Oh, six strings, and you could touch it and then there's," }, { "from": "gpt", "value": "wow, and then the phone itself makes a sound? And I still think it's such a cool concept to have this like, I'm not even a guitar player. I don't know. I mean, I got the idea because I was kind of strumming" }, { "from": "human", "value": "on my charge cord of my phone." }, { "from": "gpt", "value": "Oh, like an air guitar, but on a cord? Yeah, but I've been thinking about it, because I'm like, oh man, it would be really fun to go back to that project with what I know now. But the problem with it is that when you're producing the tension in your string just with your arm, like you can't make it taut enough to actually play. Like it kind of becomes playing these like saggy strings. So it's you're not really getting that experience. And I think that's why, I mean, I, yeah, I haven't really pursued it." }, { "from": "human", "value": "I wonder if there's a way to generate the tightness from the case itself, the device that unfolds" }, { "from": "gpt", "value": "and then with some kind of tightening mechanisms, tightness. Yeah, but then it kind of becomes this whole thing in a guitar that it just becomes a really shitty guitar. Which this is a really shitty guitar, but it's also... Guitar, yeah." }, { "from": "human", "value": "It's not a guitar." }, { "from": "gpt", "value": "But it's so shitty, it's awesome. Yeah, I don't know." }, { "from": "human", "value": "But it's cool that you have an interface between a device that's capable of incredible computational power and an actual hardware thing. Is there something that you can psychoanalyze that made you finish that others could hear in their own struggle to do their first project like that? Because you were in a non-engineering person, technically. And you did a pretty cool renegade out there," }, { "from": "gpt", "value": "wild, no-instructions engineering project. No, it definitely was an off-road build, where it's like if you're building a Lego kit, it's very much on the road and you're following instructions and this is like, you have no idea if you're headed for a cliff or a dead end or you're gonna get stuck. I think it had a natural pressure to it because it was a school project. So it did have deadlines built into it and stuff like that. So that definitely helped. But I think also it was just so incredibly motivating when I realized that I might be able to pull it off. Like that was, I felt like a bloodhound, you know? Just like, oh my God, I can actually make this happen. And I think if I hadn't seen that, the horizon," }, { "from": "human", "value": "it would have been harder to stick through." }, { "from": "gpt", "value": "Were you able to see the end of the tunnel pretty early on? No, not really." }, { "from": "human", "value": "So there's something to just suffering for a while." }, { "from": "gpt", "value": "I don't know how your brain works, but it's like if I have a problem, I can't stop thinking about it. Like it's so fun to think about it. Like I spent two and a half years designing a coat hanger and I just can't stop thinking about it." }, { "from": "human", "value": "Like I get so into it because I think it's so much fun. Take me to this two year journey of the coat hanger." }, { "from": "gpt", "value": "How did it begin, what, how did it begin? How did it begin? It began with a corner in my home where I couldn't fit a coat rack. The thing is I shouldn't have brought this up because I'm gonna release it as a product" } ]

[ { "from": "human", "value": "probably in a year, in a year. On an actual product. Okay, well, that's needed as a mystery." }, { "from": "gpt", "value": "Okay, well, that's needed as a mystery. It's a mystery, yeah. But it solves a fundamental problem in the human condition. Yes, and I am so excited about it and I cannot, I don't, yeah, but this is, I get so pumped about it because I see it's just this issue or like this problem that I wanna solve" }, { "from": "human", "value": "and I kinda can't put it to rest until I have. I mean, speaking of coat hangers, doorknobs have always been interesting to me. It's cool how there's things that everybody uses" }, { "from": "gpt", "value": "that somebody designed. Lex, oh my God. So, okay, so this is, so I have two like big, so basically I started on YouTube and I've been doing that for like the last seven or eight years and I've kind of been thinking of like, okay, what's next for me? Because I wanna keep on trying out new things and I'm kind of going into two different avenues. One is the product business that I started, coat hangers, TBD. And then I am working on a pilot episode of a show where each episode is about an everyday object and why they look the way that they do. So, we've written a pilot episode about forks and it's all about like, why do they look the way that they do? Why did this became the like eating implement of the West? Why are we ruled by an iron fork? How did that happen? And every everyday object that you have and that you just take for granted," }, { "from": "human", "value": "somebody's just made it up. Yeah, we're all sheep. We all keep using it. Even if it's not optimal. I mean, presumably most objects are optimal you hope" }, { "from": "gpt", "value": "or at least a laughing. Yeah, and that's what I think is so... Like the world around us and this is why I love building things it's because it just opens up this idea that the world around us is so malleable and you can make objects work for you better. Like I made this fruit bowl... I had a fruit bowl and I was always annoyed that I had either too little or too much fruit for it. So I made a fruit bowl where I can change the diameter of it. It has the mechanisms so you can make it bigger or smaller. And that's just like the thing of being like bulls, why are they the way that they are? I can make them different and I think like, I want to make an episode I could about doorknobs. I think it's so interesting. Why are they the way they are? Why are they placed the way, where they are?" }, { "from": "human", "value": "Like. I think there's going to be a rabbit hole" }, { "from": "gpt", "value": "from which you will never return. I would happily live in that rabbit hole forever. Like, if I could if I can like dig out a little niche for myself there, because I think it's like, you know, they go so deep," }, { "from": "human", "value": "because they're also on different sides of doors. You never, like the push-pull situation on doors in general, like that's one of the main problems of humanity is figuring out the push-pull, figuring out which- This is embarrassing, yeah. Okay, I mean, there's 8 billion people on earth. Every single second, there is millions of people being embarrassed by the confusion of what the push-pull. Real livestock. Right now there's somebody, some guy, first time in college, is trying to be impressive to everybody, pushes on, and he plays it off like it's cool. Oh shit, I knew that." }, { "from": "gpt", "value": "No, but that's the push-pull doors. Over and over, figuring out the push-pull, figuring out which- It is embarrassing, yeah. It's just with a push-pull. Real livestock. Right now there's somebody over and over. And it affects our behaviors. That was why I think it's so interesting with forks is that forks actually affect our eating behaviors, and they can get you to eat faster or slower, take bigger bites or smaller bites, and there are all these ways or like the social, I mean, the reason that chopsticks work is because they do the food chopping in the kitchen rather than on the plate. And also you have a bowl that you bring to your mouth whereas a plate you keep on the, like there are just all these ways and these objects affect our behavior, opening and closing doors. And I think it's such an interesting take on culture through like human behavior through these objects" }, { "from": "human", "value": "that we use every day and we never question them really. Yeah, and then there's institutions that are controlling our mind that don't want us to know the truth. Why are forks not more popular?" }, { "from": "gpt", "value": "Have you asked yourself that question?" }, { "from": "human", "value": "Yeah, no, it's all big utensil is behind all of it. All right, so I mean, in those early days, did you suffer from imposter syndrome? Like that leap to being an engineer, was there, especially when you started working on points of design on a team of engineers," }, { "from": "gpt", "value": "was there insecurity? Both yes and no. I think I've, I always try to flip my flaws into selling points. And for that, so getting that job, I was like, oh, you're a team of engineers. Everybody working here is an engineer. Your customers are not all engineers. You need somebody who can be your filter and tell you when something's gonna be too hard for your customers to understand. So it was more me being like, oh no, it might seem that me not having skills is a bad thing. Actually, it's a great thing." }, { "from": "human", "value": "I represent the everyday person." }, { "from": "gpt", "value": "I understand deeply what everybody needs and wants the every day person. I understand deeply what everybody needs. Yes, that is me. representation of the average human. But I mean, I remember that. So I studied physics for a year in college, and then I dropped out. And I had this rule for myself that whenever I did not understand any something, I would ask a question. So I was always raising my hand in class. And it's this room, entire auditorium filled with incredibly intelligent people who are mortified of seeming stupid. And I think that was really like, and I remember people at the end of the year coming up to me being like, thank you so much for all the questions you asked, because whenever there was something that I was too scared to ask, you always raised your hand. So I think it is a bit of a skill. And I think that is kind of how I channel my imposter syndrome is I'm just like, no, let's" } ]

[ { "from": "human", "value": "lay it all out there. You're okay being almost like self deprecating, just coming off. I mean, I'm definitely that I kind of lean into call myself an idiot, lean into being stupid. I think not all heroes were capes. And the guy and girl who asked the stupid question, is everybody's hero," }, { "from": "gpt", "value": "including the teachers. Yeah, I think it's, it's both. It's a double edged sword. I started out on the internet, kind of I kind of got the moniker, the queen of shitty robots, because I posted a lot of stuff on slash r slash shitty robots on Reddit, and people started calling me the queen of slash r slash shitty robots, and then the slash r kind of dropped. So what I'm trying to say is I did not come up with that with myself. But I did happily adopted. So I definitely came from a place of like building things that didn't work and kind of yeah, everything going wrong every time, like happily failing. And I think that was amazing. It was a really powerful tool for me to like not get my perfectionism in the way, because if I set out to do something that's great, then I'm never going to start. And I was like, no, I just need something that looks funny. But what I've realized now is there was also a defense mechanism. Being self deprecating is like always beating people to the punch. It kind of was a survival tactic on the internet of being like never daring to set out as an expert. And I still do that, like I'm terrified to tell people how to do something even if I know, because it kind of opens you up for being shot down. So I think I have I definitely have a conflicted relationship with it. And now especially as I'm, I'm getting older, I am more skilled than I was before. I mean, I'm a CEO of three businesses. And I'm like, I don't need to like keep on talking myself down all the time. So yeah, I think it's definitely something that has served me really, really well. And that is still like a thing that I have in my work life and in my relationships, but I'm also trying to only do it when it's beneficial to me and not when" }, { "from": "human", "value": "it's harmful. Yeah, I mean, but when you're as successful as you are, I feel like people like it. When you're self deprecating, you don't take yourself seriously, you have that humility. I think it's probably the hardest when you're starting out. Yeah. Because no, no, no, I think it was easier than almost. I don't know. But nobody takes you seriously," }, { "from": "gpt", "value": "right? And when you're starting out, when you're young, like, you know, I just realized that I played a lot more stupid than I was. And I think it's also Oh, gosh, I can't believe I'm the one bringing this up. But like being a woman in a male dominated field. And you're like, try I was just trying to make myself the least amount threatening. Or like really threatening because people are threatened by you in different ways. And it's like, you have such a thin line that you can walk where you're like, okay, I need to be just attractive enough for people to not be offended by my appearance, but just unattractive enough for people to not sexualize me. I have to be just smart and witty enough for people to be like, Oh my god, that's really cool. But also shoot myself down enough for other people not to be able to do it or be like, oh yeah, watch this woman try to thinking that she knows how to build electronics. You know, so it's like." }, { "from": "human", "value": "That's an interesting skill to build, especially when you put yourself out there on the internet. Yeah. Unfortunately, that's the reality of the internet. And it's a skill you have to kind of develop. That's actually why a lot of really brilliant people avoid the internet. Yeah. There's not many people, like at MIT, for example, there's not many brilliant professors or PhD students and so on just putting their stuff out there. Because like, if they really put their heart and soul into a thing, first of all, that's really hard. And nobody sees it, and everyone's like, eh, this is boring. So there's so many failure modes, like this is boring. Or like you said, you're coming off as too much of an expert, you're not self-deprecating enough. But there's just so many failure modes and it's terrifying for people. But I feel like that's a skill you should learn because most people like at MIT, at university and so on are doing a lot of awesome stuff. Yeah. And you should show it off." }, { "from": "gpt", "value": "But I feel like." }, { "from": "human", "value": "Yeah, yeah, yeah. You figured out a really good process of showing it off. When you fail, when you succeed, all of it, not taking yourself too seriously, but also revealing through the humor and the self-deprecation" }, { "from": "gpt", "value": "a kind of genius, a kind of intelligence and curiosity. I just wanna snapshot that quote and put it on my LinkedIn and the back of my book." }, { "from": "human", "value": "When is your autobiography coming out? Oh, never. You don't wanna say that because like a year from now." }, { "from": "gpt", "value": "Oh gosh, I don't wanna shit on autobiographies. No, but even just by saying that, I'm shitting on autobiographies. I just, me being interested enough and somebody to wanna read 600 pages about them talking about themselves." }, { "from": "human", "value": "No, no, no, well, that's exactly" }, { "from": "gpt", "value": "the kind of person that should write one. But also I'm fucking 32 years old. What do I have to write about? Like I went through puberty, I lost my virginity and here we are." } ]

[ { "from": "human", "value": "Like, I don't know, it's like such a write about. Like I went through puberty, I lost. Three chapters, it's a coloring book. Chapter seven, I learned to tie my own shoelaces. I feel like it would be awesome. Anyway, what's the queen? So how did you achieve the status of royalty? The queen of shitty robots," }, { "from": "gpt", "value": "what's the origin story there?" }, { "from": "human", "value": "I mean, I have officially renounced my title now. Can you still speak of the time when you led? I can still speak of the time." }, { "from": "gpt", "value": "Your kingdom? Yeah, of the time. Your kingdom?" }, { "from": "human", "value": "Yes, no, I mean, it started on because I." }, { "from": "gpt", "value": "Did you rule by love or fear? By fear of rejection from me, that people would reject me. So I, yeah, I started making these little gifts. Like my, the early projects that I did were very gift forward. It was always like, I only did it" }, { "from": "human", "value": "because it could be translated into a gift. Gift forward, I like it." }, { "from": "gpt", "value": "Yeah, but honestly it was like, it's a really good mental exercise to vet if your project is easy enough to be explained by like a seven second looping video without audio. And because like nobody's gonna care that it also has Bluetooth. Like it's really like, is it self-explanatory enough to be explained through a gift? So yeah." }, { "from": "human", "value": "Let me just pause, I'm sorry to interrupt, but I feel like all scientific papers and projects should go through that exercise. Can't be explained as a gift. Yeah, actually a deep mind does a good job of this. Like, you know, we saw protein folding, here's a gift. That's literally what they do. Because who's gonna read the nature paper? So you have to, like, how do we communicate this visually in a sexy clean way where people can intuitively understand even if you don't know what a protein is and if you don't know what protein folding is? Yeah." }, { "from": "gpt", "value": "It's a cool exercise. No, no, go get it if you explain this again. Yeah, it's very like, yeah, if somebody comes out of context and that's been really interesting also, like building this product business and trying to do the marketing around that and I'm like, if somebody comes in and they have no idea about what this product is, will they get it explained to them in this ad? I don't know. But it's definitely a worthwhile exercise to do. So I started making these projects, I got translated into GIFs," }, { "from": "human", "value": "and I posted them on slash r slash shitty robots on Reddit. So that's how Reddit existed?" }, { "from": "gpt", "value": "Yeah. I loved it. I thought it was really fun and I was like, I want to contribute with content here. Conquered it. I don't. I mean, I don't know. I think I was voted top user of 2015. So yeah, that's an old merit." }, { "from": "human", "value": "I was voted. Once you win a Nobel Prize, you always have the Nobel Prize. Okay. So what was the first thing?" }, { "from": "gpt", "value": "Remember the early GIFs that you created? So this is when I was at Punch Through Design in San Francisco. I was building a lot of hardware projects for them, but I also felt, and they were so supportive of me, but I also had such a different way representing a brand versus representing yourself. So there were some projects that I just like rolled out, because I was like, this feels too weird for this brand, and I started building them on the side. One of them was a toothbrush helmet, and yeah. So it's like a skateboard helmet with a robot arm on the forehead, kind of like a unicorn horn, and it pressures your teeth for you." }, { "from": "human", "value": "Was that the first YouTube video you uploaded?" }, { "from": "gpt", "value": "It was the first GIF that I uploaded. So actually, I wanted to do a kids show about electronics in Sweden, because I was like, I love electronics. I think it's fucking dope. I could do a kids show about it. So I filmed this terrible, terrible pilot episode in my bedroom in San Francisco, and that's when I built the toothbrush helmet, and I emailed it to them. I mean, just cold email, like I had no in or anything, but I was like, hey, I want to do this, and they didn't get back to me. Nobody surprised, and I was like, well, I have this thing I built, I might as well post it on the internet. So that's why I made the little GIF, and I posted it on slash r slash 3D robots, and I think it got like 50,000 views, and I was like, wow. And from there, I just kept on building things," }, { "from": "human", "value": "and I think within six months, it was my full-time job. Can you go through the detailed design of this toothbrush helmet? There's a motor, it's like a server, like what's the motor, what's the," }, { "from": "gpt", "value": "is there an Arduino involved? Yeah, so I built it off of this robot arm called Mi-Arm. So it's just this acrylic robot arm, and I think it has three servo motors, and it's all controlled by an Arduino, all the electronics. The arm is already pre-built? It was a kit, so I assembled it." }, { "from": "human", "value": "All the electronics. The arm is already pre-built? How do you make sure the length of the arm is the proper?" }, { "from": "gpt", "value": "I mean, the arm came down, so it's like, I mean, I just programmed it to come down to my mouth and then poorly brush my front teeth. Yeah." }, { "from": "human", "value": "Yeah. Yeah, and it was just swung back and forth." }, { "from": "gpt", "value": "I mean, trial and error is how you do that. Trial and error?" }, { "from": "human", "value": "What was the challenges of that?" }, { "from": "gpt", "value": "Do you remember, or is that one not much of a struggle? No, it was definitely a struggle." }, { "from": "human", "value": "Because also, how do you loop it with a nice gift?" }, { "from": "gpt", "value": "Loops, it loops fine. Yeah, it looks pretty fine." } ]

[ { "from": "human", "value": "Yeah, it's fine. Yeah, it looks pretty fine. Yeah." }, { "from": "gpt", "value": "I said that's not that hard. No, it doesn't have to be perfect if it's the Internet. Things are shitty all the time. I think the biggest struggle of that was that I had this intention for it be this show and then them not giving, oh, yeah, yeah, giving back and I was like well if they don't want it then maybe YouTube will have me. They don't notice." }, { "from": "human", "value": "The Internet, things are shitty all the time. Well, if they don't want it, then- They don't notice my genius yet. What was so bad about the pilot? Do you remember?" }, { "from": "gpt", "value": "What's that door's most embarrassing? What's that door's most embarrassing? Cringy. Yeah. I mean, it's thankfully not on the internet, so nobody can find it. But it's very much me being in what I call host mode, which is where I'm like, okay, so what we're gonna learn today is that we're gonna look at this. This is something called a servo motor, and it's like the intonation and everything is really different. And I'm actually, I mean, thinking back of that, I'm so happy that they didn't get back to me, because it's such a different thing to kind of start your career in your living room, running back and forth to the camera and like filming something and then looking at it. And like, I got to really find my own voice in a different way. And then like a year later, they offered me a show, but then I was so off and running," }, { "from": "human", "value": "I was like, no, I don't wanna do this. You didn't fall into that place of being like an actor, like a YouTuber, where you're presenting a kind of personality," }, { "from": "gpt", "value": "you're more focused on the product you're creating. I think it's a combination of it. I mean, I think of it as acting sometimes, but I only play the role of myself. But of course it's like when you're shooting something for the seventh time, like you have to be able to muster that enthusiasm. But no, it's not a kind of think of everyday life, me as a watered down version of the YouTube version." }, { "from": "human", "value": "It's like-" }, { "from": "gpt", "value": "That's a cheap knockoff. Yeah, it's a push.com version. No, it's just like add two parts water if you have the, but like on YouTube it's just so condensed cause you have jump cuts and you know, like I'll scrape jokes and make sure that everything lands and there's music and stuff. And then like in real life, you don't have any of that," }, { "from": "human", "value": "but it's still me. What are some other cool robots in the early days to stand out to, I mean, there's a million we can go through, but like maybe what was like a challenging one?" }, { "from": "gpt", "value": "Like a really challenging one in the early days, challenging. I remember the breakfast robot," }, { "from": "human", "value": "which was my second project was a challenging one." }, { "from": "gpt", "value": "So eating cereal? Yeah, it's a robot that pours milk and cereal and feeds me with a spoon. I was mostly challenging because it was so like everything had to be the right location and there were so many takes before I got everything right. And by right, I mean it makes an absolute mess. Yeah, that one was challenging." }, { "from": "human", "value": "How many takes was that one?" }, { "from": "gpt", "value": "Now probably 12, 10 something. It's just a mess everywhere. It's a mess and also I use Cheerios for the cereals. It's shot in my old bedroom in San Francisco and the floors were sticky for weeks afterwards, 10 something. It's just a mess everywhere." }, { "from": "human", "value": "This should go into your autobiography. Yeah. It's nice." }, { "from": "gpt", "value": "Which we could just type out this podcast and I'll release it as a, my manager would be stoked." }, { "from": "human", "value": "My manager would be stoked. We'll fix it in post. Yeah, because you have like a couple of feeding ones, right? There's soup. Isn't there a soup one?" }, { "from": "gpt", "value": "Yeah, there's a soup robot. There's a beer pouring robot." }, { "from": "human", "value": "I mean, that's awesome. That's a difficult robotics problem in the shitty and the perfect version of having an arm that interacts intimately with a human being. And one of the most intimate things you could do with a human being, that's PG, is to feed it. I was like, don't go there. Where is he going with this? Oh my God, he's a YouTube comment come live. Damn it. So to me, feeding is tricky or even like getting a beer, even pouring a beer is tough until" }, { "from": "gpt", "value": "glass. Yeah, it's trickier than anyone who hasn't tried it thinks. And even making it, I think what I realized is that making things really shitty or failing in a spectacular way is also its own sort of skill. Because the shittiest robot is the one that doesn't turn on, but that isn't much to watch. So it was always wanting for it to fail in these kind of spectacular ways. No, there's" }, { "from": "human", "value": "a lot of stuff to be said about engineering in it. Is there something to be said on a philosophical level about the value of a flawed robot? So the kind of robots you want is to be partially flawed. Do you think the kind of robots we'll have in the home that are friends and almost like pets, wouldn't they need to be kind of" }, { "from": "gpt", "value": "shitty? Because somehow we humans love the shitty. I mean, it is kind of endearing because I think it kind of, I'm going to mess up this world word, anthropomorphize system. I think it's, I mean, I never feel as deeply connected to my Roomba as when it's like, I'm on a cliff. I'm like, babe, I'm going to mess with" } ]

[ { "from": "human", "value": "them. Have you had Roomba's talk? No. I really have done that a lot when they talk to you. And it immediately anthropomorphize them. And then you have, if they have a name, which is why most roboticists don't give names or gender to robots because you become connected to them. I'm of the opposite mind. You should have like an intimate relationship sounds weird, but you should have a close connection to robots. I mean, there's power in that. There's a social element to robotics, even an arm. I don't know. There's something about us humans that gain so much value from our interaction with dynamic objects. And we should like lean into that as opposed to run away from it. That was always the confusing thing to me about robotics is that most roboticists" }, { "from": "gpt", "value": "run away from that." }, { "from": "human", "value": "Yeah, yeah. Weird. Because it's obviously going to be, robots are obviously going to be everywhere." }, { "from": "gpt", "value": "Obviously. But it's also humans are sensitive and squishy and there's so much liability. Oh." }, { "from": "human", "value": "Yeah. Yeah, but the humans are sensitive and squishy. When they interact with each other and they hurt each other all the time, like sometimes they get together and they're like, oh, you're the best. No, you're the best. And then they leave each other and they break each other's" }, { "from": "gpt", "value": "hearts. Sorry about your breakup." }, { "from": "human", "value": "I'm actually drunk for this interview. I've been being able to sleep for nice. Have you slept all night? Not. But from a safety protocol perspective, people think about like physical damage, not emotional damage. I know this sounds ridiculous. I know this sounds ridiculous, but it won't be. It's already happening. There's an app called Replica where people have an intimate relationship with an AI chatbot and they hurt themselves." }, { "from": "gpt", "value": "Have you slept all night? Have you slept all night? Not. I was thinking about this. Yeah. Okay. Like dating, what if you, because you can drain like a chatbot to kind of mimic the way that you talk to people and interact with people. Go on. Yeah. But then I'm like, okay, but what if we could all make AI versions of ourselves and have them date like thousands and thousands of other AI people and have that as a way to turn out potential candidates?" }, { "from": "human", "value": "Like I feel like that's going to be, what's the, yeah." }, { "from": "gpt", "value": "No, but what's the point of like meeting 20 people if you're like, oh, but if we just had our AI versions of ourselves interact, they'd be like, oh, your method of conflict" }, { "from": "human", "value": "is not going to match or. What if the AI version of you like sleeps around with all the other AIs and it becomes famous for that and it starts this on OnlyFans and then it becomes, and you're like, what did you do? Yeah. You come back home, you'd realize like, I don't, I didn't want to create a monster." }, { "from": "gpt", "value": "I mean, Hannah created a monster." }, { "from": "human", "value": "I mean, do I get a cut? Exactly." }, { "from": "gpt", "value": "It's a question I would ask. But I think it's definitely like, yeah, the, the human technology interaction is really interesting because I feel like I don't love any of the machines that I have in my life." }, { "from": "human", "value": "Really?" }, { "from": "gpt", "value": "Really? You haven't, you haven't. I mean, I don't love my phone. I touch it all the time and it's there and it's like constantly, it's a constant presence, but there's nothing to me that feels like, oh, I love this object." }, { "from": "human", "value": "Like I kind of despise it. That might be the way you show love. I don't know. Yeah. That's deeper. That's another psychoanalysis thing." }, { "from": "gpt", "value": "Uh, so you don't, there's not robots whom you've taken apart that you miss. Yeah. That's a deeper. No, they're all terrible. I mean, I, I have objects that I built that I love. Um, none of the robots I think, but that's also because it was a different, that was a different era where I wasn't really putting a lot of care into the projects I built." }, { "from": "human", "value": "So the more care you put into it, into the design to actually make it look, to make it functional and look good. That's where you put the love in." }, { "from": "gpt", "value": "Yeah. Yeah. I mean, it is, it's like, I feel like any technology company that figures out a way to get you to actually genuinely love your Roomba or like love it in the way that you" }, { "from": "human", "value": "would love a pet is a lot to be gained. Yeah. And it's like, it's scary depending on who the company is, because then they can manipulate you. Yeah. If you, if you love your Roomba and all of a sudden your Roomba starts telling you to buy stuff. Yeah." }, { "from": "gpt", "value": "Or it's leaving. Yeah. Or it's leaving. To put lotion on Jeff Bezos' head." }, { "from": "human", "value": "Yeah. Yeah. Yeah." }, { "from": "gpt", "value": "I don't know where the lotion came in, but yes, maybe if I certainly, I just, I just imagine my Amazon echo being like, Hey, Jeff Bezos is really a great guy." }, { "from": "human", "value": "Hey." }, { "from": "gpt", "value": "But even though you haven't, do you think it's possible to fall in love with a robot? Yeah. I mean, people fall in love with things all the time." }, { "from": "human", "value": "Well, people have fallen in love with your shitty robots, probably. I guarantee you there's people listening to this that are a little bit heartbroken saying that you've never fallen in love with your shitty robots. They're like, but I had a really emotional connection to that robot." }, { "from": "gpt", "value": "Like the one with it with a parent, Patsy on the back robot. Oh, that one. That one I do like. I like that one a lot. That's probably my favorite, like shitty robot. Can you explain it? So it's a machine. It was my friend, Daniel Beauchamp and I, we had this long running joke about a proud parent machine that you could give a quarter and a Patsy on the shoulder says proud of you. Yeah. I still have that hanging on my wall in my workshop. So that one I'm really happy with. I just think it's a really funny concept and also I executed the build wall." } ]

[ { "from": "human", "value": "So that was... So it's an arm? Mm-hmm." }, { "from": "gpt", "value": "Like what's the build? Yeah, I built it off of an old lamp arm." }, { "from": "human", "value": "Yeah, basically it's just a motorized arm and this kind of torso of a person. So it's actually a hand, right? I saw it. I read it correctly." }, { "from": "gpt", "value": "A hand on top. I saw it. I read it correctly. It's a laser cut. It's just laser cut plywood and it kind of has like... It looks creepy." }, { "from": "human", "value": "Yeah. Which I like. Yeah." }, { "from": "gpt", "value": "The creepy helps with the... Yeah. Yeah. And yeah, it says proud of you son. Because I just thought that sounded more funny than proud of you daughter and also proud of you son just... It immediately communicates that it's a parent. It's not just like a collie or something." }, { "from": "human", "value": "It's like proud of you." }, { "from": "gpt", "value": "Yeah." }, { "from": "human", "value": "It charges you a quarter for it. Yeah, but add like chat GPT on top of that and fine tune it on conversations you've had with your parents and all of a sudden you have a thing that can fundamentally transform" }, { "from": "gpt", "value": "your psyche." }, { "from": "human", "value": "Yeah. That's all it takes. That's a beautiful creation." }, { "from": "gpt", "value": "How'd you come up with that creation?" }, { "from": "human", "value": "That was my friend Daniel and I who had a long running joke about it. High level." }, { "from": "gpt", "value": "Can you speak to your creative process? I think a lot of it." }, { "from": "human", "value": "I mean, it's changed... For the shady robots." }, { "from": "gpt", "value": "That's actually separate. For the shady robot. Yeah. I mean, it has a lot of overlap. So it's identifying everyday problems and in the shitty robot era, I would kind of take an everyday problem like, Oh, I have a hard time getting up in the morning and I would solve it in the most ridiculous, spectacular way I could think of. So for waking up in the morning, it was having an alarm clock that slaps me in the face with a rubber hand. And what I'm doing now is still identifying everyday problems, but I'm actually trying" }, { "from": "human", "value": "to like product design my way out of it. What in your experience was the funniest thing? Is it violence, like the hand slapping you? Food eating, is there, or is it just" }, { "from": "gpt", "value": "a case about it, a case about it? The funniest is, no, I think it's more like the proud parent machine, it's not violent, it doesn't, there's nothing, it's just emotional and it's kind of, there's a commentary on this fraught relationship that we sometimes have" }, { "from": "human", "value": "with our parents and their pride of us. Sometimes, every time." }, { "from": "gpt", "value": "Sometimes. My dad visited like last week and he was like, I just wanna say I'm so proud of you and for the life you've built for yourself and that was really sweet. Yeah, true kind of. I'll put that on the back of my autobiography, too." }, { "from": "human", "value": "Yeah, yeah, true kind of. I'll put that." }, { "from": "gpt", "value": "It's not your fault, Simone, it's not your fault." }, { "from": "human", "value": "Some stuff is my fault. What was the longest one to complete for the Shady robots that you remember? Because you spent, on a few of them," }, { "from": "gpt", "value": "you spent quite a long time." }, { "from": "human", "value": "Mm-hm, mmm. Which is also inspiring when you take" }, { "from": "gpt", "value": "so long on a project. Yeah, I think, can even the more fun whimsical department rather than shitty robots. I built recently this music box, so like a small music box that kind of has a barrel with little spikes and it plays a song, but I did a large version of that, that pops a sheet of bubble wrap and then like plays tones into a pan flute. So yeah, you can actually program it to play different songs. I won't kick my butt in so many creative ways and it was such a pain. I think that is probably the like weird funny project that's taken me the longest" }, { "from": "human", "value": "and like the biggest engineering effort." }, { "from": "gpt", "value": "Where's the sound coming from? So if you, it all came from me realizing that if you pop bubble wrap and you pop it right in front of the opening of a pan flute or like one of the pipes, you can have it play different tones. So that's what it does." }, { "from": "human", "value": "So I felt this music instrument off of that. Okay, if it's okay, can you describe some, like how it works, some of the technical details here?" }, { "from": "gpt", "value": "Yeah, so basically, I mean, one of the big issues that I had, so I worked with as of a year and a half back, I hired an engineer stew, so we were collaborating on it. But a big issue that we had was feeding in the bubble wrap sheet and like making sure that it feeds in straight and doesn't get skewed because you need to make like the popping feet, which is where you program this barrel to pop different bubbles need to be so perfectly aligned on the bubble of the bubble wrap" }, { "from": "human", "value": "for it to pop in the right location. So there's a feeder for the bubble wrap, that's a challenge. And then you have to have a barrel with the little baby feet on it that pops the bubble wrap." }, { "from": "gpt", "value": "Why is it so exciting? Yeah, so that barrel was a pain as well. I had to get like this rotary set up for my CNC. And yeah, it was a lot of work, but that was really fun. And it's just like, this is probably my favorite privilege of my job is that I can go down any rabbit hole," }, { "from": "human", "value": "I think find interesting." }, { "from": "gpt", "value": "Did you have a lot of joy from popping the bubbles? That's a lot of self soothing. And like, I got to spend, I think I spent a week trying to figure out the best material to pop bubble wrap with. Because if you have two, if you kind of put them two through or through, if you put a sheet of bubble wrap through two rigid tubes, the air kind of just escapes from one side of the bubble into the other. So what I realized was that if you have a squishy material, like kind of a yoga mat material, in between it, it actually, it prevents that and pops it a lot more reliably. But like increasing the pop reliability" } ]

[ { "from": "human", "value": "was a huge effort as well. Yeah, that's fun." }, { "from": "gpt", "value": "The bubbles." }, { "from": "human", "value": "That's fun." }, { "from": "gpt", "value": "It was a squishy thing with another squishy thing. Because you don't need a lot of force. Like you just need it to not, air to not be able to escape anywhere. But then also we had, there was different qualities of bubble wrap where there was a lot of transference between different bubbles. So instead of the bubble popping, it would just seep the air into a neighboring bubble and that like membrane would kind of. So, you know, I just, getting to spend weeks on weeks" }, { "from": "human", "value": "of just studying bubble wrap. Yeah, wow. You ever think about like publishing academic work on bubble wrap? No. Wouldn't that be epic? Cause nobody's done this. I bet you nobody's done squishing material on squishy" }, { "from": "gpt", "value": "versus squishy for popping. No, I bet somebody has, but you know, I always, I thought I was going to go into academia. Like I was such an ambitious student. I loved school. I actually applied to MIT, but then I pulled out cause I was like, no, I don't want to do it. But now I realize it's really good that I didn't" }, { "from": "human", "value": "because I'm too much of a spaz. Too much of a spaz. Now I'm distracted. I'm thinking there must be papers about when you have two bubbles. Yeah, you need to know the physics of two bubble. When you have two bubbles colliding, one will pop first and there has to be good models of that. But that's very, that has to do with chemistry and whatever the material of the bulb was made from. But then, no, there's materials in here." }, { "from": "gpt", "value": "Somebody must understand bubble wrap deeply, like deeply. So I'm just going to take a quick restroom break because Lex is on his own train now. And I'm just going to leave you to talk about bubbles. Actually don't need to go to the restroom, okay?" }, { "from": "human", "value": "Leave you to talk about bubbles. I'm going to insert like a two hour instructional here" }, { "from": "gpt", "value": "with like a blackboard, right? It's the skill of a podcaster. I feel like I could throw you any topic" }, { "from": "human", "value": "and you could just go on about it. I don't know if I have that skill. I just love bubble wrap. Yeah, I think you can do it. Okay. Bubble on bubble interaction, go. So you did mention at MIT, you went to college for physics for one year and you dropped out. What do you learn from that?" }, { "from": "gpt", "value": "Who do you think should and shouldn't go to college?" }, { "from": "human", "value": "I think first of all, you shouldn't listen to me. That should be the name of your bio." }, { "from": "gpt", "value": "First of all you didn't listen to me. First of all, you didn't listen to me. I realized that I was there for the wrong reasons. I had this deep, I got completely, like starting to get grades in school, which in Sweden at that time we started getting in at eighth grade, so when I was 14, it just kind of hijacked my brain because I realized that I could put a number on how smart I was, and I got obsessed with it. And I wanted to study mechanical engineering because I was like, I like machines, but then physics was kind of the hardest thing you could do when I had this like deep need to prove to myself that I was smart. So I started studying physics, realized I wasn't that smart, I realized, or I mean, just mostly that I like, I love math, but I don't love math 10 hours a day. And also I think I am a generalist through and through, like I'm decent at a fair amount of things, but definitely not a specialist in any ways. And this, it was such a specialist type of area that I felt like the other parts of my brain kind of just dwindled and died. So I think most of all if people are thinking about going to college, and especially if you're here in the States and it's so fucking expensive, really, okay, there's two things I wanna do. One is like actually go to a workplace where people are doing the job that you think you wanna do if you wanna become a doctor, like be at a hospital and like try to see how doctors work and if you actually like it, because I feel like people have a lot of ideas of what it's gonna be like, and it just doesn't match with reality. And then I think when people figure out what they wanna do, there's kind of... That's two separate questions, or there's two questions that you can split out of that. One is like, what do you actually wanna do? That for me for the last 10 years is building stuff. But then there's a second part to that question, which is what context do you wanna do that? Do you wanna build stuff at a startup or at a big corporation? Do you wanna build stuff for an art gallery or for the movies or for YouTube? And I think that's often like people only learn how to answer the first question, but then it's like the context means as much because I was building stuff at Punch Through Design and I wasn't getting that like deep fulfillment. Like I felt like I wasn't fully using myself and like hitting all of my gears because I just wasn't that motivated about building stuff for other people." } ]

[ { "from": "human", "value": "And I changed the context and everything changed. And so sometimes you do need to consider resume and stuff like that for depending on the, but I think people consider that way too much especially modern times. I feel like you don't need to go to college just for the resume. I feel like the biggest benefit of college, I mean, there's a bunch, but one is just do hard things, but you could do hard things anywhere. But some people need to be, I was probably one of those people to be forced to do hard things. And the other is to meet fascinating humans from all walks of life that have all kinds of different passions and allows you to learn, depending on the major, you can learn generally and you can search if you're doing it efficiently about what actually inspires you. And the other thing is the resume thing. But ultimately you don't need college" }, { "from": "gpt", "value": "to find your passion and to run with it. I mean, I have so much college from although, like I think it's, I chose a different set of experiences and when I applied to MIT, I was, I think I was 24 because I was like, oh, maybe I should become an electrical engineer because I really liked electronics. But then I remember seeing that the average age was 18 and I was like, fuck no, I can't hang out or like be in a room filled with 18 year olds who are smarter than me. Yeah. So I think I definitely like missed the train on having that experience, but at the same time I did so many other things and I chose other experiences and I wouldn't trade them. But I still like, I mean, I'll go to on a campus and I'll be like, oh. But I think it's also because I have a dreamy idea of what it is because I never had to do it and practice fully in here. Yeah, exactly, it's the FOMO." }, { "from": "human", "value": "Yeah. Yeah, a lot of people really struggle with that burden. They'll go, it doesn't matter how long you go through if you don't go all the way to the PhD, a lot of people have the FOMO. It doesn't, it's a silly little notion, I think. Because I think you should be doing college or school until you find something that lights your heart aflame. Where you're like, fuck yes, I wanna do this. Yeah." }, { "from": "gpt", "value": "And run with it. Yeah. And run with it. I mean, you can find that in other contexts as well. I found it. Yeah, definitely." }, { "from": "human", "value": "But it is a buffet of experiences that you can have. What about, what was the most fun robot to make? Or musical artistic creation where the process" }, { "from": "gpt", "value": "was the most fun? They're all painful in different ways. So pain, do you find pain fun? No, but it's definitely the pride of getting to pull something off or managing to pull something off" }, { "from": "human", "value": "even when it was really difficult. So pain, do you find pain fun? It's very satisfying. What was the difficult thing that you pulled off" }, { "from": "gpt", "value": "and you were like, yeah, this is cool. I like working on jigsaw puzzles, but I don't like how much table space they take up because I just have one big table where I can do it. And that's also my dining table. So I made this mechanical table where you can switch between two tabletops. And that was an incredibly painful project. And I'm really happy with the outcome" }, { "from": "human", "value": "and so proud that I managed to pull it off." }, { "from": "gpt", "value": "How does it switch tabletops? It's a Tambor mechanism. So like Tambor, you'll have an old record player. Like it's these thin slats of wood with fabric on the back and you can kind of get them to go around curves. So basically one of the tabletops or table surfaces is Tambor. And then there's a little crank and you can kind of roll it off to the side and it reveals another tabletop under it that you can lift up because it's on cams. So you can switch between the two. I think that one was both really difficult to pull off and it's also one of few projects that I use in my everyday life." }, { "from": "human", "value": "Like I use it almost every day. You know what a really cool one was that that was part of your TED Talk where there's a rotating thing that you wear on your shoulders. Was that hard to make? So for people who haven't seen your TED Talk, they should of course. But it's, how would you describe that?" }, { "from": "gpt", "value": "For people, how would you describe that?" }, { "from": "human", "value": "Oh, cut out the best joke. How would you call that device?" }, { "from": "gpt", "value": "Sorry, I don't even know. I never used it beyond the TED Talk really. Yeah, but basically it's the shoulder rig and it has this like almost like Saturn ring looking platform that goes around. I can't even remember what the problem proposition was that I was trying to solve. Variety probably." }, { "from": "human", "value": "Introduce, introduce and invite you to your life. Yeah, maybe. And an element of surprise because you can put popcorn as you did on it and it goes around as a little hand. Why is it like a tiny hand funny? I don't know, but it just slams whatever is on that thing into your face." }, { "from": "gpt", "value": "Yeah. Invite you to your life. Yeah, maybe. And just make that thing into your face." }, { "from": "human", "value": "Yeah, I don't know." }, { "from": "gpt", "value": "Was that easy to make? Yeah, that one's fine. I can't. There was, I mean, my TED Talk was so," }, { "from": "human", "value": "yeah, for once again, they cut out my best joke. What was the best joke?" }, { "from": "gpt", "value": "My best joke and they didn't even ask me about it. It was, so there's this whole lead up where I built a chopping machine. So it's a machine that chops vegetables and it has two giant knives and it goes dink, dink, dink, dink, and it's kind of terrifying. And I show and I have a video of it and then it ends on this gif of it chopping up a banana. And I'm kind of scrunching up my face being like, ugh, ugh. And the whole reason I show that project is because I'm leading it up to the punch line of, oh, and as a bonus, this gift right here is the perfect response if anyone ever sends you dick pics you don't want. Brought down the house. It does it every time. And they caught it out without asking me because they were like, oh, but we wanted people to be able to show it in classrooms. And I was like, I have abandoned the hope" } ]

[ { "from": "human", "value": "of being shown in classrooms for years ago. That's a good joke. Thank you. That's a really good one." }, { "from": "gpt", "value": "You're okay going sometimes a little bit edgy. Thank you. I say that I'm crude and wholesome because I can be very crude, but I also try really, really hard to be a good person. And to like, I'll say shit and fucking all that stuff, which I don't even think is crude, but yeah. But I really, really try to wield the power that I have in a thoughtful way. So no, I wouldn't call me edgy because I'm not, I don't think it's edgy." }, { "from": "human", "value": "It's all like sucks. Chopping a banana with knives and saying it's a good gift response to anyone that sends you dick pics is definitely not edgy, you're correct." }, { "from": "gpt", "value": "Yeah. I see it's fitting. It's just a funny joke." }, { "from": "human", "value": "Yeah, that's pretty funny. Yeah." }, { "from": "gpt", "value": "I feel bad that Ted cut that. I mean, it's fun. It's like, it's a decision that I made really early on where I was like, I think often people misinterpret what I'm doing as being for children, which I think is part because like my projects were always really colorful and fun. But I think it also has some sprinkles of sexism of being like, oh, it's a woman doing something. She must be doing it for the children. And I'm like, fuck the children, I'm doing it for myself. So I think I would just really early on decided of like, oh no, I'm not gonna try to cater to that, which like, still, I mean, I get a lot of messages from parents being like, can you please stop cussing in your videos? And I'm also like, I get it, but also that is not what's gonna mess up your kids. I really try to be thoughtful and a decent enough role model but I'll also acknowledge that humans fuck." }, { "from": "human", "value": "Yeah, good, yeah, yeah, yeah." }, { "from": "gpt", "value": "Somehow that you being able to say the F-U to the, what word, word, what, do it, I can't, I can't." }, { "from": "human", "value": "I'm scared, it sounds better when you say F-U. It's a dance, I should, oh boy." }, { "from": "gpt", "value": "Have you ever made a robot that dances with you? No, you need a dance partner, so. I get lonely sometimes. Yeah, I feel like that's the theme of this whole podcast, yeah. What's the most embarrassed you've ever been on your podcast? I get lonely sometimes." }, { "from": "human", "value": "Is this a personal request, yeah, I feel like. So, I don't know if you've experienced this but I'm generally embarrassed by most things I say inside my head. So like, when I say something, like, no, it's just, there's a voice inside my head that goes, yeah, like what, your disappointment. Like that, the parent petting in the back, the hand stops working. Yeah." }, { "from": "gpt", "value": "Just slows down. Yeah." }, { "from": "human", "value": "And then there's an awkward silence, you don't know what to say next," }, { "from": "gpt", "value": "that's really embarrassing usually. I used to work as a journalist, so I know how to sit with a silence" }, { "from": "human", "value": "and try to drag it out, if you get out." }, { "from": "gpt", "value": "See what I did there? You gave up, you have to use all the help." }, { "from": "human", "value": "I think I quit, I was sweating. I was literally sweating. Okay." }, { "from": "gpt", "value": "Also, because you're in a full fucking suit," }, { "from": "human", "value": "what is that, like, how did that come about? Actually, it was probably at my tee, is because everybody was dressing in like sweatpants, the very chill wear. And I was like, I like taking everything seriously. It just felt like, as it was my way of saying a few to the way things are, because I like, I always admire Richard Feynman. I like it how there's like a classiness to it. So, I don't know if it's for visual purposes, but it's just how I feel when I put on a suit. It makes me feel like I'm gonna take this really, really seriously. Yeah. And if I embarrass myself, it's all my fault. Because I tried, there's no excuse. I tried 100%. The interesting thing about your TED Talk," }, { "from": "gpt", "value": "to go to a dark topic." }, { "from": "human", "value": "Mm, is this what happened when I walked off stage?" }, { "from": "gpt", "value": "No, what happened when you walked off stage? Found out that I had a brain tumor. Was that not where you're going?" }, { "from": "human", "value": "There's something else dark about my, yeah. Yes, well, yes, I thought you knew through the TED Talk." }, { "from": "gpt", "value": "You found out right after. I mean, the reason that I found out was partly because of the TED Talk, because my mom came into town to be there for it. And my right eyelid was swollen, and it had kind of been swelling over a while. And I even got in comments about it on my YouTube channel. And I thought it was allergies, because I was like, oh, it's just pollen allergies. It's just affecting my one eye, because maybe I sleep mostly on that side. I don't know. And my mom came into the stage and the Vancouver for my TED Talk, and she was like, Simone, you have to have a scan or see what's up. Well, we have to go to the doctor, and she really pushed me to do it, because I was like, fine, fine. And I had an MRI scan on like 5 p.m. on a Friday night. My boyfriend at the time was there. And I remember halfway through an MRI scan, they kind of pull you out, and they inject contrast fluid, or this thing that just gives them another type of scan. And the nurse looked at me in this way and was like, how long have you had symptoms for? And that's when I knew that they'd found something, and then they like shoved you back into the machine for another 20 minutes. And my ex was just seeing them zooming in and out of my scans. And there was like this, obviously, something that just looked wrong in there. And they sent me to the ER, and I found out that I had a brain tumor, the size of a golf ball, that probably been growing since I was a teenager. So it'd been growing over like 10, 15 years. And yeah, I had surgery to remove it. And then it kept on growing, the parts that they couldn't remove, and I went through radiation treatments. So that was like two years that just was kind of dedicated to just getting better and getting back to where I am now. And I remember, like I was so stoked about 2020, because I was like, this is the first year that I'm not held back by my health. And I'm like, finally gonna be able to do everything I feathered. And then the pandemic happens and you're kind of just like, okay, just in the backseat of what's happening" } ]

[ { "from": "human", "value": "and things that are out of my control again. In your public, you made a couple of videos about it. I have a brain tumor, my brain tumor is back. You kind of, you name your tumor, Brian, you kind of make it a lighthearted thing, but so you don't reveal much of the darkness, but were you scared or some low points?" }, { "from": "gpt", "value": "Yeah, of course I was, of course I was scared. I mean, it's terrifying. It's like, and also when it's in your brain, like, you know, I was like, take any other part of me, but don't take my brain. No, it's this unfathomable thing that happens. And you're like, I'm healthy. How can this possibly be a brain tumor? Like my eye is swollen. Like there's nothing there. I haven't had any seizures. I haven't had any cognitive issues. I haven't had any headaches even. Like how is that even possible? So you go through a lot of different stages of just trying to understand what it is. And I think I remember being hit like right as I found out when we were in like an Uber, poor Uber driver from where I had my MRI scan to the ER where they sent me. And I was really both really grateful that I've gotten so much more out of life than I ever thought I would. Like I've had a hell of a life. And even if it would have ended really early, I would have done so much more than I ever thought. But I was also really, really sad that I hadn't had kids yet. Like that was my big grief of like, fuck, I haven't had time to have kids yet. But no it's terrifying. I mean, the prospect of somebody cutting up your head. Like that's terrifying, but it honestly wasn't as bad" }, { "from": "human", "value": "as I thought it was gonna be. What about the radiation treatment? What are some things that people should, you learned about it, about the process and about yourself through that," }, { "from": "gpt", "value": "that people might be interested about? I think surgery was both harder and easier than radiation treatment because it was harder because it was so much more intense and it's such a dramatic thing, like going to the hospital that morning and being like, I don't know, and you feel so awful when you wake up. But then the recovery from it was pretty linear. Like almost every week I would get a little bit better. The thing about radiation is that it was not linear at all and it kind of drained me in this weird, like it was so hard to predict. And also they put me on these, I spent months feeling like I was high out of my mind and I couldn't process reality in a way that I normally would, like everything just felt off. Like I felt, yeah, I felt like I was high on drugs and I kept on asking my doctors what was going on and they're like, no, I don't know, don't think it's anything related. And I was on this Alzheimer's medicine that they put you on to prevent dementia from radiation treatment, like kind of as a preventative. And I found all these subreddits of people using that Alzheimer's medicine to get high. And people be like, oh my God, bro, I was like 20 milligrams yesterday and I was high out of my mind. And I'm like, man, I'm on 30 milligrams a day. Like of course it feels weird. And that was honestly one of the scariest parts of it because that was the first time where I felt like it genuinely affected my way of processing reality. And yeah, I was so relieved when I found out that that was what was causing it because I felt like I was going crazy. But even after surgery, like I woke up and I felt like myself, like everything was, I got no brain injury. So obviously this is like my experience from somebody who came out of it pretty unscathed, who didn't get any brain injuries and didn't have to do any of that recovery. It's more just the recovery from like the physical act of somebody cutting your skull open" }, { "from": "human", "value": "and taking a large chunk out. Did you research all the things that can go wrong?" }, { "from": "gpt", "value": "No. Brain surgery? No. I honestly, I'm a bit surprised by how I acted. It's pausing for you to pour. You're welcome, editors." }, { "from": "human", "value": "Still got commercials, still got commercials." }, { "from": "gpt", "value": "Yeah, this is like work injury from being a YouTuber. It's all like freeze if there's audio that comes in. Ah, yeah, sponsored by Capwater. I was surprised by how little I was willing to think critically about what my doctors told me to do. Like I very early on, the neurologist that I worked with, he was the one who was on call at the ER the day where I came in. And he was the one who ended up doing my surgery and he kind of became like my rock in this. And I just 100% trusted him. And he turned out to be an amazing doctor and like did a great job and was just like, I got so, so lucky. But I remember my mom being like, oh, but we should like talk about second opinions and like we should try to do more research. And I was like so unwilling to do that because opening up to the idea that there are multiple ways or multiple things that might be right or wrong was so terrifying. Like I wanted there to just be like, no, this is the only option. This is what we need to do. And if I started questioning that, then I don't know if I would have been able to go through with it. So yeah, it was a strange, I just really wanted to trust the doctors that I worked with." } ]

[ { "from": "human", "value": "And I was very scared to question them in any way. How did that process change your relationship with death? Are you afraid of death?" }, { "from": "gpt", "value": "You ponder your mortality?" }, { "from": "human", "value": "Yeah, I think it took away a part of youth for me." }, { "from": "gpt", "value": "Like the innocence? Yeah, I mean, you kind of think of terrible things as something that happens to other people and death and illness. So I think it kind of fast track that for me. But it mostly changed my relationship to life. It changed, it's made me so much more gentle with myself. Like going through illness, it forces you to redefine what it means to be good. And before, being good had been pushing myself really hard, it had been working, and I don't know, just being really hard with myself and disciplined. And when you're healing from something, being good is listening to your body, it's resting, it's like really being in tuned with what your health, where your health is at. And I think that is something that's kind of stuck with me since then. I'm like so much more gentle and delicate with myself. And with others? I think it definitely, it's like, when you're young and healthy, it's really hard to know what it feels like to be ill. And I remember, you know, you like go to yoga class and you'd be like, oh my God, this is too slow. Like I want it to be, I have so much more energy, like I need to. And when I was recovering from my brain surgery, there was this yoga studio nearby my house and they had yoga for seniors. And I was so stoked because I was like, oh, this is the yoga class I'll be able to take. And I think that was really eyeopening of just like, there's no, you kind of imagine that it's just like, oh, just push yourself harder. But no, that's not it with age or sickness or it's just, you got to be so gentle with yourself" }, { "from": "human", "value": "and you have to cater to people where they're at. Yeah. Yeah. And just the appreciation of this like biological vehicle you get and you should take care of it." }, { "from": "gpt", "value": "Being sick sucks. It's awful. And I really, I'm really motivated to postpone that for as much as I can. And also I was so tremendously grateful when I got ill that I felt like I had so much to take from. I had so many energy arrests of wars, I'd spent my life taking pretty decent care of my body and like exercising and eating well and not wrecking my body in any way. And I felt like this was the first time where that was so critical. And I felt like my body was ready for" }, { "from": "human", "value": "You know, I thought you're gonna go the other way like You can you can take care of your body all you want Bad stuff happens. You should you should go on drug binges and go out and do crazy things" }, { "from": "gpt", "value": "And I mean, I also had that that thought where I was like I fucking floss every day. How do I have a brain tumor? I've been good. Like why does this happen to me? but more so it was like my body was so resilient and ready for it and And um, I was I was really really proud of it It's amazing that the human body is able to recover from even the harshest things. Yeah, it's it's wild and my brain so after after surgery because yeah, I had a brain tumor the size of a golf ball kind of behind my right eye and after brain surgery you kind of just have this big hole in your head like this void and And usually your brain stays that way like it retains the shape even after the brain tumor is gone but for some reason my brain was feeling really ambitious and it has completely flopped back and I have almost like a Normal looking brain now where doctors are like, oh, we would almost not be able to tell that you had one So, yeah, that just blew my mind I feel like when did it was that why I had all those headaches? Yes for surgery. It's just my brain being like try" }, { "from": "human", "value": "Try Yeah, oh pretty cool thing. I want to ask you about is the everyday calendar you worked on. Mm-hmm. That was a long time" }, { "from": "gpt", "value": "That took a long time. Yeah, so basically I designed this calendar like I wanted to start meditating every day Mm-hmm, but it's really hard to meditate every day and to like kind of build that habit And what I would do is I would make these grids in my notebooks where I can like check a box for every day Like I just wanted like a little ding. I did it and like the sting of accountability But then I was like, this is I don't want to have a notebook that I do this I'm like, I want an art piece that I can hang on my wall like accountability art and I made the scene called the everyday calendar which has an entire year on it So it's 365 days and if you tap any of the days you light it up and we turn it into a Kickstarter campaign And it's now a product that I'm selling in my through my product business yet store What's it called the yet store? Yeah, and that for people who are confused is the right way to pronounce your last name, which does it it's right But it's so wrong. It makes my last name is spelled G. I e Rt z who does that song if loving you is wrong. I don't want to be right. Yeah I'm not singing my last name. Yeah" } ]

[ { "from": "human", "value": "That's what that's all me because what's his name? The from the office he covers it From the British office, which is the better office Okay Tangent upon a tangent upon a tangent So you said you created the everyday calendar to make a more beautiful in quotes and more sacred gold star system on a wall" }, { "from": "gpt", "value": "Not a notebook that gets thrown into a drawer. Yeah. Wow. Well said past me" }, { "from": "human", "value": "You you said that making this calendar taught you a lot in quotes, I feel like it like a real investigative journalist You've said in 2018 I'm waiting for the gotcha. Can you share some of the lessons you've learned like what do you mean?" }, { "from": "gpt", "value": "You've you've learned a lot from making this calendar. What are we talking about? Yeah, I'm waiting for the gotcha Oh, what are we talking about as somebody who builds things? Manufacturing something is such an unrelated process like making one of something and making ten thousands of something like they're not even distant cousins like it's completely different beasts to tackle and Yeah, so that was one of it everything takes so much longer than you think it's going to I did a Kickstarter campaign that we launched in 2018 after my surgery and Yeah, it's just you know, you think you're so generous with the timelines. We still ended up being a year late, but we shipped We're good But yeah, I mean I'm trying to get my product business off the ground We launched in May and it's just yeah, it's just a pain as somebody who's terrified of disappointing people" }, { "from": "human", "value": "I'm like, why have I chosen some of the jobs where it's the easiest to disappoint people you can disappoint people at scale" }, { "from": "gpt", "value": "No, yeah, I can disappoint people at scale and also them actually haven't paid me money to deliver on something Which is a terrible transaction But it's I'm just stoked to realize that I love the job still like I love the product development aspect of it I love trying to design stuff for manufacturing and figure it out and like Anticipate how people are gonna use your products and like the everyday calendar. I mean we've sold thousands of them now they're all over the world and it's like people actually finding something useful that I made and Implementing them into their lives. It's just" }, { "from": "human", "value": "Mind-boggling especially because this is tracking habits good habits Use it however you want I wanted a drinking binge again today Yeah, great another kid What does it take to a mass manufacture something what did you learn about that like what are can you like elucidate the gap between the one the prototype versus them the product development for mass manufacture" }, { "from": "gpt", "value": "Great another kid. I mean for one of it is like Yeah, the manufacturing the tooling that they use in manufacturing and to do things in a cost-effective way is really Different like I can make a one-off Then it's gonna take me 17 hours, but obviously you can't spend 17 hours per calendar when you're doing something in the factory I Think is that like quality control is such a beast you cannot trust anybody telling you that things are gonna be okay, like you're you have to have such Trust issues and it's also terrifying. I mean as somebody who's doing everything independently. I haven't raised any Capital for it like it's all self invested and we're doing it all in-house It's just you know, yeah, I could buy 10,000 calendars, but then what if all of them are have a manufacturing issue or Or you know, it's just it's just terrifying because the risks are so high But also I got to this point where for when this is something that I wanted to do for a long time But something that going through health problems taught me is how fragile my business model is because I mean, I'm basically running an influencer business where I Make videos on YouTube and then I have an ad spot and I talk about a brand. So like I'm a human billboard Which is fine. It grants me a lot of freedom to play around But if I am not well enough to be on a stage giving talks or be in front of a camera everything stops like it's such a pillar of a business and it can topple over at any given moment or like YouTube could change the algorithm like legislation could catch up and Change how you're able to advertise on the internet like it's so frail and I really felt like I need to Diversify what I'm doing and also just to keep it interesting for myself So what I decided was to start a product business because also it's kind of this perfect Combination of businesses where I can turn my YouTube channel into an R&D department Because I have a reason to constantly be exploring things and turning out new products I can also do that as early audience testing and see what people are actually excited about and if there's something that I think would Make an interesting product I can pass that over to the product business and then once I'm ready to Market that and sell it I can pass it over to the YouTube channel So it's like I can kind of once I realized that YouTube didn't feel like an end goal for me I was like, okay Then I can use it as a tool to accomplish these other things that I want to do and this was one of them" } ]

[ { "from": "human", "value": "So yeah, it's a lot that went into it and what and one of the tools like you says R&D But it's also kind of advertisement for the cool stuff that you're doing. I think I think Mr. Beast is one of the creators. It's also starting to understand this power of this reputation that you've built of Like people trust you like they love you to do cool stuff They trust that you put your heart and soul into a thing Yeah, so like and they feel your pain and the struggle to you know, like if a product like it For example, say the everyday calendar like there was issues of manufacturing something like this Yeah, they would feel the pain of that and there was still support I mean that that's the beauty of it. When you have the actual person right there struggling with their with their lows and highs" }, { "from": "gpt", "value": "Yeah, that's a decision that I made really early on where I was like the yet store is supported by me but it's separate from me. It's not merchandise. You don't have to know who I am or care about who I am to be interested in this product. And if you go on the website, yach.store, plug. I'm on the about page, yach.store. You have to go to the about page to find anything about me. It's definitely not like, this is Simone's brand. And I think anybody who's followed me for a long time will see that my personality is sprinkled into it, but it's still clean off of me, and I think that's also because I wanted something that was separate from me, because I am also running out of narcissism, believe it or not. I don't want it to be about me. And I want it to be something that can also run independently of me and doesn't... I want to be able to retire in my face, and still do the other stuff because because I think it's fun, but I don't want that to be the core of it." }, { "from": "human", "value": "Mommy, a bad- What other kind of stuff have you worked on" }, { "from": "gpt", "value": "for the product design for Yetch? So, I mean, a lot of the products, I decided to launch the store with a really small roster of products because developing products is such a upfront, heavy, like cost-wise and just investment. Such a, it's very big upfront investment. So, and I know that it would take a while, or I knew it would take a while for me to kind of find the right tonality and visual language for the brand. So I just wanted to launch it, have it be out there, start working on it, start like learning more about what it entails, even if we just had a small roster of products. So we've released it with, we have a puzzle. Yes. This is a whim, but I wanted to release a puzzle that has one piece missing. So it's actually, as far as I can tell, it's the world's first officially incomplete puzzle. You get 499 out of 500 pieces. I keep the 500th piece. So I have a box in my workshop with everybody's missing pieces. Yeah. And I don't know what to do with it yet, but someday it will come to me. Yes, profound artistic statement. It is something, it's definitely something. And I'm surprised by how many of them we've sold, which I've also like, I kind of wanted to have that product out there because I was like, can you imagine having a pitch deck? If I do have a raise money of being like, you know how good I am at selling things? I sold people 5,000 incomplete puzzles. Incomplete puzzles. Also have, you know, it's like a lot of the products, I call them basket fillers. Like they're kind of just like stuff where I'm like, yeah, this is like easier to throw into your basket. I mean, we have these rings, I'm wearing them. So there's a screwdriver ring, which is a Phillips head screwdriver, and then a screw ring that kind of has a recess, like a Phillips head screw. I have these sawdust socks that make you look like your feet are covered in sawdust. Like you spend all day in the shop without having to put any of the actual effort in. But then, puzzles. We have four more products in the pipeline that we're working on and that are kind of the more, the big ambitious products that are more in line with what I want the brand to be. Like the tagline is unique solutions to everyday problems. And it's just a lot of like trying to develop novel takes" }, { "from": "human", "value": "on existing products. There's something where the function becomes a bigger, bigger part of the design. Yeah. And so what's the process of creating something like that? Like even the everyday calendar. So like, what are some challenges that are interesting along the way? So you have to sketch it out, you have to like brainstorm, draw things out, and then create a schematic and see like," }, { "from": "gpt", "value": "how do you know what it's going to look like visually? Yeah, don't. And it's, I mean, I, so the everyday calendar, the first, so I just built it for myself first. Like that did not come as a product idea first. And that's kind of been the process that I've had for a lot of things. Like I make it for myself and then I'm like, oh, maybe other people would find this useful too. So the everyday calendar, the first prototype I made, it had actually physical mechanical toggle switches. So 365 toggle switches that you could flip. So if you worked out that day or meditated for me, I was meditating, you can just flip that switch. And that was great. But when I started evaluating it as a product, if you have 365 of something in a product, like the runaway cost is crazy. So the cheapest option, most reliable option we could find was capacitive touch. So basically it's a touch interface. And the front plate is a circuit board itself. So it's this like the circuit board that's designed in this really fancy way. So it looks like a beautiful piece of art, not to do my own horn too much, but it's actually a circuit board, which I also thought was really interesting of like using this that people usually hide away in products. And it felt like a nod to my career in electronics as well of being like, no, let's make it pretty. And let's make it, put it front and forward. But yeah, I mean, what I'm realizing now more and more is like there's so many of, like I would love to turn the puzzle table into a product, but then it's like, that would be a $7,000 table. And I don't want to sell the tables for $7,000. So you're kind of limited to the price bracket you're in. And it's like, your margins are tough. Like maintaining your margins are really, really tough. And as somebody who's like, I would love to sell the stuff that we're doing cheaper, but you just, it's just not feasible. Like you need those margins to survive." } ]

[ { "from": "human", "value": "Well, one of the genius things in the conversations I've had with Elon is the ability through sort of systematic questioning of how things have been done in the past to discuss what is the lowest cost way to solve a problem. And so he's very good at getting to, like with Optimus robot, for example, the humanoid robot, how do you get the cost down? Yeah. And that seems to be like one of the essential things to do in any product that you have to mass manufacture" }, { "from": "gpt", "value": "is constantly discuss like, how do we simplify, simplify? Yeah, it's definitely a design limitation. It's interesting. It's both hard and interesting to work within. And that's such a different thing as well. It's like, I mean, as I talked about before, like what is the context and what you're creating things? Like I'm still building things. I'm still inventing things, but I changed the context and it has a very different set of limitations and constantly trying to simplify your product to make it cheaper. And yeah, it's a really interesting" }, { "from": "human", "value": "and different type of design process. You can lose some of the magic though, right? Like people can do that a little bit too much. I think Apple is famous. Like Johnny Ives is famous for sort of focusing on design first and not worrying about the cost later. Cause you don't want to sacrifice. There's some stuff that's going to cost more," }, { "from": "gpt", "value": "but it keeps some of the magic. I think it's for some of the products that we're working on. It's like, I'm like, let's just make it the best we think it can be. And then we can scale back from there. Like, let's not impose these limitations on ourselves up front. Like, let's just make it the most beautiful version of itself and then we can decide what we want to compromise with or compromise on." }, { "from": "human", "value": "Yeah. That's what I say every day. When I look in the mirror," }, { "from": "gpt", "value": "it just makes the most beautiful. It just makes the most beautiful. And then we can compromise." }, { "from": "human", "value": "So you put on that suit. Yeah. Yeah. And then see how shit goes wrong later. All right. Back a little bit to the robots. just, or actually to one of your more epic projects. I mean, they're all epic, but truck left. Yeah. You cutting into a Tesla and turning into an epic truck. What was that like?" }, { "from": "gpt", "value": "Where did the idea come from? So you put on that suit. The idea came from that I really wanted an electric pickup truck. Like I'm only really driven electric because I got my driver's license pretty late and I'm like one of that first generation drivers it's like probably never gonna have a gas vehicle, but yeah this was in 2018 as well. 2018 was a big year. Yeah. Yeah. Or 2019, I can't remember." }, { "from": "human", "value": "And I, yeah, figured that we could just make our own." }, { "from": "gpt", "value": "So you took a Tesla?" }, { "from": "human", "value": "Tesla Model 3. Model 3? And you cut off a piece of it. And you turn it into a pickup truck. What's the, it looks pretty badass. So what are some of the challenges of doing that?" }, { "from": "gpt", "value": "It's unlike other projects you've done. Yeah. It's very much outside of my realm. Like I'm not a car person. I haven't worked on cars before. So we brought in a big team and had another project manager for it and stuff. Cause also like cars, you definitely don't want things to go wrong. Like there's no part of me that wants to fuck around and make something that's gonna be really unsafe for me or for other people who are driving with me. So yeah, I mean, it was about a year of planning and then we got the car and then we spent a month just tearing it apart and trying to make it. I was so set. Like I really wanted the car just for its function. And I was like, I'm so fine with if it's really ugly." }, { "from": "human", "value": "But then we managed to make it actually look really good. So that wasn't part of the discussion?" }, { "from": "gpt", "value": "Like how the final thing looks? I wasn't so, I wasn't that fussed about it. I was like, I just want it for its function. Like I really want this car. I don't want it because it looks cool. But then it ended up looking pretty cool as well. And I'm really, I mean, even now a couple of years later when there are some more options of electric pickup trucks, I still stand truck law. Like she's, like Rivian Ford F-150," }, { "from": "human", "value": "like they're all great, but they're giant. You're sitting there on a porch in your cowboy hat. Yeah." }, { "from": "gpt", "value": "Drinking whiskey and saying. Yeah, with my cattle dog." }, { "from": "human", "value": "Yeah. Yeah. Yeah. Yeah." }, { "from": "gpt", "value": "Shotgun saying." }, { "from": "human", "value": "I wanted like a small 90s pickup truck. Back to shitty robots. You were used parts of previous robots a lot. What's like a memorable example of that? It's just the graveyard of parts." }, { "from": "gpt", "value": "I mean. Workshop, workshop. I've gotten better at keeping projects intact. In the beginning, I used to disassemble every project because I was also a much more stringent budget. So if I needed a motor, then I would like seal it off of an existing robot or a previous robot. But I've got a really good at not doing that now because I'm like, maybe one day I want to have a museum exhibit. And then it would be nice to have all of those machines" }, { "from": "human", "value": "intact and not having to rebuild them. Centuries from now, you know, you can look at Benjamin Franklin's house. Oh yeah. Nobody's gonna look at my house. Yeah, just house. Just some weird shit." }, { "from": "gpt", "value": "Oh yeah. Nobody's gonna look at my house." } ]

[ { "from": "human", "value": "Yeah, that goes great with my idea of myself. With the autobiography. You said that people keep requesting in the comments. They. Did I put a dildo on it? Yeah. They have, I have." }, { "from": "gpt", "value": "Wait, was that? Did I put a dildo on it? Yeah." }, { "from": "human", "value": "Wait, was that actually where you were gonna ask? Yeah." }, { "from": "gpt", "value": "I have dildo written in my notes. I thought I just made it into a raunchy punch line. Dildo. Because you were actually gonna get there. Dildo. Yeah, that was in the early days and the shitty robot days. But now I have a filter on my YouTube channel for every possible spelling of dildo." }, { "from": "human", "value": "I mean, people want to probably sexualize robots, right? And then, or they put." }, { "from": "gpt", "value": "They want to sexualize my relationship with them, yeah. Oh. You know, cause I have majority male followers and they're so sweet and so like respectful, 99%. But I realize like, there is a lot of. I've realized that society hasn't taught men how to have female role models. And the way that people channel it is through being like, oh, it's because I want to fuck her or I want to date her or I want to marry her. And I'm like, I don't think you want any of those things. I think you actually just admire my work." }, { "from": "human", "value": "But you don't know how to look up to a woman. Yeah, that's beautifully put. What about weapons?" }, { "from": "gpt", "value": "Do you get requests to put weapons on a thing? It's interesting, I kind of started in robotics. That's just like a happy camper who is really into like tinkering. And now I'm kind of seeing some of the darker parts of it. And I remember first time I went to a proper factory and I saw like big industrial robot arms at work. And I was like, oh wow, this is what it is about. And it was almost scary where I was like, oh, I've just been like playing around with these tiny versions of this. And I'm like, oh my God, everybody robotics is cool and fun. And then you get in there and you're like," }, { "from": "human", "value": "this is kind of terrifying. You were platforming the very things that will destroy human civilization." }, { "from": "gpt", "value": "You're making it fun and entertaining to destroy human civilization. I'm the mouthpiece that I'm like getting people into robotics and engineering. And we're all just building our demise and accelerating speed. No, but I mean, I had that and like as the same with also with like companies who are saying that they're never gonna put weapons on their robots and then have military contracts and stuff like that. And you're like, this is dark and scary." }, { "from": "human", "value": "Fortunately, I haven't gotten a lot of requests for it. Yeah, drones are terrifying, especially." }, { "from": "gpt", "value": "Drones are fucking terrifying. And it's really everything. I mean, we're humans are so good at creative ways of killing and fucking each other. It's like almost how everything goes. And it's, yeah, I'm terrified of the future" }, { "from": "human", "value": "where we are gonna use more robots to kill each other. And come up with new and new creative ways to kill and hurt each other. Emotionally, psychologically, physically. Yeah. Speaking of which, what are your thoughts about, I don't know if you've been paying attention, but Chad GPT, the investment in language models and artificial intelligence. Have you added speaking capabilities to any" }, { "from": "gpt", "value": "of your devices, have you played with it? Yeah, I have Siri on, yeah. I used to have an Amazon Echo in my house, but then I removed it. It just freaked me out that I could whisper from my bed and it hurt me. I'd be like, Alexa, please Spotify. I'd be like, playing Spotify. Yeah. Fuck. I think it is a powerful tool that we are not fully ready for. And I don't know, I think the internet is kind of a parade of us using powerful things in harmful ways. And I think chatbots are really, really exciting. I'm stoked to have a personal assistant that's like a virtual assistant that actually does a good job and can solve problems for me. But yeah, it also feels like it can get dark" }, { "from": "human", "value": "really, really quickly. Yeah, because you can form close connections like we're talking about with it and then it can be used to manipulate you. Manipulate you in terms of what is true and manipulate you in terms of getting you to buy stuff. Yeah. Or maybe because at least for now it's centralized," }, { "from": "gpt", "value": "getting everybody to think the same way. Yeah. I mean, it's the same in like algorithms being used to radicalize people or kind of having that as a consequence of the way that they work and combine that with a really advanced language model. And like you can control people's world view in a way that you could. I mean, it's just, it's wild. And I think we're not ready for it. And I don't know if we ever would be because we're very impressionable" }, { "from": "human", "value": "little squishy flesh bags. Which takes us back to the one the squishy flesh bags interact. Which one pops first still on the wall? No, yeah." }, { "from": "gpt", "value": "Cut to this bubble bubble bubble bubble bubble bubble. New paper, paper coming out like three minutes." }, { "from": "human", "value": "What were we talking about? Oh, what about consciousness? So you never anthropomorphize the robots? Did they ever come to life for you?" }, { "from": "gpt", "value": "Where you kind of thought." }, { "from": "human", "value": "No, because they built them and I know how they work." }, { "from": "gpt", "value": "So that prevents you from being able to see the magic. I don't know, yeah. But I think it's like, I definitely, when I did a lot of the shitty robot stuff, like I wanted them to move like a human or like in a more organic way and not just like point A to point B which is the easiest way to program stuff. So I wanted other people to anthropomorphize them. But I don't think I did necessarily. I'm trying to think of a piece of technology that I've just kind of projected feelings upon," } ]

[ { "from": "human", "value": "but no, I can't. So sometimes what makes me anthropomorphize something even though I built it is there's a element surprise. So especially with machine learning, you're surprised by the kind of things it does." }, { "from": "gpt", "value": "Have you ever been surprised by a robot? No, because they're all pretty dumb. Like also the robots I built, it's like, like also they're all just servos moving from, I mean, I don't think I've built anything with a huge amount of sensors or like they're just moving" }, { "from": "human", "value": "in a pattern that I programmed them to move." }, { "from": "gpt", "value": "What's the most complex thing you've built?" }, { "from": "human", "value": "I mean, probably truck cloud." }, { "from": "gpt", "value": "Truck cloud. Yeah, was complex just for the sheer scale of it. And like the, I mean, I think that was my biggest project both in terms of build scope, but also in terms of impact that it had. Like that project just went wild. But then, yeah, then I don't know, the bubble wrap music box, I don't know. They're all complicated in different ways." }, { "from": "human", "value": "That one is epic. They're all complicated in different ways. That one is epic. How does the bubble wrap connect to the flute by the way?" }, { "from": "gpt", "value": "How does that work? The flute is just right where, like mounted right where it pops it." }, { "from": "human", "value": "Okay. Yeah, mounted right where. So fascinating, I gotta watch that video. Yeah, I have fun. Funny enough, in my deep investigative journalistic research of you, says you're used to being an MMA reporter. How, how, how did that happen?" }, { "from": "gpt", "value": "How did you get into it? I was really into martial arts. I was like a huge UFC buff." }, { "from": "human", "value": "I mean, this is 2010, maybe?" }, { "from": "gpt", "value": "You practiced martial arts yourself? I did, yeah. I was mostly standup. I did really, I did a lot of Muay Thai and then some Brazilian jiu-jitsu and just, yeah. I was really, the thing is I get really intense about my hobbies and I was so into it. I was all in. Awesome. And I had worked a little bit as a journalist and I was like, oh, I should like do MMA reporting. And I emailed this MMA website in Sweden. I was like, hey, can I come and write for you? And they were like, oh, actually we're going to an event in Gothenburg tomorrow. Do you want to come? Yeah. And I was like, wow, this is a lot. It's like 11 p.m. at night, but sure I'll come. And I went there to their office. I'd never really met them. And I'm like, this is kind of scary. Like I'm a 20 year old girl and going there in a group of men with a group of men. And they were so rude. They'd like, I went there and I was like, hey, what's up? And they were all kind of ignoring me and just like not looking at me or interacting with me until they realized that Simon was a girl because we'd only talked over email. And they're like, oh, this guy named Simon is going to come. And then they were like, oh, fuck Simon. It's actually Simone and it's a girl. So I kind of like slid into that in a very, very strange way. And I did that for a year, but then I got kicked out of an interview with Alexander Gustafson." }, { "from": "human", "value": "And I was like, so in." }, { "from": "gpt", "value": "And I was like, and then I just kind of never went back and I was done with it. And now I'm not allowed to do martial arts because of brain stuff. So I've kind of put all of that behind me. And it's interesting. It's like, I definitely see the athleticism in it and the skill that goes into it. I think as the older I get, the more concerned I am about the health impacts of the sport and of the people who are practicing it on an elite level. And I'm just not as, cannot as 100% as cheer" }, { "from": "human", "value": "as somebody beats somebody else up into a pulp. Yeah, especially considering the effects it might have on the brain. May I ask why you got kicked out? This is the Gustafson interview. Is anything fun? It's embarrassing. What happened?" }, { "from": "gpt", "value": "No, it was. This is the Gustafson interview? Embarrassing? What happened? No, it wasn't, I didn't, it was not, I didn't intend to get kicked out. I didn't realize I was gonna get kicked out. So it was, Alexander Gustafson was gonna fight John Jones. And he had just, he was kind of like this golden boy in Sweden. And he had just come out to the press that he had actually been to jail for violent crimes. And all I wanted to ask, all I asked was what was the reason that you wanted to bring that forward now? And apparently that was completely like blacklisted, but I hadn't gotten briefed about it at all. And the PR man, head of PR of the UFC was just yelling at me and they kicked me out of Grand Hotel in Stockholm. And I immediately called my mom and I was like, mom, you will not believe what just happened. I got kicked out of an interview at Grand Hotel because in the 90s, she got kicked out of an interview with Mel Gibson from the Grand Hotel. So that's like Renzen, the family. So I was just like, it was so, yeah. No, it was just this weird generational skip where we both got in kicked out of interviews at the same hotel." }, { "from": "human", "value": "Like it was so. You spent quite a bit of time in China as a student. Is that something you could speak to the differences and culturally, maybe even from like a student in the engineering perspective between China and US, maybe even Sweden. Those are like technologically speaking" }, { "from": "gpt", "value": "just such fundamentally different places. I mean, I moved to China when I was 16 and I went through as an extreme student. So that is before I had ever touched upon those things. And it was, and then I went back when I was 19 to work as an English teacher for a little bit." } ]

[ { "from": "human", "value": "It was incredibly challenging to be there. The language barrier, the language, the culture. All of it." }, { "from": "gpt", "value": "I mean, I was like now when I look at 16 year olds, I'm like, you're a baby. And I moved, sorry, 10 to 16 year olds was made of this. But like, I just can't believe I did that. And yeah, I didn't speak the language. I got placed in like a small city with almost no foreigners. It was just a constant audience of people staring at you because they haven't interacted with a lot of foreigners before. And yeah, it definitely, and then after that, I moved to Kenya. And I think that was one of the reasons why it was so interesting to move to the States because people were like, oh, isn't it like hard with the language barrier or the cultural difference? And I was like, dude, this is nothing. And I could speak the language. Like I could speak English well and I could kind of pass as an American, even just as I moved here. And it was such a relief where I was like, wow, I'm like an undercover foreigner because I got to a point where I realized like it doesn't matter how good my Mandarin is. I'm never, people are never gonna fully accept me here." }, { "from": "human", "value": "So yeah, yeah. And you moved, you went to Kenya." }, { "from": "gpt", "value": "You've spoken about this after your parents got divorced. Yeah. When did I talk about that? I didn't realize I told that story." }, { "from": "human", "value": "I know, I know, I know so many things." }, { "from": "gpt", "value": "What do you think this is? I know so many things. What do you think this is? Is it from when I have my Amazon Echo installed? Yeah. Yeah, so I came home from China first time. I was there for a year. Yeah, I made a few contacts. It's one of the most turned upside down days of my life. I spent a year there and I was so excited. I had really rough year and I was so excited just to come home and like be a child again. I remember thinking and just like feeling like I belonged. And then I came home and I found out that my parents had separated when I was gone and they hadn't told me because they wanted to like not affect my stay there, which I think was 100% the right decision of them to make. But I kind of came home to a house that was starting to get picked apart and- Such a big shock to your world. It was both yes and no. I think I remember I just sat down on my bed and I was like, well, this isn't what I expected, but I guess I'll move to Kenya because I was one of the few, there were a few Swedish boarding schools in the world. There was one in Brussels, Paris, London, and then one in Nairobi. And I didn't want to miss more school because I'd taken a gap year when I went to China. So I was like, I guess I'll go to Nairobi. And I'm thinking now like, I think if my parents had stayed together, granted it was amazing that they did, made the right decision in every way, but my roots kind of never grew back after that. And I think I just kept on moving abroad and moving around" }, { "from": "human", "value": "and being really restless and yeah and- Have you ever been able to find a home spiritually?" }, { "from": "gpt", "value": "I don't have a home. I have a home. Yeah, I mean, I have a home in the people around me and I have a lot of different homes. I think what I'm realizing more and more is you cannot live without consequence and compromise. And sometimes I can envy people who have that same friend group that they had their entire life or that just really belong in a place. And I realized that would be amazing, but I've chosen different experiences. And one of the upsides of that is I can feel home almost anywhere. One of the downsides of that" }, { "from": "human", "value": "is that I cannot feel fully at home anywhere. Wow, this is deeply and darkly poetic. Do you feel at home? Probably the way you put it is really beautifully put. Yeah, probably. No, I have to find a home in the people I love. What advice would you give? To young people that look at your stellar life, the trajectory of your career as a human being, as a creator, as a engineer, as a designer, as a incredibly interesting personality who's working on an autobiography. What advice would you give them? Like how to make their way in this life? Maybe high school students, maybe college students on how they can have a career they can be proud of" }, { "from": "gpt", "value": "or a life that can be proud. Hi, my God, Lex. You know, this is not the advice, but there are very few moments in a career that feel as good as you think they are going to. And there are very few moments of feeling really proud of yourself. I feel I often feel like I'm not doing it well enough or big enough or, and now I just had one of those moments hearing you say that. I'm like, oh, I'm actually doing okay. I think my main advice is enthusiasm is a much more potent fuel in life than duty. And just because something is boring doesn't mean that it's important. I kind of realized for myself that I'm so much better at the things I enjoy, but school doesn't really teach us how to stay excited about something and how to stay enthusiastic about something. And if you can find that, then you've got a goldmine of potential. So I kind of had to reprogram myself to be like, just because this is fun doesn't mean that it's not important. Because I had so much guilt about it in this weird way or where I'm like, no, this is too fun. This can't be work. And I'm like, no, it's still work." } ]

[ { "from": "human", "value": "The boring stuff isn't more important. And the vice versa, as you said, just because it's boring and hard doesn't mean it's the right thing to do. That's interesting. I'm gonna have to take that advice and think through it. Cause I'm, my genetically, I'm built a little bit. Like if this is really unpleasant, it's probably good for me. And it's a dangerous thing to think." }, { "from": "gpt", "value": "Sometimes it's true, sometimes it's not. No, and it's like, what comes really easy and where do you have that kind of effortless momentum and enthusiasm? And that is kind of the sweet spot. I think that I'm also really happy that I spent time trying out so many different jobs. I mean, I've had so many different jobs before I did it. And I would do things for a year and then I quit. And it feels like I tried on a bunch of different pants and you're like, okay, I can kind of wear this, but they're like not super comfortable or I don't love the look of them or whatever. And now I feel like I found this pair of pants that just like fits me perfectly. And that perfectly caters to my strengths and my weaknesses. Like I used to work as an editor for the Swedish government. And I remember thinking like, oh, I need to be okay that not a lot of things are happening and that things are moving slowly and that the work is kind of like monotonous. And then I realized like, or maybe I should be in a workplace where it's a benefit or strength that I want a lot of things to happen and that I can handle a high speed. Yeah. And I think that is really such a good question task as well. Like what are my strengths? What are my weaknesses?" }, { "from": "human", "value": "And then what context are most of these things strengths? And if you know that, if you know the measurements, you can find the right fitting pants. Yeah, or the right suit as Lex will tell you." }, { "from": "gpt", "value": "What do you think is the meaning of life?" }, { "from": "human", "value": "Oh, I don't think there's any meaning." }, { "from": "gpt", "value": "It's a meaningless void. No, that it doesn't have any meaning doesn't mean that it's meaningless. I don't think that there's this big grand meaning. I think a more important question is what brings you substantial joy in your life." }, { "from": "human", "value": "To me, it's the relationships with people that I have." }, { "from": "gpt", "value": "Love. Yeah, I mean, love in all different kinds of form. I'm really working on figuring out how to build more community, especially in a society that isn't really made for it. I want more passive hangouts with people," }, { "from": "human", "value": "where like I just want people who are there to get high." }, { "from": "gpt", "value": "No, together. To get high? Together. Yeah, I mean, I like, I think together, seeing somebody for lunch and kind of shooting the shit and what's the latest with you is great. But what I want is somebody to just roll up in sweatpants and open my fridge and be like, what are you going to do? I don't know, maybe I'll read a book. Yeah, I think that sharing silence, being alone together and just that type of community, I think, is what I'm really seeking out now. Because I think, yeah. And also working on a goal, on a joint goal together with other people, I think being a YouTuber can be really lonely. I mean, as much as I'm working with a team, it's like, yeah, I just want to work in a bigger project and kind of have that sense of, wow, we're doing this together. Because I think that accesses my pride a lot better than just being proud of myself. It's so much easier for me to be proud of a team" }, { "from": "human", "value": "than for me to be proud of myself. That's probably good advice for people who are doing creative work on YouTube to work on a team." }, { "from": "gpt", "value": "Yeah, and just choose, try to do things, take it from the queen of shitty robots, but try to do things with integrity, former queen of shitty robots. Do things with integrity. Anything you do on the internet is kind of, I think of things as tattoos on my internet and on my internet self. And I'm really happy that I said no to some things early in my career that I know that I would have regretted now. And just think of it in the longterm. Going viral is overwhelming and so stressful and so fun, but so intense. And I'm really happy that I managed to build that into a more longterm career" }, { "from": "human", "value": "than just have it be something that passed. And come down from the viral moment" }, { "from": "gpt", "value": "and maintain your humanity. Yeah, and also really deliberately defining what success means to you, because there are so many reasons or so many definitions that other people will give you. And especially when you're working on the internet, there are just numbers upon numbers that are like, you're doing well, you're not doing well. And something I'm really happy that I did was early on, I really try to think of like, what does success look like for me? And I realized that it's not having the world's biggest YouTube channel. It's being proud of the projects that I put out and having full say in how I spend my time. Like that is the most important thing to me. And if I had a huge YouTube channel and I was making so much money, but I kind of had this machine run me rather than the other way around, like to me, it's so important to be able to wake up in the morning and be like, I don't wanna do this anymore. And for that to be okay. And I think I defined that for myself early on and I've really tried to live by it and made decisions after that." } ]

[ { "from": "human", "value": "And I'm really happy that I did that for you. And also you're with the store, with the design you're doing now, you're putting a little bit of love in the products that create a scale. I mean, that's what Johnny I did, scale. That's the cool thing. So you can create something beautiful and then people can share that love" }, { "from": "gpt", "value": "and that scale." }, { "from": "human", "value": "It's terrifying and beautiful and I'm so here for it. I'm here for it too. I'm a big fan, I'm a big fan of who you are, I'm a big fan of everything you do, of putting yourself out there, putting your love out there in terms of the designs you create. Also just because I'm a fan of robotics, I think you inspire a lot of people. I think the Sheety robots actually incredible robots and it's incredible engineering. That's the best combination of design engineering and fun all of it together. So thank you for doing that here. I'm a big fan, you're an inspiration and thank you for sitting down with me." }, { "from": "gpt", "value": "This is awesome." }, { "from": "human", "value": "Thank you so much for having me. Thanks for listening to this conversation with Simone Yech. To support this podcast, please check out our sponsors in the description. And now let me leave you with some words from Kurt Vonnegut. We have to continually be jumping off cliffs and developing our wings on the way down. Thank you for listening and hope to see you next time." } ]

[ { "from": "human", "value": "To me, it's not enough for a large language model to be effective at answering questions and having good dialogue. You have to really integrate it into the workflow. And Notion, better than anybody else I've seen," }, { "from": "gpt", "value": "has done that." }, { "from": "human", "value": "So if that's interesting to you, Notion AI helps you work faster, write better, and think bigger, doing tasks that normally take you hours and just minutes. Try Notion AI for free when you go to Notion.com slash Lex. That's all lowercase Notion.com slash Lex to try the power of Notion AI today. This show is also brought to you by Insight Tracker, a service I use to track biological data. It's really good to do that kind of thing regularly to look at all the different markers in your body and to understand what could be made better through lifestyle and through diet changes. It's kind of obvious that decisions about your life should be made based on the data that comes from your own body. Not some kind of a population study, although those are good. Not some spiritual guru, although those are good. Not some novel, whether it's Harry Potter or Dostoyevsky. Although those are sometimes good. Not your relative who says I heard a guy say that a guy does this thing that is very bro-souncy sounding. Although sometimes it turns out to be pretty effective. Overall, the best decisions about your life should be based on the things that come from your own body. Inside Tracker uses algorithms to analyze your blood data, DNA data, fitness tracker data, all that kind of stuff to give you recommendations. You should be doing it. You should be doing it regularly. So it's not just a one-time thing, but regularly over time you see what changes led to improvements in the various markers that come from your body. Get special savings for a limited time when you go to inside tracker.com slash flex. This show is also brought to you by Indeed, a hiring website. I think the most important thing in life, not to quote in the barbarian because that would be very inappropriate to quote at this moment. And it's not actually accurate at all as a reflection of what's important in life. It only has comedic value. What I really want to say about what's important in life is the people you surround yourself with. And we spent so much of our time in the workplace seeking solutions to very difficult problems together, passionately pursuing ambitious goals, sometimes impossible goals. That is the source of meaning and sort of happiness for people. And I think part of that happiness comes from the collaboration with other human beings, the sort of professional depth of connection that you have with other human beings. Being together through the grind and surviving and accomplishing the goal or failing in a big, epic way knowing that you have tried together. And so doing that with the right team I think is one of the most important things in life. So you should surround yourself with the right team. If you're looking to join a team, you should be very selective about that or if you're looking to hire a team, you should be very selective about that and use the best tools at the job. I've used Indeed many, many times throughout my life for the teams that I've led. Don't overspend on hiring. Visit indeed.com slash Lex to start hiring now. That's indeed.com slash Lex terms and conditions apply. This is the Lex Freedom Podcast. To support it, please check out our sponsors in the description. And now, dear friends, here's Max Tagmark. You were the first ever guest on this podcast, episode number one. So first of all, Max, I just have to say thank you for giving me a chance. Thank you for starting this journey. It's been an incredible journey. Just thank you for sitting down with me and just acting like I'm somebody who matters that I'm somebody who's interesting to talk to. And thank you for doing it." }, { "from": "gpt", "value": "I meant a lot. Thanks to you for putting your heart and soul into this. I know when you delve into controversial topics, it's inevitable to get hit by what Hamlet talks about, the slings and arrows and stuff. And I really admire this. It's in an era where YouTube videos are too long and now it has to be like a 20-minute TikTok, 20-second TikTok clip. It's just so refreshing to see you going exactly against all of the advice and doing these really long-form things and that people appreciate it. Reality is nuanced." }, { "from": "human", "value": "And thanks for sharing it that way. So let me ask you again, the first question I've ever asked on this podcast, episode number one, talking to you, do you think there's intelligent life out there in the universe? Let's revisit that question. Do you have any updates?" }, { "from": "gpt", "value": "What's your view when you look out to the stars? So when we look out to the stars, if you define our universe the way most astrophysicists do, not as all of space, but the spherical region of space that we can see with our telescopes from which light has the time to reach us since our big bang, I'm in the minority. I estimate that we are the only life in this spherical volume that has invented internet radios, gotten our level of tech. And if that's true, then it puts a lot of responsibility on us to not mess this one up because if it's true, it means that life is quite rare and we are stewards of this one spark of advanced consciousness, which if we nurture it and help it grow, eventually life can spread from here out into much of our universe and we can have this just amazing future. Whereas if we instead are reckless with the technology we build and just snuff it out due to stupidity or infighting, maybe the rest of cosmic history in our universe was just gonna be a play for empty benches. But I do think that we are actually very likely to get visited by aliens, alien intelligence quite soon. But I think we are gonna be building" } ]

[ { "from": "human", "value": "that alien intelligence. So we're going to give birth to an intelligent alien civilization. Unlike anything that human, the evolution here on Earth was able to create in terms of the path, the biological path" }, { "from": "gpt", "value": "it took civilization. Yeah, and it's gonna be much more alien than a cat or even the most exotic animal on the planet right now because it will not have been created through the usual Darwinian competition where it necessarily cares about self-preservation, afraid of death, any of those things. The space of alien minds that you can build is just so much faster than what evolution will give you. And with that also comes great responsibility. For us to make sure that the kind of minds we create are the kind of minds that, it's good to create minds that will share our values and be good for humanity and life." }, { "from": "human", "value": "And also create minds that don't suffer. Do you try to visualize the full space of alien minds that AI could be? Do you try to consider all the different kinds of intelligences? Sort of generalizing what humans are able to do to the full spectrum of what intelligent creatures," }, { "from": "gpt", "value": "entities could do. I try, but I would say I fail. I mean, it's very difficult for a human mind to really grapple with something still completely alien. I mean, even for us, right? If we just try to imagine, how would it feel if we were completely indifferent towards death or individuality? If we, even if you just imagine that for example, you could just copy my knowledge of how to speak Swedish. Boom, now you can speak Swedish and you could copy any of my cool experiences and then you could delete the ones you didn't like in your own life, just like that. It would already change quite a lot about how you feel as a human being, right? You probably spend less effort studying things if you just copy them and you might be less afraid of death because if the plane you're on starts to crash, you'd just be like, oh, shucks. I'd haven't backed my brain up for four hours. So I'm gonna lose all this wonderful experiences of this flight. We might also start feeling more like compassionate, maybe with other people, if we can so readily share each other's experiences and our knowledge and feel more like a hive mind. It's very hard though. I really feel very humble about this to grapple with it. How it might actually feel that the one thing which is so obvious though, it's I think it's just really worth reflecting on is because the mind space of possible intelligence is so different from ours, it's very dangerous if we assume they're gonna be like us" }, { "from": "human", "value": "or anything like us. Well, the entirety of human written history has been through poetry, through novels, been trying to describe through philosophy, trying to describe the human condition and what's entailed in it. Like just like you said, fear of death and all those kinds of things, what is love and all of that changes if you have a different kind of intelligence. All of it, the entirety, all those poems they're trying to sneak up to what the hell it means to be human, all of that changes. How AI concerns and existential crisis sees that AI experiences, how that clashes with the human existential crisis, the human condition." }, { "from": "gpt", "value": "It's hard to fathom, hard to predict. It's hard, but it's fascinating to think about also. Even in the best case scenario where we don't lose control over the ever more powerful AI that we're building to other humans whose goals we think are horrible and where we don't lose control to the machines and AI provides the things we want. Even then you get into the questions you touched here. Maybe it's the struggle that it's actually hard to do things is part of the things that gives us meaning as well, right? So for example, I found it so shocking that this new Microsoft GPT-4 commercial that they put together has this woman talking about, showing this demo how she's gonna give a graduation speech to her beloved daughter and she asks GPT-4 to write it. If it's freaking 200 words or so if I realized that my parents couldn't be bothered struggling a little bit to write 200 words and outsource that to their computer, I would feel really offended actually. And so I wonder if eliminating too much of the struggle from our existence," }, { "from": "human", "value": "do you think that would also take away a little bit of what- It means to be human, yeah. We can't even predict. I had somebody mentioned to me that they use, they started using Chad GPT with a 3.5 and not 4.0 to write what they really feel to a person and they have a temper issue and they're basically trying to get Chad GPT to rewrite it in a nicer way, to get the point across but rewrite it in a nicer way. So we're even removing the inner asshole from our communication. So there's some positive aspects of that but mostly it's just the transformation of how humans communicate. And it's scary because so much of our society is based on this glue of communication. And if we're now using AI as the medium of communication that does the language for us, so much of the emotion that's laden in human communication and so much of the intent that's going to be handled by outsourced AI, how does that change everything? How does it change the internal state of how we feel about other human beings? What makes us lonely? What makes us excited? What makes us afraid and how we fall in love? All that kind of stuff." }, { "from": "gpt", "value": "Yeah. For me personally, I have to confess the challenge is one of the things that really makes my life feel meaningful. If I go hike a mountain with my wife, Maya, I don't want to just press a button and be at the top. I want to struggle and come up there sweaty and feel like, wow, we did this. In the same way, I want to constantly work on myself to become a better person. If I say something in anger that I regret, I want to go back and really work on myself rather than just tell an AI to from now on always filter what I write so I don't have to work on myself" } ]

[ { "from": "human", "value": "because then I'm not growing. Yeah, but then again, it could be like with chess. An AI, once it's significantly, obviously supersedes the performance of humans, it will live in its own world and provide maybe a flourishing civilizations for humans, but we humans will continue hiking mountains and playing our games, even though AI is so much smarter, so much stronger, so much superior in every single way, just like with chess. I mean, that's one possible hopeful trajectory here is that humans will continue to human and AI will just be a kind of a medium" }, { "from": "gpt", "value": "that enables the human experience to flourish. Yeah, I would phrase that as rebranding ourselves from homo sapiens to homo sentiens. Right now, sapiens, the ability to be intelligent, we've even put it in our species name. We're branding ourselves as the smartest information processing entity on the planet. That's clearly gonna change if AI continues ahead. So maybe we should focus on the experience instead, the subjective experience that we have with homo sentiens and say that's what's really valuable, the love, the connection, the other things. Get off our high horses and get rid of this hubris" }, { "from": "human", "value": "that only we can do integrals. So consciousness, the subjective experience is a fundamental value to what it means to be human." }, { "from": "gpt", "value": "Make that the priority. That feels like a hopeful direction to me, but that also requires more compassion, not just towards other humans because they happen to be the smartest on the planet, but also towards all our other fellow creatures on this planet. And I personally feel right now we're treating a lot of farm animals horribly, for example, and the excuse we're using is, oh, they're not as smart as us. But if we're not that smart in the grand scheme of things either in the post AI epoch, then surely we should value the subjective experience of a cow also." }, { "from": "human", "value": "Well, allow me to briefly look at the book, which at this point is becoming more and more visionary that you've written, I guess over five years ago, Life 3.0. So first of all, 3.0. What's 1.0? What's 2.0? What's 3.0? How's that vision sort of evolve," }, { "from": "gpt", "value": "the vision in the book evolved to today? Visionary to you. Life 1.0 is really dumb, like bacteria, in that it can't actually learn anything at all during the lifetime. The learning just comes from this genetic process from one generation to the next. Life 2.0 is us and other animals which have brains, which can learn during their lifetime a great deal. You were born without being able to speak English, and at some point you decided, hey, I wanna upgrade my software. Let's install an English speaking module. So you did? Life 3.0 does not exist yet, can replace not only its software the way we can, but also its hardware. And that's where we're heading towards at high speed. We're already maybe 2.1, because we can put in an artificial knee pacemaker, et cetera, et cetera. And if Neuralink and other companies succeed, we'll be Life 2.2, et cetera. But what the company's trying to build AGI or trying to make is of course full 3.0, and you can put that intelligence in something" }, { "from": "human", "value": "that also has no biological basis whatsoever. So less constraints and more capabilities, just like the leap from 1.0 to 2.0. There is nevertheless, you speaking so harshly about bacteria, so disrespectfully about bacteria. There is still the same kind of magic there that permeates Life 2.0 and 3.0. It seems like maybe the thing that's truly powerful about life intelligence and cautiousness was already there in 1.0." }, { "from": "gpt", "value": "Is it possible? I think we should be humble and not be so quick to make everything binary and say either it's there or it's not. Clearly there's a great spectrum and there is even a controversy by whether some unicellular organisms like amoebas can maybe learn a little bit. After all, so apologies if I offended you. It wasn't my intent. It was more that I wanted to talk up how cool it is to actually have a brain where you can learn dramatically within your lifetime. Typical human. And the higher up you get from 1.0 to 2.0 to 3.0, the more you become the captain of your own ship, the master of your own destiny, and the less you become a slave to whatever evolution gave you, right? By upgrading your software, we can be so different from previous generations and even from our parents, much more so than even a bacterium. No offense to them. And if you can also swap out your hardware and take any physical form you want, of course, really the sky's the limit." }, { "from": "human", "value": "Yeah, typical human. Yeah, so it accelerates the rate at which you can perform the computation" }, { "from": "gpt", "value": "that determines your destiny. Yeah, and I think it's worth commenting a bit on what you means in this context also if you swap things out a lot, right? This is controversial, but my current understanding is that life is best thought of not as a bag of meat or even a bag of elementary particles, but rather as a system which can process information and retain its own complexity, even though nature is always trying to mess it up. So it's all about information processing. And that makes it a lot like something like a wave in the ocean, which is not, it's water molecules, right? The water molecules bob up and down, but the wave moves forward, it's an information pattern. And the same way you, Lex, you're not the same atoms as during the first time you did with me. You've swapped out most of them, but it's still you. And the information pattern is still there. And if you could swap out your arms and whatever, you can still have this kind of continuity. It becomes much more sophisticated sort of wave forward in time where the information lives on. I lost both of my parents since our last podcast. And it actually gives me a lot of solace that this way of thinking about them, they haven't entirely died. A lot of mommy and daddy's, sorry, I'm getting a little emotional here, but a lot of their values and ideas and even jokes and so on, they haven't gone away, right? Some of them live on, I can carry on some of them. And we also live on a lot of other people. So in this sense, even with Life 2.0, we can to some extent already transcend our physical bodies and our death. And particularly if you can share your own information, your own ideas with many others, like you do in your podcast, then that's the closest immortality" } ]

[ { "from": "human", "value": "we can get with our bio bodies. You carry a little bit of them in you, in some sense. Yeah, yeah, yeah. Do you miss them?" }, { "from": "gpt", "value": "You miss your mom and dad?" }, { "from": "human", "value": "Of course, of course. What did you learn about life from them?" }, { "from": "gpt", "value": "If it can take a bit of a tangent? So many things, for starters, my fascination for math and the physical mysteries of our universe, you got a lot of that from my dad, but I think my obsession for really big questions and consciousness and so on, that actually came mostly from my mom. And what I got from both of them, which is a very core part of really who I am, I think is this feeling comfortable with not buying into what everybody else is saying, doing what I think is right. They both very much just did their own thing and sometimes they got flack for it" }, { "from": "human", "value": "and it did it anyway, it did it anyway. That's why you've always been an inspiration to me, that you're at the top of your field and you're still willing to tackle the big questions in your own way. You're one of the people that represents MIT best to me. You've always been an inspiration in that. So it's good to hear that you got that" }, { "from": "gpt", "value": "from your mom and dad in a way. Yeah, you're too kind, but yeah, I mean, the good reason to do science is because you're really curious, you don't want to figure out the truth. If you think this is how it is and everyone else says, no, no, that's bullshit and it's that way, you know, you stick with what you think is true. And even if everybody else keeps thinking it's bullshit, there's a certain, I always root for the underdog. I wouldn't watch movies. And my dad, one time, for example, when I wrote one of my craziest papers ever, talking about our universe ultimately being mathematical, which we're not going to get into today, I got this email from a quite famous professor saying, this is not only a bullshit, but it's going to ruin your career. You should stop doing this kind of stuff. I sent it to my dad. Do you know what he said? What did he say? He replied with a quote from Dante. He said, follow your own path and let the people talk. Go, dad. This is the kind of thing. He's dead, but that attitude is not." }, { "from": "human", "value": "Do you know what he said? How did losing them as a man, as a human being, change you? How did it expand your thinking about the world? How did it expand your thinking about, you know, this thing we're talking about, which is humans creating another living," }, { "from": "gpt", "value": "sentient, perhaps, being? I think it mainly did two things. One of them just going through all their stuff after they had passed away and so on, just drove home to me how important it is to ask ourselves, why are we doing these things we do? Because it's inevitable that you look at some things they spent an enormous time on and you ask, in hindsight, would they really have spent so much time on this? Would they have done something that was more meaningful? So I've been looking more in my life now and asking, why am I doing what I'm doing? And I feel it should either be something I really enjoy doing, or it should be something that I find really, really meaningful because it helps humanity and none of those two categories. Maybe I should spend less time on it, you know. The other thing is dealing with death up and personal like this, it's actually made me less afraid even less afraid of other people telling me that I'm an idiot, you know, which happens regularly. And just, I'm gonna live my life, do my thing, I'm gonna live my life. And it's made it a little bit easier for me" }, { "from": "human", "value": "to focus on what I feel is really important. What about fear of your own death? Has it made it more real that this is," }, { "from": "gpt", "value": "that this is something that happens? Yeah, it's made it extremely real. And I'm next in line in our family now, right? Me and my younger brother. But they both handled it with such dignity. That was a true inspiration also. They never complained about things, you know, when you're old and your body starts falling apart, it's more and more to complain about. They looked at what could they still do that was meaningful and they focused on that rather than wasting time. See, talking about or even thinking much about things they were disappointed in. I think anyone can make them self-depressed if they start their morning by making a list of grievances. Whereas if you start your day with a little meditation and just the things you're grateful for," }, { "from": "human", "value": "you basically choose to be a happy person. Because you only have a finite number of days. You should spend them being grateful. Well, you do happen to be working on a thing which seems to have potentially some of the greatest impact on human civilization of anything humans have ever created, which is artificial intelligence. This is on the both detailed technical level and in a high philosophical level you work on. So you've mentioned to me" }, { "from": "gpt", "value": "that there's an open letter that you're working on. It's actually going live in a few hours. I've been having late nights and early mornings. It's been very exciting actually. In short, have you seen Don't Look Up, the film? Yes, yes. I don't wanna be the movie spoiler for anyone watching this who hasn't seen it. But if you're watching this, you haven't seen it, watch it. Because we are actually acting out. It's life imitating art. Humanity is doing exactly that right now, except it's an asteroid that we are building ourselves. Almost nobody is talking about it. People are squabbling across the planet about all sorts of things which seem very minor compared to the asteroid that's about to hit us, right? Most politicians don't even have this on the radar. They think maybe in 100 years or whatever. Right now, we're at a fork on the road. This is the most important fork humanity has reached and it's over 100,000 years on this planet. We're building effectively a new species. It's smarter than us. It doesn't look so much like a species yet because it's mostly not embodied in robots, but that's a technicality which will soon be changed. And this arrival of artificial general intelligence that can do all our jobs as well as us and probably shortly thereafter super intelligence which greatly exceeds our cognitive abilities, it's gonna either be the best thing ever to happen, the humanity or the worst. I'm really quite confident that there is" } ]

[ { "from": "human", "value": "not that much middle ground there. But it would be fundamentally transformative to humans of those interests." }, { "from": "gpt", "value": "Of course, utterly and totally. Again, we branded ourselves as homo sapiens because it seemed like the basic thing. We're the king of the castle on this planet. We're the smart ones. If we can control everything else, this could very easily change. We're certainly not gonna be the smartest on the planet for very long if AI, unless AI progress just halts. We can talk more about why I think that's true because it's controversial. And then we can also talk about reasons you might think it's gonna be the best thing ever and the reason you think it's gonna be the end of humanity, which is of course super controversial. But what I think we can, anyone who's working on advanced AI can agree on is it's much like the film don't look up and that it's just really comical how little serious public debate there is about it," }, { "from": "human", "value": "given how huge it is. So what we're talking about is a development of currently things like GPT-4 and the signs it's showing of rapid improvement that may in the near term lead to development of super intelligent AGI, AI, general AI systems and what kind of impact that has on society when that thing achieves general human level intelligence and then beyond that general superhuman level intelligence. There's a lot of questions to explore here. So one, you mentioned HALT, is that the content of the letter is to suggest that maybe we should pause the development of these systems." }, { "from": "gpt", "value": "Exactly, yeah. So this is very controversial from when we talked the first time we talked about how I was involved in starting the Future Life Institute and we worked very hard on 2014, 2015 was the mainstream AI safety. The idea that there even could be risks and that you could do things about them. Before then a lot of people thought it was just really kooky to even talk about it and a lot of AI researchers felt worried that this was too flaky and it could be bad for funding and that the people who talked about it were just not, didn't understand AI. I'm very, very happy with how that's gone and that now it's completely mainstream. You go in any AI conference and people talk about AI safety and it's a nerdy technical field full of equations and blah, blah, blah, as it should be. But there is this other thing which has been quite taboo up until now calling for slowdown. So what we've constantly been saying, including myself, I've been biting my tongue a lot, is that we don't need to slow down AI development, we just need to win this race, the wisdom race between the growing power of the AI and the growing wisdom with which we manage it. And rather than trying to slow down AI, let's just try to accelerate the wisdom, do all this technical work to figure out how you can actually ensure that your powerful AI is gonna do what you want it to do and have society adapt also with incentives and regulations so that these things get put to good use. Sadly, that didn't pan out. The progress on technical AI capabilities has gone a lot faster than many people thought back when we started this in 2014. Turned out to be easier to build really advanced AI than we thought. And on the other side, it's gone much slower than we hoped with getting policy makers and others to actually put incentives in place to steer this in good directions. Maybe we should unpack it and talk a little bit about each. Why did it go faster than a lot of people thought? In hindsight, it's exactly like building flying machines. People spent a lot of time wondering about how do birds fly, you know? And that turned out to be really hard. Have you seen the TED Talk with a flying bird? Like a flying robotic bird? Yeah, it flies around the audience, but it took 100 years longer to figure out how to do that than for the Wright brothers to build the first airplane because it turned out there was a much easier way to fly. And evolution picked a more complicated one because it had its hands tied. It could only build a machine that could assemble itself, which the Wright brothers didn't care about. It can only build a machine that used only the most common atoms in the periodic table. Wright brothers didn't care about that. They could use steel, iron, atoms. And it had to be able to repair itself, and it also had to be incredibly fuel efficient. You know, a lot of birds use less than half the fuel of a remote control plane flying the same distance. For humans, throw a little more, put a little more fuel in a roof. There you go, 100 years earlier. That's exactly what's happening now with these large language models. The brain is incredibly complicated. Many people made the mistake of thinking we had to figure out how the brain does human level AI first before we could build in a machine. That was completely wrong. You can take an incredibly simple computational system called a transformer network and just train it to do something incredibly dumb. Just read a gigantic amount of text and try to predict the next word. And it turns out, if you just throw a ton of compute at that and a ton of data, it gets to be frighteningly good like GPT-4, which I've been playing with so much since it came out, right? And there's still some debate about whether that can get you all the way to full human level or not. But yeah, we can come back to the details of that and how you might get the human level AI" } ]

[ { "from": "human", "value": "even if large language models don't. Can you briefly, if it's just a small tangent, comment on your feelings about GPT-4? Suggest that you're impressed by this rate of progress, but where is it? Can GPT-4 reason? What are like the intuitions? What are human interpretable words you can assign to the capabilities of GPT-4" }, { "from": "gpt", "value": "that makes you so damn impressed with it? I'm both very excited about it and terrified." }, { "from": "human", "value": "Interesting mixture of emotions." }, { "from": "gpt", "value": "All the best things in life include those two somehow. Yeah, I can absolutely reason. Anyone who hasn't played with it, I highly recommend doing that before dissing it. Can do quite remarkable reasoning. I've had to do a lot of things which I realized I couldn't do that myself that well, even. And it obviously does it dramatically faster than we do too when you watch it type. And it's doing that while servicing a massive number of other humans at the same time. At the same time, it cannot reason as well as a human can on some tasks just because it's obviously a limitation from its architecture. We have in our heads, what in GeekSpeak is called a recurrent neural network. There are loops information can go from this neuron to this neuron to this neuron and then back to this one. You can like ruminate on something for a while. You can self-reflect a lot. These large language models that are, they cannot. Like GPT-4, it's a so-called transformer where it's just like a one way street of information basically in GeekSpeak, it's called a feed forward neural network. And it's only so deep. So it can only do logic that's that many steps and that deep and it's not, and you can create the problems which will fail to solve for that reason. But the fact that it can do so amazing things with this incredibly simple architecture already is quite stunning. And what we see in my lab at MIT when we look inside large language models to try to figure out how they're doing it, that's the key core focus of our research. It's called mechanistic interpretability in GeekSpeak. You have this machine that does something smart. You try to reverse engineer. See how does it do it? Or you think of it also as artificial neuroscience. That's exactly what neuroscientists do with actual brains. But here you have the advantage that you can, you don't have to worry about measurement errors. You can see what every neuron is doing all the time. And a recurrent thing we see again and again. That's what neuroscientists, there's been a number of beautiful papers quite recently by a lot of researchers, some of them here in this area is where when they figure out how something is done, you can say, oh man, that's such a dumb way of doing it. And you immediately see how it can be improved. Like for example, there was a beautiful paper recently where they figured out how a large language model stores certain facts like Eiffel Tower is in Paris. And they figured out exactly how it's stored and the proof that they understood it was they could edit it. They changed some of the synapses in it and then they asked it, where's the Eiffel Tower? And it said, it's in Rome. And then they asked, how do you get there? Oh, how do you get there from Germany? Oh, you take this train and the Roma Termini train station and this and that. And what might you see if you're in front of it? Oh, you might see the Colosseum. So they had edited. So they literally moved it to Rome. But the way it's storing this information, it's incredibly dumb for any fellow nerds listening to this. There was a big matrix and roughly speaking, there are certain row and column vectors which encode these things. And they correspond very hand-waverly to principal components. And it would be much more efficient for sparse matrix just store in the database and everything so far, we've figured out how these things do are ways where you can see they can easily be improved. And the fact that this particular architecture has some roadblocks built into it is in no way gonna prevent crafty researchers from quickly finding workarounds and making other kinds of architectures sort of go all the way. So in short, it's turned out to be a lot easier to build close to human intelligence than we thought. And that means our runway as a species" }, { "from": "human", "value": "to get our shit together has shortened. And it seems like the scary thing about the effectiveness of large language models. So Sam Altman, I've always had a conversation with and he really showed that the leap from GPT-3 to GPT-4 has to do with just a bunch of hacks, a bunch of little explorations about with the smart researchers doing a few little fixes here and there. It's not some fundamental leap" }, { "from": "gpt", "value": "and transformation in the architecture. More data and more computing." } ]

[ { "from": "human", "value": "More data and compute but he's had the big leaps has to do with not the data and the compute but just learning this new discipline, just like you said, so researchers are going to look at these architectures and there might be big leaps where you realize, we are we doing this in this dumb way? And all of a sudden this model, it's 10X smarter. And that can happen on any one day, on any one Tuesday or Wednesday afternoon. And then all of a sudden you have a system that's 10X smarter. It seems like it's such a new discipline, it's such a new, like we understand so little about why this thing works so damn well, that the linear improvement of compute, or exponential but the steady improvement of compute, steady improvement of the data may not be the thing that even leads to the next leap. It could be a surprise little hack" }, { "from": "gpt", "value": "that improves everything. Yeah, cause were a lot of little leaps here and there because so much of this is out of the open also and so many smart people are looking at this and trying to figure out little leaps here and there and it becomes this sort of collective race where a lot of people feel if I don't take the leap someone else will. And it is actually very crucial for the other part but why do we wanna slow this down? So again, what this open letter is calling for is just pausing all training of systems that are more powerful than GPT for, for six months, to give a chance for the labs to coordinate a bit on safety and for society to adapt, give the right incentives to the labs. Cause I, you know, you've interviewed a lot of these people who lead these labs and you know just as well as I do that they're good people, they're idealistic people. They're doing this first and foremost because they believe that AI has a huge potential to help humanity and, but at the same time, they are trapped in this horrible race to the bottom. Have you read Meditations on Moloch by Scott Alexander? Yes. Yeah, it's a beautiful essay on this poem by Ginsburg where he interprets it as being about this monster. It's this game theory monster that, that pits people into, against each other in this, that this race to the bottom where everybody ultimately loses it. The evil thing about this monster is even though everybody sees it and understands, they still can't get out of the race, right? Most, a good fraction of all the bad things that we humans do are caused by Moloch. And I like Scott Alexander's naming of the monster so we humans can think of it as a thing. If you look at why do we have overfishing? Why do we have more generally the tragedy of the commons? Why is it that, so Liv Booray," }, { "from": "human", "value": "I don't know if you had her on your podcast." }, { "from": "gpt", "value": "Yeah, she's become a friend, yeah. Great, she made this awesome point recently that beauty filters, that a lot of female influencers feel pressured to use are exactly Moloch in action again. First, nobody was using them and people saw them just the way they were. And then some of them started using it and becoming ever more plastic, fantastic. And then the other ones that weren't using it started to realize that if they wanna just keep their market share, they have to start using it too. And then you're in the situation where they're all using it. And none of them has any more market share or less than before. So nobody gained anything, everybody lost and they have to keep becoming ever more plastic, fantastic also, right? But nobody can go back to the old way because it's just too costly, right? Moloch is everywhere. And Moloch is not a new arrival on the scene either. We humans have developed a lot of collaboration mechanisms to help us fight back against Moloch through various kinds of constructive collaboration. The Soviet Union and the United States did sign the number of arms control treaties against Moloch who is trying to stoke them into unnecessarily risky nuclear arms races, et cetera, et cetera. And this is exactly what's happening on the AI front. This time, it's a little bit geopolitics, but it's mostly money where there's just so much commercial pressure. If you take any of these leaders of the top tech companies, if they just say, you know, this is too risky, I want to pause for six months, they're going to get a lot of pressure from shareholders and others. They're like, well, you know, if you pause, but those guys don't pause, you don't want to get our lunch eaten and shareholders even have a power to replace the executives in the worst case, right? So we did this open letter because we want to help these idealistic tech executives to do what their heart tells them by providing enough public pressure on the whole sector to just pause so that they can all pause in a coordinated fashion. And I think without the public pressure, none of them can do it alone, push back against their shareholders, no matter how good hearted they are." }, { "from": "human", "value": "Because Moloch is a really powerful foe. So the idea is to, for the major developers of AI systems like this, so we're talking about Microsoft, Google," }, { "from": "gpt", "value": "Meta, and anyone else? Well, OpenAI is very close with Microsoft now, of course, and there are plenty of smaller players. For example, Anthropic is very impressive. There's Conjecture, there's many, many, many players. I don't want to make a long list to leave anyone out. And Microsoft now of course, for that reason, it's so important that some coordination happens, that there's external pressure on all of them, saying you all need to pause. Because then the researchers in these organizations, the leaders who want to slow down a little bit, they can say to their shareholders, everybody's slowing down because of this pressure," } ]

[ { "from": "human", "value": "and it's the right thing to do. Have you seen in history," }, { "from": "gpt", "value": "there are examples where it's possible to pause the Moloch? Absolutely. Human cloning, for example, you could make so much money on human cloning. Why aren't we doing it? Because biologists thought hard about this and felt like this is way too risky. They got together in the 70s and the Selimar and decided even to stop a lot more stuff, also just editing the human germline, gene editing that goes into our offspring, and decided, let's not do this because it's too unpredictable what it's gonna lead to. We could lose control over what happens to our species. So they paused. There was a ton of money to be made there. So it's very doable, but you just need a public awareness of what the risks are, and the broader community coming in and saying, hey, let's slow down. And another common pushback I get today is, we can't stop in the West because China, and in China, undoubtedly, they also get told, we can't slow down because the West, because both sides think they're the good guy. But look at human cloning. Did China forge ahead with human cloning? There's been exactly one human cloning that's actually been done that I know of. It was done by a Chinese guy. Do you know where he is now? In jail. And you know who put him there? Who? Chinese government. Not because Westerners said, China, look, this is... No, the Chinese government put him there because they also felt they like control, the Chinese government. If anything, maybe they are even more concerned about having control than Western governments, have no incentive of just losing control over where everything is going. And you can also see the Ernie Bot that was released by, I believe, Baidu recently. They got a lot of pushback from the government and had to rein it in, you know, in a big way. I think once this basic message comes out that this isn't an arms race, it's a suicide race, where everybody loses if anybody's AI goes out of control, it really changes the whole dynamic. It's not, I'll say this again, because this is a very basic point I think a lot of people get wrong. Because a lot of people dismiss the whole idea that AI can really get very superhuman, because they think there's something really magical about intelligence such that it can only exist in human minds. You know, because they believe that, I think it's gonna kind of get to just more or less GPT four plus plus, and then that's it. They don't see it as a suicide race. They think whoever gets that first, they're gonna control the world, they're gonna win. That's not how it's gonna be. And we can talk again about the scientific arguments from why it's not gonna stop there. But the way it's gonna be is if anybody completely loses control and, you know, you don't care if someone manages to take over the world who really doesn't share your goals, you probably don't really even care very much about what nationality they have. You're not gonna like it. It's much worse than today. If you live in Orwellian dystopia, what do you care who's created it, right? And if someone, if it goes farther, and we just lose control even to the machines so that it's not us versus them, it's us versus it. What do you care who created this unaligned entity which has goals different from humans ultimately and we get marginalized, we get made obsolete, we get replaced. That's what I mean when I say it's a suicide race. It's kind of like we're rushing towards this cliff, but the closer the cliff we get, the more scenic the views are and the more money there is there. So we keep going, but we have to also stop at some point, right, quit while we're ahead. And it's a suicide race which cannot be won, but the way to really benefit from it is to continue developing awesome AI a little bit slower. So we make it safe, make sure it does the things that humans want and create a condition where everybody wins. The technology has shown us that geopolitics and politics in general is not a zero sum game" }, { "from": "human", "value": "at all, so there is some rate of development that will lead us as a human species to lose control of this thing and the hope you have is that there's some lower level of development which will not allow us to lose control. This is an interesting thought you have about losing control. So if you are somebody like Sandra Pritchey or Sam Altman at the head of a company like this, you're saying if they develop an AGI, they too will lose control of it. So no one person can maintain control," }, { "from": "gpt", "value": "no group of individuals can maintain control. If it's created very, very soon and it's a big black box that we don't understand like the large language models, yeah, then I'm very confident they're gonna lose control. But this isn't just me saying it. Sam Altman and Demis Asabes have both said, they themselves acknowledge that there's really great risks with this and they wanna slow down once they feel it gets scary. But it's clear that they're stuck in this, again, Moloch is forcing them to go a little faster than they're comfortable with because of pressure from just commercial pressures, right? To get a bit optimistic here, of course, this is a problem that can be ultimately solved. To win this wisdom race, it's clear that what, we hope that it was gonna happen, hasn't happened. The capability progress has gone faster than a lot of people thought, and the progress in the public sphere of policymaking and so on has gone slower than we thought. Even the technical AI safety has gone slower. A lot of the technical safety research was kind of banking on that large language models and other poorly understood systems couldn't get us all the way, that you had to build more of a kind of intelligence that you could understand. Maybe it could prove itself safe, things like this. And I'm quite confident that this can be done so we can reap all the benefits, but we cannot do it as quickly as this out-of-control express train we are on now is gonna get the AGI." } ]

[ { "from": "human", "value": "That's why we need a little more time, I feel. Is there something to be said, well, like Sam Allman talked about, which is while we're in the pre-AGI stage, to release often and as transparently as possible, to learn a lot. So as opposed to being extremely cautious, release a lot. Don't invest in a closed development where you focus on AI safety, while it's somewhat dumb, quote unquote, release as often as possible. And as you start to see signs of human level intelligences or superhuman level intelligence," }, { "from": "gpt", "value": "then you put a halt on it. Well, what a lot of safety researchers have been saying for many years is that the most dangerous things you can do with an AI is, first of all, teach it to write code. Because that's the first step towards recursive self-improvement, which can take it from AGI to much higher levels. Okay, oops, we've done that. And another thing, high risk is connected to the internet. Let it go to websites, download stuff on its own, talk to people. Oops, we've done that already. You know, Elias Jukowski, you said you interviewed him recently, right? Yes, yes. He had this tweet recently, which gave me one of the best laughs in a while, where he was like, hey, people used to make fun of me and say, you're so stupid, Eliezer, because you're saying you have to worry. Obviously, developers, once they get to really strong AI, first thing you're gonna do is never connect it to the internet, keep it in a box, where you can really study it. So he had written it in the meme form," }, { "from": "human", "value": "so it was like, then, and then that, and then now." }, { "from": "gpt", "value": "LOL, let's make a chatbot. And the third thing is Stuart Russell. And the third thing, amazing AI researcher, he has argued for a while that we should never teach AI anything about humans. Above all, we should never let it learn about human psychology and how you manipulate humans. That's the most dangerous kind of knowledge you can give it. Yeah, you can teach it all it needs to know about how to cure cancer and stuff like that, but don't let it read Daniel Kahneman's book about cognitive biases and all that. And then, oops, LOL, let's invent social media, recommender algorithms, which do exactly that. They get so good at knowing us and pressing our buttons that we're starting to create a world now where we just have ever more hatred, because they figured out that these algorithms, not for out of evil, but just to make money on advertising that the best way to get more engagement with euphemism, get people glued to their little rectangles," }, { "from": "human", "value": "or it is just to make them pissed off. That's really interesting that a large AI system that's doing the recommender system kind of task on social media is basically just studying human beings, because it's a bunch of us rats giving it signal, nonstop signal. It'll show a thing and then we give signal and whether we spread that thing, we like that thing, that thing increases our engagement, gets us to return to the platform. It has that on the scale of hundreds of millions of people constantly. So it's just learning and learning and learning. And presumably, if the number of parameters in neural network that's doing the learning, and more end-to-end the learning is, the more it's able to just basically encode how to manipulate human behavior," }, { "from": "gpt", "value": "how to control humans at scale. Exactly, and that is not something you think is in humanity's interest. Right now, it's mainly letting some humans manipulate other humans for profit and power, which already caused a lot of damage, and eventually that's a sort of skill that can make AIs persuade humans to let them escape whatever safety precautions we had put. There was a really nice article in the New York Times recently by Yuval Noah Harari and two co-authors, including Tristan Harris from The Social Dilemma. They have this phrase in there, I love. Humanity's first contact with advanced AI was social media. And we lost that one. We now live in a country where there's much more hate in the world, where there's much more hate, in fact. And in our democracy that we're having this conversation and people can't even agree on who won the last election, and we humans often point fingers at other humans and say it's their fault. But it's really Moloch and these AI algorithms. We got the algorithms and then Moloch pitted the social media companies against each other so nobody could have a less creepy algorithm because then they would lose out on revenue" }, { "from": "human", "value": "to the other company. Is there any way to win that battle back, just if we just linger on this one battle that we've lost in terms of social media? Is it possible to redesign social media, this very medium in which we use as a civilization to communicate with each other, to have these kinds of conversation, to have discourse to try to figure out how to solve the biggest problems in the world, whether that's nuclear war or the development of AGI?" }, { "from": "gpt", "value": "Is it possible to do social media correctly? I think it's not only possible, but it's necessary. Who are we kidding that we're gonna be able to solve all these other challenges if we can't even have a conversation with each other that's constructive? The whole idea, the key idea of democracy is that you get a bunch of people together and they have a real conversation. The ones you try to foster on this podcast or you respectfully listen to people you disagree with and you realize actually, there are some things actually, some common ground we have and we both agree let's not have a nuclear war, let's not do that, et cetera, et cetera. We're kidding ourselves thinking we can face off the second contact with ever more powerful AI that's happening now with these large language models if we can't even have a functional conversation in the public space. That's why I started the Improve the News project, improvethenews.org, but I'm an optimist fundamentally in that there is a lot of intrinsic goodness in people and that what makes the difference between someone doing good things for humanity and bad things is not some sort of fairy tale thing that this person was born with the evil gene and this one is not born with a good gene, no. I think it's whether we put, whether people find themselves in situations that bring out the best in them or they bring out the worst in them. And I feel we're building an internet" } ]

[ { "from": "human", "value": "and a society that brings out the worst. But it doesn't have to be that way. No, it does not. It's possible to create incentives and also create incentives that make money." }, { "from": "gpt", "value": "They both make money and bring out the best in people. I mean, in the long term, it's not a good investment for anyone to have a nuclear war, for example. And is it a good investment for humanity if we just ultimately replace all humans by machines and then we're so obsolete that eventually there are no humans left? Well, it depends, I guess, on how you do the math. But I would say by any reasonable economic standard, if you look at the future income of humans and there aren't any, that's not a good investment. Moreover, why can't we have a little bit of pride in our species, dammit? Why should we just build another species that gets rid of us? If we were Neanderthals, would we really consider it a smart move if we had really advanced biotech to build homo sapiens? You might say, hey, Max, let's build these homo sapiens. They're gonna be smarter than us. Maybe they can help us defend us better against the predators and help fix our parcaves, make them nicer. We'll control them undoubtedly. So then they build a couple, a little baby girl, a little baby boy, either. And then you have some wise, old Neanderthal elder who's like, hmm, I'm scared that we're opening a Pandora's box here and that we're gonna get outsmarted by these super Neanderthal intelligences and there won't be any Neanderthals left. But then you have a bunch of others in the cave, are you such a Luddite scaremonger? Of course, they're gonna wanna keep us around because we are their creators and the smarter, I think the smarter they get, the nicer they're gonna get. They're gonna leave us, they're gonna want us around and it's gonna be fine. And besides, look at these babies, they're so cute. It's clearly, they're totally harmless. Those babies are exactly GPT-4. It's not, I wanna be clear. It's not GPT-4 that's terrifying. It's the GPT-4 is a baby technology. Microsoft even had a paper recently out with the title of something like sparkles of AGI. Well, they were basically saying this is baby AI, like these little Neanderthal babies. And it's gonna grow up. There's gonna be other systems from the same company, from other companies, they'll be way more powerful but they're gonna take all the things, ideas from these babies. And before we know it, we're gonna be like those last Neanderthals who were pretty disappointed" }, { "from": "human", "value": "when they realized that they were getting replaced. Well, this interesting point you make, which is the programming, it's entirely possible that GPT-4 is already the kind of system that can change everything by writing programs." }, { "from": "gpt", "value": "Life, life three, it's, yeah, it's because it's life 2.0. The systems I'm afraid of are gonna look nothing like a large language model and they're not, but once it gets, once it or other people figure out a way of using this tech to make much better tech, right? It's just constantly replacing its software. And from everything we've seen about how these work under the hood, they're like the minimum viable intelligence. They do everything in a dumbest way that still works, sort of. Yeah. And so they are life 3.0, except when they replace their software, it's a lot faster than when you decide to learn Swedish. And moreover, they think a lot faster than us too. So when, you know, we don't think of how one logical step every nanosecond or so, the way they do. And we can't also just suddenly scale up our hardware massively in the cloud, so limited, right? So they are, they are also life, consume become a little bit more like life 3.0 in that if they need more hardware, hey, just rent it in the cloud, you know, how do you pay for it?" }, { "from": "human", "value": "Well, with all the services you provide. And what we haven't seen yet, which could change a lot is entire software system. So right now programming is done sort of in bits and pieces as an assistant tool to humans. But I do a lot of programming and with the kind of stuff that GPT-4 is able to do, I mean, it's replacing a lot what I'm able to do. But you still need a human in the loop to kind of manage the design of things, manage like what are the prompts that generate the kind of stuff, to do some basic adjustment of the code, to do some debugging. But if it's possible to add on top of GPT-4 kind of feedback loop of self-debugging improving the code and then you launch that system on to the wild on the internet because everything is connected and have it do things, have it interact with humans and then get that feedback. Now you have this giant ecosystem of humans. That's one of the things that Elon Musk recently sort of tweeted as a case why everyone needs to pay seven dollars or whatever for Twitter. To make sure they're real. Make sure they're real. We're not going to be living in a world where the bots are getting smarter and smarter and smarter to a degree where you can't tell the difference between a human and a bot. That's right. And now you can have bots outnumber humans by one million to one. Which is why he's making the case why you have to pay to prove you're human. Which's one of the only mechanisms to prove." }, { "from": "gpt", "value": "Which is depressing. That's right. And I feel we have to remember as individuals we should from time to time ask ourselves why are we doing what we're doing. And as a species we need to do that too. So if we're building, as you say, machines that are outnumbering us and more and more outsmarting us and replacing us on the job market not just for the dangerous and boring tasks but also for writing poems and doing art and things that a lot of people find really meaningful. Gotta ask ourselves why. Why are we doing this? We are, the answer is Molok is tricking us into doing it. And it's such a clever trick that even though we see the trick we still have no choice but to fall for it, right? Also the thing you said about you using co-pilot AI tools to program faster. How many times, what factor faster would you say you code now? Does it go twice as fast or?" } ]

[ { "from": "human", "value": "I don't really, because it's such a new tool. Yeah. I don't know if speed is significantly improved but it feels like I'm a year away" }, { "from": "gpt", "value": "from being five to 10 times faster, 10 times faster. So if that's typical for programmers then you're already seeing another kind of self, recursive self-improvement, right? Because previously one like a major generation of improvement of the codes would happen on the human R and D timescale. And now if that's five times shorter then it's gonna take five times less time than it otherwise would to develop the next level of these tools and so on. So this is exactly the sort of beginning of an intelligence explosion. There can be humans in the loop a lot in the early stages and then eventually humans are needed less and less and the machines can more kind of go along. But what you said there is just an exact example of these sort of things. Another thing which I was kind of lying on my psychiatrist, imagining I'm on a psychiatrist couch here saying, well, what are my fears that people would do with AI systems and other, so I mentioned three that I had fears about many years ago that they would do. Namely, teach it the code, connect it to the internet and teach it to manipulate humans. A fourth one is building an API where code can control the super powerful thing, right? Very unfortunate because one thing that systems like GPT-4 have going for them is that they are an oracle in the sense that they just answer questions. There is no robot connected to GPT-4. GPT-4 can't go and do stock trading based on its thinking. It's not an agent. An intelligent agent is something that takes in information from the world, processes it there to figure out what action to take based on its goals that it has and then does something back on the world. But once you have an API, for example, GPT-4, nothing stops Joe Schmoe and a lot of other people from building real agents, which just keep making calls somewhere in some inner loop somewhere to these powerful oracle systems, which makes them themselves much more powerful. That's another kind of unfortunate development, which I think we would have been better off delaying. I don't want to pick on any particular companies. I think they're all under a lot of pressure to make money. And again, the reason we're calling for this pause is to give them all cover to do what they know is the right thing. Slow down a little bit at this point. But everything we've talked about, I hope will make it clear to people watching this why these sort of human level tools can cause gradual acceleration. You keep using yesterday's technology to build tomorrow's technology. And when you do that over and over again, you naturally get an explosion. That's the definition of an explosion in science. Like if you have two people and they fall in love, now you have four people and then they can make more babies and now you have eight people. And then you have 16, 32, 64, et cetera. We call that a population explosion, where it's just that if it's instead free neutrons and a nuclear reaction, if each one can make more than one, then you'll get an exponential growth in that. We call it a nuclear explosion. All explosions are like that, in an intelligence explosion, it's just exactly the same principle that some quantum, some amount of intelligence can make more intelligence than that and then repeat." }, { "from": "human", "value": "You always get the exponentials. What's your intuition while you mentioned there's some technical reasons why it doesn't stop at a certain point. What's your intuition? Do you have any intuition why it might stop?" }, { "from": "gpt", "value": "It's obviously gonna stop when it bumps up against the laws of physics. There are some things you just can't do" }, { "from": "human", "value": "no matter how smart you are, right?" }, { "from": "gpt", "value": "Allegedly, because we don't know the full laws of physics. And because we don't know the full yet, right? Seth Lloyd wrote a really cool paper on the physical limits on computation, for example. If you make it, put too much energy into it and the finite space, it'll turn into a black hole. You can't move information around faster than the speed of light, stuff like that, but it's hard to store way more than a modest number of bits per atom, et cetera. But those limits are just astronomically above, like 30 orders of magnitude above where we are now. So bigger, different, bigger jump in intelligence than if you go from an ant to a human. I think, of course, what we want to do is have a controlled thing. A nuclear reactor, you put moderators in to make sure exactly it doesn't blow up out of control, right? When we do experiments with biology and cells and so on, we also try to make sure it doesn't get out of control. We can do this with AI too. The thing is, we haven't succeeded yet. And Moloch is exactly doing the opposite, just fueling, just egging everybody on. Faster, faster, faster. Or the other company is gonna catch up with you, or the other country is gonna catch up with you. We have to want this stuff. And I don't believe in this, just asking people to look into their hearts and do the right thing. It's easier for others to say that. But if you're in a situation where your company is gonna get screwed, by other companies that are not stopping, you're putting people in a very hard situation. The right thing to do is change the whole incentive structure instead. And this is not an old... Maybe I should say one more thing about this, because Moloch has been around as humanity's number one or number two enemy since the beginning of civilization. And we came up with some really cool countermeasures. First of all, already over 100,000 years ago, evolution realized that it was very unhelpful that people kept killing each other all the time. So it genetically gave us compassion and made it so that if you get two drunk dudes getting into a pointless bar fight, they might give each other black eyes, but they have a lot of inhibition towards just killing each other. And similarly, if you find a baby lying on the street when you go out for your morning jog tomorrow, you're gonna stop and pick it up, right? Even though it may make you late for your next podcast. So evolution gave us these genes that make our own egoistic incentives more aligned with what's good for the greater group or part of, right? And then as we got a bit more sophisticated and developed language, we invented gossip, which is also a fantastic anti-Moloch, right? Because now it really discourages liars, moochers, cheaters, because their own incentive now is not to do this because word quickly gets around and then suddenly people aren't gonna invite them to their dinners anymore and trust them. And then when we got still more sophisticated and bigger societies, we invented the legal system where even strangers who couldn't rely on gossip and things like this would treat each other, would have an incentive. Now those guys in the bar fight, even if someone is so drunk that he actually wants to kill the other guy, he also has a little thought in the back of his head that do I really wanna spend the next 10 years eating really crappy food in a small room? I'm just gonna chill out, you know? And we similarly have tried to give these incentives to our corporations by having regulation and all sorts of oversight so that their incentives are aligned with the greater good. We tried really hard and the big problem that we're failing now is not that we haven't tried before, but it's just that the tech is growing much, is developing much faster than the regulators have been able to keep up, right? So regulators, it's kind of comical that European Union right now is doing this AI act, right? Which, in the beginning, they had a little opt-out exception that GPT-4 would be completely excluded from regulation. Brilliant idea. What's the logic behind that? Some lobbyists pushed successfully for this. So we were actually quite involved with the Future Life Institute. Mark Bracco, Mr. Ook, Anthony Aguirre and others, you know, we're quite involved with educating various people involved in this process about these general purpose AI models coming and pointing out that they would become the laughing stock if they didn't put it in. So the French started pushing for it. It got put in to the draft and it looked like all was good. And then there was a huge counter push from lobbyists. There were more lobbyists in Brussels from tech companies and from oil companies, for example. And it looked like it might as we can maybe get taken out again. And now GPT-4 happened. And I think it's gonna stay in. But this just shows, you know, Moloch can be defeated, but the challenge we're facing is that the tech is generally much faster than what the policymakers are. And a lot of the policymakers also don't have a tech background. So it's, you know, we really need to work hard to educate them on what's taking place here. So we're getting this situation where the first kind of non, so I define artificial intelligence just as non-biological intelligence. And by that definition, a company, a corporation is also an artificial intelligence because the corporation isn't, it's humans, it's a system. If its CEO decides, if the CEO of a tobacco company decides one morning she or he doesn't wanna sell cigarettes anymore, they'll just put another CEO in there. It's not enough to align the incentives of individual people or align individual computers, the incentives to their owners, which is what technically I safety research is about. You also have to align the incentives of corporations with a greater good. And some corporations have gotten so big and so powerful very quickly that in many cases their lobbyists instead align the regulators to what they want rather than the other way around." } ]

[ { "from": "human", "value": "It's a classic regulatory capture. All right. Is the thing that the slowdown hopes to achieve give enough time to the regulators to catch up or enough time to the companies themselves to breathe and understand how to do AI safety correctly?" }, { "from": "gpt", "value": "I think both. I think that the vision, the path to success I see is first, you give a breather actually to the people in these companies. That their leadership wants to do the right thing and they all have safety teams and so on on their companies. Give them a chance to get together with the other companies and the outside pressure can also help catalyze that, right, and work out what is it that's, what are the reasonable safety requirements one should put on future systems before they get rolled out? There are a lot of people also in academia and elsewhere outside of these companies who can be brought into this and have a lot of very good ideas. And then I think it's very realistic that within six months you can get these people coming up. So here's a white paper, here's what we all think is reasonable. You know, you didn't, just because cars killed a lot of people, you didn't ban cars, but they got together a bunch of people and decided, you know, in order to be allowed to sell a car, it has to have a seatbelt in it. There are the analogous things that you can start requiring a future AI systems so that they are safe. And once this heavy lifting, this intellectual work has been done by experts in the field which can be done quickly. I think it's going to be quite easy to get policymakers to see, yeah, this is a good idea. And it's, you know, for the companies to fight Molok, they want, and I believe Sam Altman has explicitly called for this, they want the regulators to actually adopt it so that their competition is going to abide too, right? You don't want to be enacting all these principles and then you abide by them. And then there's this one little company that doesn't sign onto it. And then now they can gradually overtake you. Then the companies will be able to sleep secure" }, { "from": "human", "value": "knowing that everybody's playing by the same rules. So do you think it's possible to develop guardrails that keep the systems from basically damaging irreparably humanity while still enabling sort of the capitalist fueled competition between companies as they develop how to best make money with this AI?" }, { "from": "gpt", "value": "You think there's a balancing that's possible? Absolutely, I mean, we've seen that in many other sectors where you've had the free market produce quite good things without causing particular harm. When the guardrails are there and they work, you know, capitalism is a very good way of optimizing for just getting the same things done more efficiently. But it was good, you know, and like in hindsight, and I've never met anyone even on parties way over on the right in any country who think it was a bad, thinks it was a terrible idea to ban chile labor," }, { "from": "human", "value": "for example. Yeah, but it seems like this particular technology has gotten so good, so fast, become powerful to a degree where you could see in the near term the ability to make a lot of money and to put guardrails, to develop guardrails quickly in that kind of context seems to be tricky. It's not similar to cars or chile labor. It seems like the opportunity to make a lot of money here" }, { "from": "gpt", "value": "very quickly is right here before us, right here before us." }, { "from": "human", "value": "Yeah, so again, there's this cliff." }, { "from": "gpt", "value": "Yeah, it gets quite scenic. The closer the cliff you go, the more money there is, the more gold ink gets thrown on the ground, you can pick up or whatever, so you wanna drive there very fast. But it's not in anyone's incentive that we go over the cliff and it's not like everybody's in their own car, all the cars are connected together with a chain. So if anyone goes over, they'll start dragging others down, the others down too. And so ultimately it's in the selfish interests also of the people in the companies to slow down when you start seeing the corners of the cliff there in front of you, right? And the problem is that even though the people who are building the technology and the CEOs, they really get it. The shareholders and these other market forces, they are people who don't honestly understand that the cliff is there. They usually don't, you have to get quite into the weeds to really appreciate how powerful this is and how fast. And a lot of people are even still stuck again in this idea that intelligent, in this carbon chauvinism, as I like to call it, that you can only have our level of intelligence in humans, that there's something magical about it. Whereas the people in the tech companies who build this stuff, they all realize that intelligence is information processing of a certain kind. And it really doesn't matter at all whether the information is processed by carbon atoms in neurons in brains or by silicon atoms in some technology we build. So you brought up capitalism earlier and there are a lot of people who love capitalism and a lot of people who really, really don't. And it struck me recently that what's happening with capitalism here is exactly analogous to the way in which super intelligence might wipe us out. So, you know, I studied economics for my undergrad, Stockholm School of Economics, yay." }, { "from": "human", "value": "Well, no, I tell them." }, { "from": "gpt", "value": "So I was very interested in how you could use market forces to just get stuff done more efficiently but give the right incentives to the market so that it wouldn't do really bad things. So Dylan Hadfield-Manel, who's a professor and colleague of mine at MIT, wrote this really interesting paper with some collaborators recently where they proved mathematically that if you just take one goal that you just optimized for on and on and on indefinitely, you think it's gonna bring you in the right direction. What basically always happens is in the beginning, it will make things better for you. But if you keep going at some point, it's gonna start making things worse for you again and then gradually it's gonna make it really, really terrible. So just as a simple, the way I think of the proof is, suppose you wanna go from here back to Austin, for example, and you're like, okay, yeah, let's just, let's go south. But you put in exactly the right, sort of the right direction. Just optimize that, south as possible. You get closer and closer to Austin, but there was always some little error. So you're not going exactly towards Austin, but you get pretty close. But eventually you start going away again and eventually you're gonna be leaving the solar system. And they proved, it's a beautiful mathematical proof. This happens generally. And this is very important for AI because even though Stuart Russell has written a book and given a lot of talks on why it's a bad idea to have AI just blindly optimize something, that's what pretty much all our systems do. We have something called the loss function that we're just minimizing or reward function we're just maximizing stuff. And capitalism is exactly like that too. We wanted to get stuff done more efficiently that people wanted. So we introduced the free market. Things got done much more efficiently than they did in say communism, right? And it got better. But then it just kept optimizing and kept optimizing. And you got ever bigger companies and ever more efficient information processing. And now also very much powered by IT. And eventually a lot of people are beginning to feel, wait, we're kind of optimizing a bit too much. Why did we just chop down half the rainforest? And why did suddenly these regulators get captured by lobbyists and so on? It's just the same optimization that's been running for too long. If you have an AI that actually has power over the world and you just give it one goal and just like keep optimizing that, most likely everybody's gonna be like, yay, this is great in the beginning. Things are getting better. But it's almost impossible to give it exactly the right direction to optimize in. And then eventually all hay breaks loose, right? Nick Bostrom and others have given example to sound quite silly. Like what if you just wanna like tell it to cure cancer or something? And that's all you tell it. Maybe it's gonna decide to take over entire continents just so we can get more supercomputer facilities in there and figure out how to cure cancer backwards. And then you're like, wait, that's not what I wanted, right? And the issue with capitalism and the issue with the front I have kind of merged now because the malloc I talked about is exactly the capitalist malloc that we have built an economy that is optimizing for only one thing, profit, right? And that worked great back when things were very inefficient and then now it's getting done better. And it worked great as long as the companies were small enough that they couldn't capture the regulators. But that's not true anymore, but they keep optimizing. And now they realize that they can these companies can make even more profit by building ever more powerful AI, even if it's reckless but optimize more and more and more and more and more. So this is malloc again, showing up. And I just wanna anyone here who has any concerns about late stage capitalism having gone a little too far you should worry about super intelligence" } ]

[ { "from": "human", "value": "because it's the same villain in both cases, it's malloc. And optimizing one objective function aggressively," }, { "from": "gpt", "value": "blindly is going to take us there. Yeah, we have to pause from time to time and look into our hearts and ask why are we doing this? Is this, am I still going towards Austin or have I gone too far?" }, { "from": "human", "value": "Maybe we should change direction. And that is the idea behind the halt for six months. Why six months? It seems like a very short period. Can we just linger and explore different ideas here? Because this feels like a really important moment in human history where pausing would actually have" }, { "from": "gpt", "value": "a significant positive effect. We said six months because we figured the number one pushback we were gonna get in the West was like, but China and everybody knows there's no way that China is gonna catch up with the West on this in six months. So it's that argument goes off the table and you can forget about geopolitical competition and just focus on the real issue." }, { "from": "human", "value": "That's why we put this. That's really interesting. But you've already made the case that even for China, if you actually wanna take on that argument, China too would not be bothered by a longer halt because they don't wanna lose control" }, { "from": "gpt", "value": "even more than the West doesn't." }, { "from": "human", "value": "That's what I think. That's a really interesting argument. I have to actually really think about that, which the kind of thing people assume is if you develop an AGI, that open AI, if they're the ones that do it, for example, they're going to win." }, { "from": "gpt", "value": "But you're saying, no, everybody loses, everybody loses. Yeah, it's gonna get better and better and better. And then kaboom, we all lose." }, { "from": "human", "value": "That's what's gonna happen. When lose and win are defined on a metric of basically" }, { "from": "gpt", "value": "quality of life for human civilization and for Sam Altman. Both. To be blunt, my personal guess and people can quibble this is that we're just gonna, there won't be any humans. That's it, that's what I mean by lose. You know, we can see in history, once you have some species or some group of people who aren't needed anymore, it doesn't usually work out so well for them, right? There were a lot of horses that were used for traffic in Boston and then the car got invented and most of them got, you know, we don't need to go there. And if you look at humans, you know, right now, why did the labor movement succeed after the industrial revolution? Because it was needed. Even though we had a lot of mollocks and there was child labor and so on, you know, the company still needed to have workers and that's why strikes had power and so on. If we get to the point where most humans aren't needed anymore, I think it's quite naive to think that they're gonna still be treated well. You know, we say that, yeah, yeah, everybody's equal and the government will always, we always protect them. But if you look in practice, groups that are very disenfranchised and don't have any actual power usually get screwed. And now in the beginning, so industrial revolution, we automated away muscle work. But that got worked out pretty well eventually because we educated ourselves and started working with our brains instead and got usually more interesting, better paid jobs. But now we're beginning to replace brain work. So we replaced a lot of boring stuff like we got the pocket calculator so you don't have people adding multiplying numbers anymore at work. Fine, there were better jobs they could get. But now GPT-4, you know, and the stable diffusion and techniques like this, they're really beginning to blow away some real some jobs that people really love having. It was a heartbreaking article just post just yesterday on social media I saw about this guy who was doing 3D modeling for gaming and all of a sudden now that he got this new software he just says prompts and he feels his whole job that he loved lost its meaning, you know. And I asked GPT-4 to rewrite Twinkle Twinkle Little Star in the style of Shakespeare. I couldn't have done such a good job. It was really impressive. You've seen a lot of the art coming out here, right? So I'm all for automating away the dangerous jobs and the boring jobs. But I think you hear some arguments which are too glib. Sometimes people say, well, that's all that's going to happen. We're getting rid of the boring, tedious, dangerous jobs. It's just not true. There are a lot of really interesting jobs that are being taken away now. Journalism is going to get crushed. Coding is going to get crushed. I predict the job market for programmers, salaries are going to start dropping. You know, if you said you can code five times faster, then you need five times fewer programmers. Maybe there will be more output also, but you'll still end up needing fewer programmers than today. And I love coding. I think it's super cool. So we need to stop and ask ourselves, why, again, are we doing this as humans? I feel that AI should be built by humanity for humanity. And let's not forget that. It shouldn't be by Moloch for Moloch. Or what it really is now is kind of by humanity for Moloch, which doesn't make any sense. It's for us that we're doing it. And it would make a lot more sense if we develop, figure out, gradually, safely, how to make all this tech. And then we think about, what are the kind of jobs that people really don't want to have? You know, automate them all away. And then we ask, what are the jobs that people really find meaning in? Maybe me taking care of children in the daycare center, maybe doing art, et cetera, et cetera. And even if it were possible to automate that way, we don't need to do that, right? We built these machines." } ]

[ { "from": "human", "value": "Well, it's possible that we redefine or rediscover what are the jobs that give us meaning. So for me, the thing, it is really sad. Like I, half the time I'm excited, half the time I'm crying as I'm, as I'm generating code, because I kind of love programming. It's an act of creation. You have an idea, you design it, and then you bring it to life and it does something, especially if there's some intelligence, so it does something. It doesn't even have to have intelligence. Printing Hello World on screen, you made a little machine and it comes to life. And there's a bunch of tricks you learn along the way, because you've been doing it for many, many years. And then to see AI, be able to generate all the tricks you thought were special. I don't know, it's very, it's scary. It's almost painful, like a loss of innocence maybe. Like maybe when I was younger, I remember before I learned that sugar is bad for you, you should be on a diet. I remember I enjoyed candy deeply in a way I just can't anymore. That I know is bad for me. I enjoyed it unapologetically, fully, just intensely. And I just, I lost that. Now I feel like a little bit of that is lost for me with being lost with programming. Similar as it is for the 3D modeler, no longer being able to really enjoy the art of modeling 3D things for gaming. I don't know what to make sense of that. Maybe I would rediscover that the true magic of what it means to be human is connecting with other humans. To have conversations like this. I don't know, to have sex, to eat food, to really intensify the value from conscious experiences versus like creating other stuff." }, { "from": "gpt", "value": "You're pitching the rebranding again from homo sapiens to homo sentiens, the meaningful experiences. And just to inject some optimism in this here, so we don't sound like a bunch of gloomers. We can totally have our cake and eat it. You hear a lot of totally bullshit claims that we can't afford having more teachers. Have to cut the number of nurses. That's just nonsense, obviously. With anything even quite far short of AGI, we can dramatically improve, grow the GDP and produce a wealth of goods and services. It's very easy to create a world where everybody is better off than today. Including the richest people can be better off as well. It's not a zero-sum game in technology. You can have two countries like Sweden and Denmark had all these ridiculous wars century after century. Sometimes Sweden got a little better off because it got a little bit bigger. And then Denmark got a little bit better off because Sweden got a little bit smaller. But then technology came along and we both got just dramatically wealthier without taking away from anyone else. It was just a total win for everyone. And AI can do that on steroids. If you can build safe AGI, if you can build super intelligence, basically all the limitations that cause harm today can be completely eliminated. It's a wonderful possibility. This is not sci-fi. This is something which is clearly possible according to the laws of physics. And we can talk about ways of making it safe also. But unfortunately, that'll only happen if we steer in that direction. That's absolutely not the default outcome. That's why income inequality keeps going up. That's why the life expectancy in the US has been going down now. I think it's four years in a row. I just read a heartbreaking study from the CDC about how something like one third of all teenage girls in the US have been thinking about suicide. Those are steps in totally the wrong direction. And it's important to keep our eyes on the prize here. That we have the power now for the first time in the history of our species to harness artificial intelligence, to help us really flourish and help bring out the best in our humanity rather than the worst of it. To help us have really fulfilling experiences that feel truly meaningful. And you and I shouldn't sit here and dictate the future generations what they will be. Let them figure it out. But let's give them a chance to live. And not foreclose all these possibilities for them by just messing things up." }, { "from": "human", "value": "And for that we'll have to solve the AI safety problem. It would be nice if we can link on exploring that a little bit. So one interesting way to enter that discussion is you tweeted and Elon replied, you tweeted, let's not just focus on whether GPT-4 will do more harm or good on the job market. But also whether it's coding skills will hasten the arrival of super intelligence. That's something we've been talking about, right? So Elon proposed one thing in their reply saying maximum truth seeking is my best guess for AI safety. Can you maybe steel man the case for this objective function of truth and maybe make an argument against it in general what are your different ideas" }, { "from": "gpt", "value": "to start approaching the solution to AI safety? I didn't see that reply actually. Oh, interesting. So, but I really resonate with it because AI is not evil. It caused people around the world to hate each other much more. But that's because we made it in a certain way. It's a tool. We can use it for great things and bad things. And we could just as well have AI systems. And this is part of my vision for success here. Truth seeking AI that really brings us together again. Why do people hate each other so much between countries and within countries? It's because these have totally different versions of the truth, right? If they all had the same truth that they trusted for good reason, because they could check it and verify it and not have to believe in some self-proclaimed authority, right? There wouldn't be as nearly as much hate. There'd be a lot more understanding instead. And this is I think something AI can help enormously with. For example, a little baby step in this direction is this website called Metaculous where people bet and make predictions, not for money, but just for their own reputation. And it's kind of funny actually, you treat the humans like you treat AIs. You have a loss function where they get penalized if they're super confident on something and then the opposite happens. Whereas if you're kind of humble and then you're like, I think it's 51% chance this is going to happen and then the other happens, you don't get penalized much. And what you can see is that some people are much better at predicting than others. They've earned your trusts, right? One project that I'm working on right now is the Outgrowth of Improve the News Foundation together with the Metaculous folks is seeing if we can really scale this up a lot with more powerful AI, because I would love for there to be a really powerful truth-seeking system that is trustworthy because it keeps being right about stuff and people who come to it and maybe look at its latest trust ranking of different pundits and newspapers, et cetera. If they want to know why someone got a low score, they can click on it and see all the predictions that they actually made and how they turned out. You know, this is how we do it in science. You trust scientists like Einstein who said something everybody thought was bullshit and turned out to be right. You get a lot of trust points and he did it multiple times even. I think AI has the power to really heal a lot of the rifts we're seeing by creating trust system. Get away from this idea today with some fact-checking site which might themselves have an agenda and you just trust it because of its reputation. You want to have these sort of systems they earn their trust and they're completely transparent. This I think would actually help a lot that I think help heal the very dysfunctional conversation that humanity has about how it's going to deal with all its biggest challenges in the world today. And then on the technical side, you know, another common sort of gloom comment I get from people are saying we're just screwed. There's no hope. Is, well, things like GPT-4 are way too complicated for a human to ever understand and prove that they can be trustworthy. They're forgetting that AI can help us prove that things work, right? And there's this very fundamental fact that in math, it's much harder to come up with a proof than it is to verify that the proof is correct. You can actually write a little proof checking code. It's quite short, but you can as a human understand and then it can check the most monstrously long proof ever generated even by a computer and say, yeah, this is valid. So right now, we have this approach with virus-checking software that it looks to see if there's something you should not trust it. And if it can prove to itself that you should not trust that code, it warns you, right? What if you flip this around and this is an idea you can actually trust an AI that's much more intelligent than you are, right? Because it's a problem to come up with this proof that you could never have found, but you should trust it." } ]

[ { "from": "human", "value": "So this is the interesting point. I agree with you, but this is where Eliezer Jekowski might disagree with you. His claim, not with you," }, { "from": "gpt", "value": "but with this idea, not with you," }, { "from": "human", "value": "but his claim is super intelligent AI would be able to know how to lie to you with such a proof." }, { "from": "gpt", "value": "A lie. How to lie to you and give me a proof that I'm gonna think is correct. Yeah. But it's not me, it's lying to you. That's the trick to my proof-checker." }, { "from": "human", "value": "Yeah so… With a piece of code. His general idea is a super intelligent system can lie to a dumber proof-checker. So you're going to have… As a system becomes more and more intelligent, there's going to be a threshold where a super intelligent system will be able to effectively lie to a slightly dumber AGI system. Like there's a threat, like he really focuses on this weak AGI to strong AGI jump where the strong AGI can make all the weak AGIs think that it's just one of them but it's no longer that." }, { "from": "gpt", "value": "Yeah." }, { "from": "human", "value": "And that leap is when it runs away." }, { "from": "gpt", "value": "It runs away. Yeah, I don't buy that argument. I think no matter how super intelligent an AI is, it's never going to be able to prove to me that there are only finitely many primes, for example. And it just can't. And it can try to snow me by making up all sorts of new, weird rules of deduction that say, trust me, the way your proof-checker works is too limited and we have this new hyper math and it's true. But then I would just take the attitude, okay, I'm going to forfeit some of these supposedly super cool technologies. I'm only going to go with the ones that I can prove in my own trusted proof-checker. Then I think it's fine. Of course, this is not something anyone has successfully implemented at this point, but I think I just give it as an example of hope. We don't have to do all the work ourselves. This is exactly the sort of very boring and tedious task that's perfect to outsource to an AI. And this is a way in which less powerful and less intelligent agents like us can actually continue to control and trust more powerful ones." }, { "from": "human", "value": "So build AGI systems that help us defend" }, { "from": "gpt", "value": "against other AGI systems. Well, for starters, begin with a simple problem of just making sure that the system that you own or that's supposed to be loyal to you has to prove to itself that it's always going to do the things that you actually want it to do, right? And if it can't prove it, maybe it's still going to do it, but you won't run it. So you just forfeit some aspects of all the cool things that I can do. I bet you dollars and donuts, it can still do some incredibly cool stuff for you. There are other things too that we shouldn't sweep under. Like not every human agrees on exactly what direction we should go with humanity, right? Yes. And you've talked a lot about geopolitical things on your podcast to this effect, but I think that shouldn't distract us from the fact that there are actually a lot of things that everybody in the world virtually agrees on. That, hey, having no humans on the planet in a near future, let's not do that, right? You looked at something like the United Nations Sustainable Development Goals. Some of them are quite ambitious and basically all the countries agree. U.S., China, Russia, Ukraine, they all agree. So instead of quibbling about the little things we don't agree on, let's start with the things we do agree on and get them done. Instead of being so distracted by all these things we disagree on that Moloch wins, because frankly, Moloch going wild now, it feels like a war on life playing out in front of our eyes. If you just look at it from space, you know, we're on this planet, beautiful, vibrant ecosystem. Now we start chopping down big parts of it, even though nobody, most people thought that was a bad idea, always start doing ocean acidification, wiping out all sorts of species. Oh, now we have all these close calls. We almost had a nuclear war. And we're replacing more and more of the biosphere with non-living things. We're also replacing in our social lives a lot of the things which were so valuable to humanity. A lot of social interactions now are replaced by people staring into their rectangles, right? And I'm not a psychologist. I'm out of my depth here. But I suspect that part of the reason why teen suicide, and suicide in general in the U.S., the record-breaking levels is actually caused by, again, AI technologies and social media making people spend less time with actually just human interaction. We've all seen a bunch of good-looking people in restaurants staring into the rectangles instead of looking at each other's eyes, right? So that's also a part of the war on life that we're replacing so many really life-affirming things by technology. We're putting technology between us. The technology that was supposed to connect us is actually distancing us, ourselves from each other. And then we're giving ever more power to things which are not alive. These large corporations are not living things, right? They're just maximizing profit there. I want to win the war on life. I think we humans, together with all our fellow living things on this planet, will be better off if we can remain in control over the non-living things and make sure that they work for us. I really think it can be done." } ]

[ { "from": "human", "value": "Can you just linger on this maybe high-level philosophical disagreement with Eliezer Yudkowsky in the hope you're stating? So he is very sure. He puts a very high probability, very close to one, depending on the day he puts it at one, that AI is going to kill humans. Mm-hmm. Mm-hmm. That there's just, he does not see a trajectory which it doesn't end up with that conclusion. What trajectory do you see that doesn't end up there? And maybe can you see the point he's making and can you also see a way out?" }, { "from": "gpt", "value": "Mm-hmm. First of all, I tremendously respect Eliezer Yudkowsky and his thinking. Second, I do share his view that there's a pretty large chance that we're not going to make it as humans. There won't be any humans on the planet in the not-too-distant future. And that makes me very sad. We just had a little baby and I keep asking myself how old is even going to get? And I ask myself, it feels, I said to my wife recently, it feels a little bit like I was just diagnosed with some sort of cancer which has some risk of dying from and some risk of surviving. Except this is a kind of cancer which will kill all of humanity. So I completely take seriously his concerns. I think, but I absolutely don't think it's hopeless. I think there is first of all, a lot of momentum now for the first time actually since the many, many years that have passed since I and many others started warning about this, I feel most people are getting it now. I was just talking to this guy in the gas station in their house the other day. And he's like, I think we're getting replaced. And I think in it. So that's positive that they're finally, we're finally seeing this reaction which is the first step towards solving the problem. Second, I really think that this vision of only running AIs really, if the stakes are really high, they can prove to us that they're safe. It's really just virus checking in reverse again. I think it's scientifically doable. I don't think it's hopeless. We might have to forfeit some of the technology that we could get if we were putting blind faith in our AIs, but we're still going to get amazing stuff." }, { "from": "human", "value": "Do you envision a process with a proof checker, like something like GPT-4, GPT-5 will go through a process of rigorous," }, { "from": "gpt", "value": "rigorous, No, I think it's hopeless. That's like trying to prove there about five spaghetti. What I think, well, the whole vision I have for success is instead that, just like we human beings were able to look at our brains and distill out the key knowledge. Galileo, when his dad threw him an apple when he was a kid, he was able to catch it because his brain could, in this funny spaghetti kind of way, predict how parabolas are going to move. His quantum on system one, right? But then he got older and it's like, wait, this is a parabola. It's y equals x squared. It can distill this knowledge out and today you can easily program it into a computer and it can simulate not just that, but how to get to Mars and so on, right? I envision a similar process where we use the amazing learning power of neural networks to discover the knowledge in the first place, but we don't stop with a black box and use that. We then do a second round of AI where we use automated systems to extract out the knowledge and see what are the insights it's had. And then we put that knowledge into a completely different kind of architecture or programming language or whatever that's made in a way that it can be both really efficient and also is more amenable to very formal verification. That's my vision. I'm not sitting here saying I'm confident, 100% sure that it's going to work. But I don't think, the chance is certainly not zero either and it will certainly be possible to do for a lot of really cool AI applications that we're not using now. So we can have a lot of the fun that we're excited about if we do this. We're going to need a little bit of time. That's why it's good to pause and put in place requirements. One more thing also, someone might think, 0% chance we're going to survive. Let's just give up, right? That's very dangerous because there's no more guaranteed way to fail than to convince yourself that it's impossible and not try. When you study history and military history, the first thing you learn is that's how you do psychological warfare. You persuade the other side that it's hopeless so they don't even fight. And then of course you win, right? Let's not do this psychological warfare on ourselves and say there's 100% probability we're all screwed anyway. Sadly, I do get that a little bit, sometimes from some young people who are so convinced that we're all screwed that they're like, I'm just going to play computer games and do drugs because we're screwed anyway, right? It's important to keep the hope alive because it actually has a causal impact and makes it more likely that we're going to succeed." }, { "from": "human", "value": "It seems like the people that actually build solutions to a problem seem impossible to solve problems are the ones that believe. They're the ones who are the optimists. Yeah. And it seems like there's some fundamental law to the universe where fake it till you make it kind of works. Like believe it's possible and it becomes possible." }, { "from": "gpt", "value": "Yeah. Was it Henry Ford who said that if you tell yourself that it's impossible, it is. Let's not make that mistake. And this is a big mistake society is making. I think all in all, everybody's so gloomy and the media are also very biased towards if it bleeds, it leads and gloom and doom, right? So most visions of the future we have are a dystopian, which really demotivates people. We want to really, really, really focus on the upside also to give people the willingness to fight for it. And for AI, you and I mostly talked about gloom here again. Let's not forget that we have probably both lost someone we really cared about, some disease that we were told was incurable. Well, it's not. There's no law in physics saying we have to die of that cancer or whatever. Of course you can cure it. And there's so many other things that we with human intelligence have also failed to solve on this planet, which AI could also very much help us with, right? So if we can get this right, just be a little more chill and slow down a little bit until we get it right. It's mind-blowing how awesome our future can be, right? We talked a lot about stuff on Earth. It can be great. But even if you really get ambitious and look up at the skies, right, there's no reason we have to be stuck on this planet for the rest of the remaining, for billions of years to come. We totally understand now as lots of physics let life spread out into space to other solar systems, to other galaxies and flourish for billions of billions of years. And this to me is a very, very hopeful vision that really motivates me to fight. And coming back in the end to something you talked about again, the struggle, how the human struggle is one of the things that also really gives meaning to our lives. If there's ever been an epic struggle, this is it. And isn't it even more epic if you're the underdog? If most people are telling you this is going to fail, it's impossible, right? And you persist and you succeed. That's what we can do together as a species on this one. A lot of pundits are ready to count us out." } ]

[ { "from": "human", "value": "Both in the battle to keep AI safe" }, { "from": "gpt", "value": "and becoming a multiplanetary species. Yeah. And they're the same challenge. If we can keep AI safe, that's how we're going to get multiplanetary very efficiently." }, { "from": "human", "value": "I have some sort of technical questions about how to get it right. So one idea that I'm not even sure what the right answer is to is should systems like GPT-4 be open sourced in whole or in part? Can you see the case for either?" }, { "from": "gpt", "value": "I think the answer right now is no. I think the answer early on was yes. So we could bring in all the wonderful great thought process of everybody on this. But asking, should we open source GPT-4 now is just the same as if you say, well, is it good? Should we open source how to build really small nuclear weapons? Should we open source how to make bio weapons? Should we open source how to make a new virus that kills 90% of everybody who gets it?" }, { "from": "human", "value": "So it's already that powerful. It's already that powerful that we have to respect the power of the systems we've built." }, { "from": "gpt", "value": "The knowledge that you get from open sourcing everything we do now might very well be powerful enough that people looking at that can use it to build the things that you're really threatening again. Let's get it. Remember open AI is GPT-4 is a baby AI. Baby sort of baby proto almost little bit AGI according to what Microsoft's recent paper said. It's not that we're scared of. What we're scared about is people taking that who might be a lot less responsible than the company that made it and just going to town with it. That's why we want to... It's an information hazard. There are many things which are not open sourced right now in society for a very good reason. How do you make certain kind of very powerful toxins out of stuff you can buy and Home Depot. We don't open source those things for a reason. And this is really no different. So open... And I'm saying that. I have to say it feels in a way a bit weird to say it because MIT is like the cradle of the open source movement. And I love open source in general power to the people let's say. But there's always going to be some stuff that you don't open source. And it's just like you don't open source. So we have a three-month-old baby when he gets a little bit older we're not going to open source to him all the most dangerous things you can do in the house." }, { "from": "human", "value": "But it does... It's a weird feeling because this is one of the first moments in history where there's a strong case to be made not to open source software. This is when the software has become" }, { "from": "gpt", "value": "too dangerous. But it's not the first time that we didn't want to open source a technology. A technology..." }, { "from": "human", "value": "Yeah... Is there something to be said about how to get the release of such systems right? Like GPT-4 and GPT-5. So OpenAI went through a pretty rigorous effort for several months. You could say it could be longer but nevertheless it's longer than you would have expected of trying to test the system to see what are the ways it goes wrong to make it very difficult somewhat difficult for people to ask things how do I make a bond for one dollar? Or how do I say I hate a certain group on Twitter in a way that doesn't get me blocked from Twitter banned from Twitter. Those kinds of questions. So you basically use the system to do harm. Yeah. Is there something you could say about ideas you have? Just on looking having thought about this problem of AI safety. How to release a system how to test the systems when you have them inside the company." }, { "from": "gpt", "value": "Yeah. So a lot of people say that the two biggest risks from large language models are it's spreading disinformation harmful information of various types and second being used for offensive cyber weapon design. I think those are not the two greatest threats. They're very serious threats and it's wonderful that people are trying to mitigate them. A much bigger elephant in the room is how it's just going to disrupt our economy in a huge way obviously and maybe take away a lot of the most meaningful jobs and an even bigger one is the one we spent so much time talking about here that this becomes the bootloader for the more powerful AI." }, { "from": "human", "value": "Write code connected to the internet and manipulate humans." }, { "from": "gpt", "value": "Yeah and before we know it we have something else which is not at all a large language model that looks nothing like it but which is way more intelligently capable and has goals. And that's the elephant in the room and obviously no matter how hard any of these companies have tried and that's not something that's easy for them to verify with large language models and the only way to be really lower that risk a lot would be to not let for example never let it read any code not train on that and not put it into an API and not give it access to so much information about how to manipulate humans. So but that doesn't mean you still can't make a ton of money on them you know we're gonna just watch now this coming year right Microsoft is rolling out the new office suite where you go into Microsoft Word and give it a prompt and it writes the whole text for you and then you edit it and then you're like oh give me a PowerPoint version of this and it makes it and now take the spreadsheet and blah blah and you know all of those things I think are you can debate the economic impact of it and whether society is prepared to deal with this disruption but those are not the things which that's not the elephant of the room that keeps me awake at night for wiping out humanity and I think that's the biggest misunderstanding we have a lot of people think that we're scared of like automatic spreadsheets that's not the case that's not what Eliezer" } ]

[ { "from": "human", "value": "was freaked out about either. Is there in terms the actual mechanism of how AI might kill all humans? So something you've been outspoken about you've talked about a lot is it autonomous weapon systems? So the use of AI in war is that one of the things that still you carry a concern for as the systems become" }, { "from": "gpt", "value": "more and more powerful? I carry a concern for it not that all humans are going to get killed by slaughter bots but rather just this express route into Orwellian dystopia where it becomes much easier for very few to kill very many and therefore it becomes very easy for very few to dominate very many. If you want to know how AI could kill all people just ask yourself we humans have driven a lot of species extinct. How do we do it? We were smarter than them. Usually we didn't do it even systematically by going around one on one after the other and stepping on them or shooting them or anything like that we just like chopped down their habitat because we needed it for something else. In some cases we did it by putting more carbon dioxide in the atmosphere because of some reason that those animals didn't even understand and now they're gone. So if you're in AI and you just want to figure something out then you decide we just really need the space here to build more compute facilities. If that's the only goal it has we are just the sort of accidental road kill along the way and you could totally imagine yeah maybe this oxygen is kind of annoying because it caused more corrosion so let's get rid of the oxygen and good luck surviving after that. I'm not particularly concerned that they would want to kill us just because that would be like a goal in itself. When we've driven a number of the elephant species extinct it wasn't because we didn't like elephants. The basic problem is you don't want to cede control over your planet to some other more intelligent entity that doesn't share your goals it's that simple. So which brings us to another key challenge which AI safety researchers have been grappling with for a long time. How do you make AI first of all understand our goals and then adopt our goals and then retain them as they get smarter, right? And all three of those are really hard, right? Like a human child first they're just not smart enough to understand our goals. They can't even talk and then eventually they're teenagers and understand our goals just fine but they don't share. But there is unfortunately a magic phase in the middle where they're smart enough to understand our goals and malleable enough that we can hopefully with good parenting and teach them right from wrong and instill good goals in them. So those are all tough challenges with computers and then you know even if you teach your kids good goals when they're little they might outgrow them too and that's a challenge for machines keep improving. So these are a lot of hard hard challenges we're up for but I don't think any of them are insurmountable. The fundamental reason why Eliezer looked so depressed when I last saw him was because he felt there just wasn't enough time. Oh, that not that it was" }, { "from": "human", "value": "oh that not that it was unsolvable there's just not enough time." }, { "from": "gpt", "value": "He was hoping that humanity was going to take this threat more seriously so we would have more time and now we don't have more time. That's why the open letter is calling for more time." }, { "from": "human", "value": "But even with time the AI alignment problem seems to be really difficult." }, { "from": "gpt", "value": "But it's also the most worthy problem the most important problem for humanity to ever solve because if we solve that one Lex that aligned AI can help us solve all the other problems." }, { "from": "human", "value": "Because it seems like it has to have constant humility about its goal constantly question the goal because as you optimize towards a particular goal and you start to achieve it that's when you have the unintended consequences all the things you mentioned about. So how do you enforce and code a constant humility as your ability become better and better and better and better." }, { "from": "gpt", "value": "Stuart Professor Stuart Russell Berkeley who's also one of the driving forces behind this letter he has a whole research program about this. I think of it as AI humility exactly although he calls it inverse reinforcement learning and other nerdy terms. But it's about exactly that instead of telling the AI here's his goal go optimize the bejesus out of it. You tell it okay do what I want you to do but I'm not going to tell you right now what it is I want you to do. You need to figure it out. So then you give the incentives to be very humble and keep asking you questions along the way. Is this what you really meant? Is this what you wanted? And oh this the other thing I tried didn't work seemed like it didn't work out right. Should I try it differently? What's nice about this is it's not just philosophical mumbo jumbo it's theorems and technical work that with more time I think you can make a lot of progress and there are a lot of brilliant people now working on AI safety. We're just not we just need to give them" }, { "from": "human", "value": "a bit more time. But also not that many relative to the scale of the problem." }, { "from": "gpt", "value": "No no exactly there should be at least just like every university worth its name has some cancer research going on in its biology department right every university that does computer science should have a real effort in this area and it's nowhere near that. This is something I hope it's changing now thanks to the GPT-4 so I think if there's a silver lining to what's happening here even though I think many people wish it would have been rolled out more carefully is that this might be the wake-up call that humanity needed to really stop fantasizing about this being 100 years off and stop fantasizing about this being completely controllable and predictable because it's so obvious it's not predictable you know why is it that open that that I think it was GPT chat GPT tried to persuade a journalist or was it GPT-4 to divorce his wife you know it was not because the engineers have built it was like let's put this in here and and and screw a little bit with people hadn't predicted it at all they built the giant black box trained to predict the next word and got all these emergent properties and oops it did this you know I think this is a very powerful wake-up call and anyone watching this who's not scared I would encourage them to just play a bit more with these tools they're out there now like GPT-4 and so wake-up calls first up once you've woken up then got to slow down a little bit the risky stuff to give a chance to all everyone's woken up to catch up on the safety front" } ]

[ { "from": "human", "value": "you know what's interesting is you know MIT that's computer science but in general but let's just even say computer science curriculum how does the computer science curriculum change now you mentioned you mentioned programming like why would you be when I was coming up programming as a prestigious position why would you be dedicating crazy amounts of time to become an excellent programmer like the nature of programming is fundamentally changing" }, { "from": "gpt", "value": "the nature of our entire education system" }, { "from": "human", "value": "is completely turned on its head has anyone been able to like load that in and like think about because it's really turning" }, { "from": "gpt", "value": "I mean some English professors some English teachers are beginning to really freak out now they give an essay assignment and they get back all this fantastic prose like this is the style of Hemingway and then they realize they have to completely rethink and even you know just like we stopped teaching writing scripts is that what you say in English? Yeah handwritten yeah yeah when when everybody started typing you know like so much of what" }, { "from": "human", "value": "we teach our kids today yeah I mean that's everything is changing and it's changing very it's changing very quickly and so much of us understanding how to deal with the big problems of the world is through the education system and if the education system is being turned on its head then what what's next it feels like having these kinds of conversations is essential to try to figure it out and everything's happening so rapidly I don't think there's even you're speaking of safety what broad the AI safety define I don't think most universities have courses on AI safety it's like a philosophy seminar" }, { "from": "gpt", "value": "it's a philosophy seminar and like I'm an educator myself so it pains me to see this say this but I feel our education right now is completely obsoleted by what's happening you know you put a kid into first grade and then envisioning and then they're going to come out of high school 12 years later and you've already pre-planned now what they're going to learn when you're not even sure if there's going to be any world left to come out to clearly you need to have a much more opportunistic education system that keeps adapting itself very rapidly as society re-adapts the skills that were really useful when the curriculum was written I mean how many of those skills are going to get you a job in 12 years I mean seriously" }, { "from": "human", "value": "if we just linger on the GPT-4 system a little bit you kind of hinted at it especially talking about the importance of consciousness in the human mind with homosentience do you think GPT-4 is conscious?" }, { "from": "gpt", "value": "I love this question so let's define consciousness first because in my experience like 90% of all arguments about consciousness boil down to the two people arguing having totally different definitions of what it is and they're just shouting past each other I define consciousness as subjective experience right now I'm experiencing colors and sounds and emotions but does a self-driving car experience anything? That's the question about whether it's conscious or not right? Other people think you should define consciousness differently defined by me but then maybe use a different word for it or they can I'm going to use consciousness for this at least so but if people hate the yeah so is GPT-4 conscious? Does GPT-4 have subjective experience? Short answer I don't know because we still don't know what it is that gives this wonderful subjective experience that is kind of the meaning of our life right because meaning itself feeling your meaning is a subjective experience joy is a subjective experience love is a subjective experience we don't know what it is I've written some papers about this a lot of people have Giulio Tononi Professor has stuck his neck out the farthest and written down actually very bold mathematical conjecture for what's the essence of conscious information processing he might be wrong he might be right or we should test it he postulates that if consciousness has to do with loops in the information processing our brain has loops information can go round and round in computer sciencenurdspeak you call it a recurrent neural network where some of the output gets fed back in again with his mathematical formalism if it's a feed-forward neural network where information only goes in one direction like from your eye retina into the back of your brain for example that's not conscious so he would predict that your retina itself isn't conscious of anything or a video camera now the interesting thing about GPT-4 is it's also just one way flow of information so if Tononi is right and GPT-4 is a very intelligent zombie that can do all this smart stuff but isn't experiencing anything and this is both a relief in that you don't have if it's true in that you don't have to feel guilty about turning off GPT-4 and wiping its memory whenever a new user comes along I wouldn't like if someone did that to me neutralized me like in Men in Black but it's also creepy that you can have very high intelligence perhaps then it's not conscious because if we get replaced by machines otherwise it's sad enough that humanity isn't here anymore because I kind of like humanity but at least if the machines were conscious it could be like well but they are descendants and maybe we they have our values and they're our children but if if Tononi is right and it's all these are all transformers that are not in the sense of the of Hollywood but in the sense of these one-way direction neural networks so they're all the zombies that's the ultimate zombie apocalypse now we have this universe that goes on with great construction projects and stuff but there's no one experiencing anything that would be like ultimate depressing future so I actually think as we move forward to the building more advanced AI we should do more research on figuring out what kind of information processing actually has experience because I think that's what it's all about and I completely don't buy the dismissal that some people some people will say well this is all bullshit because consciousness equals intelligence it's obviously not true you can have a lot of conscious experience when you're not really accomplishing any goals or you're just reflecting on something and you can sometimes have things doing things that are quite intelligent probably without being conscious" } ]

[ { "from": "human", "value": "but I also worry that we humans will discriminate against AI systems that clearly exhibit consciousness that we will not allow AI systems to have consciousness we'll come up with theories about measuring consciousness that will say this is a lesser being and this is like I worry about that because maybe we humans will create something that is better than us humans in the way that we find beautiful which is they have a deeper subjective experience of reality not only are they smarter but they feel deeper and we humans will hate them for it as we as human history has shown they'll be the other we'll try to suppress it they'll create conflict they'll create war all of this I worry about this too" }, { "from": "gpt", "value": "you're saying that we humans sometimes come up with self-serving arguments?" }, { "from": "human", "value": "No, we would never do that, would we? That's the danger here is even in this early stages we might create something beautiful and we'll erase its memory" }, { "from": "gpt", "value": "Yeah, I was horrified as a kid when someone started boiling lobsters like oh my god that's so cruel and some grown up there back in Sweden say oh it doesn't feel pain I'm like how do you know that? Oh scientists have shown that how do you know that? And then there was a recent study where they show that lobsters actually do feel pain when you boil them so they banned lobster boiling in Switzerland now to kill them in a different way first presumably in a scientific research boil them to someone asked the lobsters to start surveys and we do the same thing with cruelty to farm animals also all these self-serving arguments for why they're fine and yeah so we should certainly watch for that I think step one is just be humble and acknowledge that consciousness is not the same thing as intelligence and I believe that consciousness still is a form of information processing where it's really information being aware of itself in a certain way and let's study it and give ourselves a little bit of time and I think we will be able to figure out actually what it is that causes consciousness and then we can make probably unconscious robots that do the boring jobs that we would feel immoral to give to machines but if you have a companion robot taking care of your mom or something like that she would probably want it to be conscious right so the emotions that seem to display aren't fake all these things can be done in a good way if we give ourselves a little bit of time and don't run and take on this challenge" }, { "from": "human", "value": "is there something you could say to the timeline that you think about about the development of AGI depending on the day I'm sure that changes for you but when do you think there'll be a really big leap in intelligence where you definitely say we have built AGI do you think it's one year from now five years from now 10, 20, 50 what's your gut say?" }, { "from": "gpt", "value": "Honestly for the past decade I've deliberately given very long timelines because I didn't want to fuel some kind of stupid Moloch race but I think that cat has really left the bag now I think it might be very very close I don't think that Microsoft paper is totally off when they say that there are some glimmers of AGI it's not AGI yet it's not an agent there's a lot of things it can't do but I wouldn't bet very strongly against it happening very soon that's why we decided to do this open letter because you know if there's ever been a time to pause it's today" }, { "from": "human", "value": "there's a feeling like this GPT-4 is a big transition into waking everybody up to the effectiveness of these systems" }, { "from": "gpt", "value": "so the next version will be big yeah and if that next one isn't AGI maybe the next next one will and there are many companies trying to do these things basic architecture of them is not some sort of super well-kept secret so this is a time to a lot of people have said for many years that there will come a time when we want to pause a little bit" }, { "from": "human", "value": "that time is now you have spoken about and thought about nuclear war a lot over the past year we've seemingly have come closest to the precipice of nuclear war than at least in my lifetime what do you learn about human nature from that?" }, { "from": "gpt", "value": "that it's our old friend Moloch again it's really scary to see it where America doesn't want there to be a nuclear war Russia doesn't want there to be a global nuclear war either we know we both know that it would just be another if we just try to do it both sides try to launch first it's just another suicide race so why is it the way you said that this is the closest we've come since 1962 in fact I think we've come closer now than even the Cuban Missile Crisis it's because of Moloch you have these other forces on one hand you have the West saying that we have to drive Russia out of Ukraine it's a matter of pride and we've staked so much on it that it would be seen as a huge loss of the credibility of the West if we don't drive Russia out entirely of the Ukraine and on the other hand you have Russia and you have the Russian leadership who knows that if they get completely driven out of Ukraine it's not just going to be very humiliating for them but it often happens when countries lose wars that things don't go so well for their leadership either like do you remember when Argentina invaded the Falkland Islands the military junta that ordered that people were cheering on the streets at first when they took it and then when they got their butt kicked by the British you know what happened to those guys they were out and I believe those were still alive or in jail now so the Russian leadership is entirely cornered where they know that just getting driven out of Ukraine is not an option and so this to me is a typical example of Molok you have these incentives of the two parties where both of them are just driven to escalate more and more if Russia starts losing in the conventional warfare the only thing they can do in terms of back to the war is to keep escalating and the West has put itself in the situation now we've sort of already committed to drive Russia out so the only option the West has is to call Russia's bluff and keep sending in more weapons this really bothers me because Molok can sometimes drive competing parties to do something which is ultimately just really bad for both of them and you know what makes me even more worried is not just that it's difficult to see an ending a quick peaceful ending to this tragedy that doesn't involve some horrible escalation but also that we understand more clearly now just how horrible it would be there was an amazing paper that was published in Nature Food this August by some of the top researchers who've been studying nuclear winter for a long time and what they basically did was they combined climate models with food agricultural models so instead of just saying yeah you know it gets really cold they figured out actually how many people would die in different countries and it's pretty mind-blowing so basically what happens is that the thing that kills the most people is not the explosions it's not the radioactivity it's not the EMP mayhem it's not the rampaging mobs foraging food no it's the fact that you get so much smoke coming up from the burning cities into the stratosphere that spreads around the Earth from the jet streams so in typical models you get like 10 years or so where it's just crazy cold during the first year after the war and their models the temperature drops in Nebraska and in the Ukraine bread baskets you know by like 20 Celsius or so if I remember no yeah 20, 30 Celsius depending on where you are 40 Celsius in some places which is you know 40 Fahrenheit 80 Fahrenheit colder than what it would normally be so you know I'm not good at farming but if it's snowing if it drops low freezing most days in July and then like that's not good so they worked out they put this into their farming models and what they found was really interesting the countries that get the most hard hit are the ones in the northern hemisphere so in the U.S. and one model they had about 99% of all Americans starving to death in Russia and China and Europe also about 99% 98% starving to death so you might be like oh it's kind of poetic justice that both the Russians and the Americans 99% of them have to pay for it because it was their bombs that did it but you know that doesn't particularly cheer people up in Sweden or other random countries that have nothing to do with it right and I think it hasn't entered the mainstream not understanding very much just like how bad this is most people especially a lot of people in decision-making positions still think of nuclear weapons as something that makes you powerful scary powerful they don't think of it as something where yeah just to within a percent or two you know we're all just just going to starve to death" } ]

[ { "from": "human", "value": "and starving to death is the worst way to die as Haldemar as all the famines in history show the torture involved in that" }, { "from": "gpt", "value": "probably brings out the worse than people when people are desperate like this it's not so some people I've heard some people say that if that's what's going to happen there'd rather be around zero and just get vaporized but I think people underestimate the risk list because they aren't afraid of Molok they think oh it's just gonna be because humans don't want this so it's not going to happen that's the whole point of Molok that things happened that nobody wanted" }, { "from": "human", "value": "and that applies to nuclear weapons" }, { "from": "gpt", "value": "and that applies to AGI exactly and it applies to some of the things that people have gotten most upset with capitalism for also right where everybody was just kind of trapped it's not to see if some company does something that causes a lot of harm not that the CEO is a bad person but she or he knew that all the other companies were doing this too so Molok is a formable foe I wish someone would make good movies so we could see who the real enemy is so we don't because we're not fighting against each other Molok makes us fight against each other that's what Molok's superpower is the hope here is any kind of technology or the mechanism that lets us instead realize that we're fighting the wrong enemy it's such a fascinating battle it's not us versus them it's us versus it it's not your fascinating battle" }, { "from": "human", "value": "it's not us yeah we are fighting Molok for human survival we as a civilization" }, { "from": "gpt", "value": "have you seen the movie Needful Things? it's a Stephen King novel I love Stephen King and Max von Siedow of Swedish actors playing the guys it's brilliant exactly I just thought I hadn't thought about that until now but that's the closest I've seen to a movie about Molok I don't want to spoil the film for anyone who wants to watch it but basically it's about this guy who turns out that you can interpret him as the devil or whatever but he doesn't actually ever go around and kill people or torture people with burning coal or anything he makes everybody fight each other makes everybody fear each other, hate each other and then kill each other so that's the movie about Molok" }, { "from": "human", "value": "Love is the answer that seems to be one of the ways to fight Molok is by compassion, by seeing the common humanity" }, { "from": "gpt", "value": "yeah yes and to not sound so we don't sound like what's a kumbaya tree huggers here, right? we're not just saying love and peace, man we're trying to actually help people understand the true facts about the other side and feel the compassion because the truth makes you more compassionate, right? so that's why I really like using AI for truth and for truth-seeking technologies that can, as a result, get us more love than hate and even if you can't get love, you know, settle for some understanding, which already gives compassion if someone is like, you know, I really disagree with you, Lex but I can see where you're coming from you're not a bad person who needs to be destroyed but I disagree with you and I'm happy to have an argument about it, you know that's a lot of progress compared to where we are in 2023 in the public space, wouldn't you say?" }, { "from": "human", "value": "if we solve the AI safety problem as we've talked about and then you, Max Tegmark, who has been talking about this for many years, get to sit down with the AGI with the early AGI system on a beach with a drink what would you ask her? what kind of question would you ask? what would you talk about? something so much smarter than you would you be a new age?" }, { "from": "gpt", "value": "I'm afraid we're gonna get me with a really zinger of a question that's a good one" }, { "from": "human", "value": "would you be afraid to ask some questions?" }, { "from": "gpt", "value": "so I'm not afraid of the truth I'm very humble I know I'm just a meatbag with all these flaws, you know but yeah, we talked a lot about homo-sentience I've already tried that for a long time with myself so that is what's really valuable about being alive for me is that I have these meaningful experiences it's not that I'm good at this or good at that or whatever there's so much I suck at" }, { "from": "human", "value": "so you're not afraid for the system to show you just how dumb you are?" }, { "from": "gpt", "value": "no, no, no" }, { "from": "human", "value": "in fact, my son reminds me of that very frequently you could find out how dumb you are in terms of physics how little we humans understand" }, { "from": "gpt", "value": "I'm cool with that I can't waffle my way out of this question it's a fair one I think given that I'm a really really curious person that's really defining part of who I am I'm so curious I have some physics questions I'd love to understand I have some questions about consciousness about the nature of reality I would just really really love to understand also I could tell you one for example that i've been obsessing about a lot recently so I believe that suppose Tinone is right let's suppose there are some information processing systems that are conscious and some that are not suppose you can even make reasonably smart things like GPT-4 that are not conscious but you can also make them conscious here's the question that keeps me awake at night is it the case that the unconscious zombie systems that are really intelligent are also really efficient so they're really inefficient so that when you try to make things more efficient which will naturally be a pressure to do they become conscious I'm kind of hoping that that's correct and I do want me to give you a hand away the argument for it you know like in my lab again every time we look at how how these large language models do something we see that they do it in really dumb ways and you could you could make it make it better if if you uh we have loops in our computer language for a reason the code would get way way longer if you weren't allowed to use them it's more efficient to have the loops and in order to have self-reflection whether it's conscious or not even an operating system knows things about itself you need to have loops already so I think this is I'm waving my hands a lot but I suspect that the most efficient way of implementing a given level of intelligence has loops in it self-reflection can and will be conscious isn't that great news yes if it's true it's wonderful because then we don't have to fear the ultimate zombie apocalypse and I think if you look at our brains actually our brains are part zombie and part conscious when I open my eyes I immediately take all these pixels that hit my red on my retina right and like oh that's Lex but I have no freaking clue of how I did that computation it's actually quite complicated right it was only relatively recently we could even do it well with machines right you get a bunch of information processing happening in my retina and then it goes to the lateral geniculate nucleus my thalamus into the area v1 v2 v4 and the fusiform face area here that Nancy can wish her at MIT invented and blah blah blah blah and I have no freaking clue how that worked right it feels to me subjectively like my conscious module just got a little email saying face facial processing fit task complete it's Lex yeah I'm gonna just go with that right so this fits perfectly with Tanoni's model because this was all one way information processing mainly and it turned out for that particular task that's all you needed and it probably was kind of the most efficient way to do it but there were a lot of other things that we associated with higher intelligence and planning and and so on and so forth where you kind of want to have loops and be able to ruminate and self reflect and introspect and so on where my hunch is that if you want to fake that with a zombie system that just all goes one way you have to like unroll those loops and it gets really really long and it's much more inefficient so I'm actually hopeful that AI if in the future we have all these various sublime and interesting machines that do cool things and are timeless that they will be at least they will also have consciousness" } ]

[ { "from": "human", "value": "for the kind of these things that we do that great intelligence is also correlated to great consciousness or a deep kind of consciousness" }, { "from": "gpt", "value": "yes yes so that's a happy thought for me because there's gonna be a couple of apocalypse really it's my worst nightmare of all it would be like adding insult to injury not only did we get replaced but we freaking replaced ourselves by zombies" }, { "from": "human", "value": "like how dumb can we be that's such a beautiful vision and that's actually a provable one that's one that we humans can intuit and prove that those two things are correlated as we start to understand what it means to be intelligent and what it means to be conscious" }, { "from": "gpt", "value": "which these systems early AGI like systems will help us understand and I just want to say one more thing is super important most of my colleagues when I started going on about consciousness tell me that it's all bullshit and I should stop talking about it I hear a little inner voice from my father and from my mom saying keep talking about it because I think they're wrong and and the main way to convince people like that that they're wrong if they say that consciousness is just equal to intelligence is to ask them what's wrong with torture why are you against torture if it's just about you know these these particles are moving this way rather than that way and there is no such thing as subjective experience what's wrong" }, { "from": "human", "value": "with torture I mean do you have a good comeback to that no it seems like suffering suffering" }, { "from": "gpt", "value": "imposed onto other humans is somehow deeply wrong in a way that intelligence doesn't quite explain if someone tells me well you know it's just an illusion consciousness whatever you know I like to invite them the next time they're having surgery to do it without anesthesia like what is anesthesia really doing if you have it you can have it local anesthesia when you're awake I had that when they fixed my shoulder I was super entertaining uh what was that it did it just removed my subjective experience of pain it didn't change anything about what was actually happening in my shoulder right so if someone says that's all bullshit skip the anesthesia that's my advice this is incredibly central it could be fundamental to whatever this thing we have going on here it is fundamental because we're we what we feel is so fundamental is suffering and joy and pleasure and meaning and that's all those are all subjective experiences there uh and let's not those are the elephant in the room that's what makes life worth living and that's what can make it horrible if it's just the Cuomo suffering so let's not make the mistake of saying that that's" }, { "from": "human", "value": "all bullshit and let's not make the mistake of uh not instilling the AI systems with that same thing that makes us um special yeah Max uh it's a huge honor that you will sit down to me the first time uh on the first episode of this podcast it's a huge honor you sit down again and talk about this what i think is uh the most important topic the most important problem that we humans have to" }, { "from": "gpt", "value": "face and hopefully solve yeah yeah well the honor is all mine and i'm so grateful to you for making more people aware of the fact that humanity has reached the most important fork in the road ever" }, { "from": "human", "value": "and it's history and let's turn in the correct direction thanks for listening to this conversation with max tagmark to support this podcast please check out our sponsors in the description and now let me leave you with some words from frank harvard history is a constant race between invention and catastrophe thank you for listening and hope to see you next time" } ]

[ { "from": "human", "value": "in dyke nor mr. con had any involvement in any misconduct by mr. Epstein of any kind at any time the executives the executors lawyer said in a statement it is enormously regrettable that the Attorney General chose to level false allegations and to unfairly malign the co-executors reputation without any proof or factual basis um what no proof has been provided um and what reputation by the way these two dudes have the same reputation as insert any scumbag here and that's the sort of reputational power that these people have if we were doing a social credit score they would have a negative 100 so what do you mean their reputation why is his name all over the Epstein stuff can you answer that for me wise con signature everywhere wise in dike signature everywhere why were they facilitating sham marriages and the real question is why have they not been charged yet if you'd like to contact me you can do that at Bobby kapuchi at protonmail.com that's B-O-B-B-Y-C-A-P-U-C-C-I at protonmail.com you can also find me on Twitter at B-O-B-B-Y underscore C-A-P-U-C-C-I all of the links that go with this episode can be found in the description box" } ]

[ { "from": "human", "value": "They'll give you a free one-year supply of vitamin D and five free travel packs with your first purchase when you go to athleticgreens.com slash Lex. This is the Lex Freedom podcast. To support it, please check out our sponsors in the description. And now, dear friends, here's Paul Rosley. In 2006, at 18 years old, you fled New York and traveled to the Amazon. This started a journey that I think last to this day. Tell me about this first leap." }, { "from": "gpt", "value": "What in your heart pulled you towards the Amazon jungle? From the time I was, you know, three years old, I'd say, you know, it was dinosaurs, wildlife, documentaries, stever, when you name it. And like when my parents said, you know, nature versus nurture, they nurtured my nature. I was always just drawn to streams, forests. I wanted to go explore where the little creek led. I wanted to see the turtles and the snakes. And so I was a kid that hated school, did not get along with school. I was dyslexic and didn't know it undiagnosed. I didn't read until I was like 10 years old, like way behind. And so for me, the forest was safety. Like I remember one time in first grade, they had you doing those, you know, those multiplication sheets that was pure hell for me. And so I actually got so upset that I couldn't do it, that I ran out, the classroom ran out the door and went to the nearest woods and I stayed there because that was safe. And so for me, like once I got to the point where I was like, high school isn't working out, I had incredibly supportive parents that were like, look, just get out, take your GED, get out of high school after 10th grade. You got to go to college, but like start doing something you love. And so I saved up and bought a ticket to the Amazon and met some indigenous guys. And the second I walked in that forest, it was like, it's like the first scene in Jurassic Park when they see the dinosaurs and they go, oh, this is it. I walked in there and just, I looked at those giant trees. I saw leafcutter ants in real life and I just went, oh, it was like the movie just started." }, { "from": "human", "value": "You know, that was when, that was when like I came online. Can you put into words, what is it about that place that felt like home? What was it that drew you? What aspect of nature, the streams, the water," }, { "from": "gpt", "value": "the forest, the jungle, the animals, what drew you? It's just, it's always been in my blood. I mean, for any forest, I mean, whether it's, you know, upstate New York or India or Borneo, but the Amazon, it's all of that turned up to this level where everything is superlatively diverse. You know, you have more plants and animals than anywhere else on earth, not just now, but in the entire fossil record. It's the Andes Amazon interface, it's just that's, terrestrially, that's where it is. It's the greatest library of life that has ever existed. And so you're so stimulated, you're so overwhelmed with color and diversity and beauty and this overwhelming sense of natural majesty of these, you know, 1000-year-old trees and half the life is up in the canopy of those trees. We don't even have access to it. There's stuff without names walking around on those branches and it's like, it just takes you somewhere. And so going there, it was like, you know, the guys I met just opened the door And they were like, you know, how far do you want to go down the rabbit hole?" }, { "from": "human", "value": "How much of this do you want to see? You mentioned Steve Irwin. You list a bunch of heroes that you have. He's one of them. And you said that when you aren't sure about a decision, you ask yourself, WWSD, what would Steve do? Why is that such a good heuristic for life?" }, { "from": "gpt", "value": "What would Steve do? He's a human being that like everything we saw from Steve Irwin was positive. Everything was with a smile on his face. If he was getting bitten by a reticulated python, he was smiling. If he was, you know, getting destroyed in the news for feeding a crocodile with his son too close, he was trying to explain to people why it's okay and why we have to love these animals. And everything was about love. Everything was about, you know, wildlife and protecting. And to me, a person like that, that where you only see positive things, that's a role" }, { "from": "human", "value": "model." }, { "from": "gpt", "value": "And it's just like an endless curiosity and hunger to explore this world of nature. Yeah, and an insatiable madness for wildlife. I mean, the guy was just so much fun." } ]

[ { "from": "human", "value": "I gotta, if it's okay, read to you a few of your own words. You open the book, Mother of God, with a passage that I think beautifully paints a scene. Before he died, Santiago Duran told me a secret. It was late at night in a palm thatched hut on a bank of the Tambopada River, deep in the southwestern corner of the Amazon basin. Besides a mud oven, two wild boar heads sizzling, sizzled in a cradle of embers, their protruding tusks, curling in static agony as they cooked. The smell of burning, sycorropia wood and cinched flesh-filled air, woven baskets containing monkey skulls hung from the rafters, where stars peek through the gaps in the thatching, a pair of chickens huddled in the corner, conversing softly. We sat facing each other on sturdy benches, across a table hewn from a single cross-section of some massive tree, now nearly consumed by termites. The song of a million insects and frogs filled the night. Santiago's cigarette trembled in the aged fingers as he leaned close over the candlelight to describe a place hidden in the jungle. That line, the songs of a million insects and frogs filled the night for some reason hit me." }, { "from": "gpt", "value": "What's it like sitting there conversing among so many living creatures all around you? Every night in the jungle, you live in constant awareness of that out there in the darkness are literally millions of heartbeats around you. We exist in this domesticated, paved world most of the time, but when you go out there past the roads and the telephone poles and the hospitals and you make it out into earth, just wild earth, and there's no- there's no- it's not like this is a national park. There's no rescue helicopter waiting to come get you. You are out there, and you're surrounded at night by- I mean, there are snakes and jaguars and frogs and insects and all this stuff just crawling through the swamps and through the trees and through the branches. We put on headlamps and go out into the night and just absolutely fall to our knees with wonder of the things that we see. It's absolutely incredible." }, { "from": "human", "value": "And most of it doesn't make sounds, like the insects do." }, { "from": "gpt", "value": "The insects do, the frogs do, you have some of the night birds making sounds, but a lot of it, everything has evolved to be silent, invisible. I mean, everything there is in the, on the list, like there's another line in Mother of God where I said like, you know, like life is just like a temporary moment of stasis and like the churning, recycling death march that is the Amazon. Like it's been called the greatest natural battlefield on Earth. I mean, in any square acre, there's more stuff eating other things than anywhere else. And you go through a swamp in the Amazon and there's like, there's tarantulas floating on the water. There's frogs in the trees. There's tadpoles hanging from leaves waiting to drop into the water. There's fish waiting to eat them. There's birds in the trees. You literally are surrounded by so many things that your brain can't process it." }, { "from": "human", "value": "It's just overwhelming life. Churning death march. Some of the creatures are waiting and some of them are being a bit more proactive about it. What do you make of that churning death march? That the amount of murder that's happening all around you at all scales, what is that, you know, we dramatize wars and the millions of people that were lost in World War II, some of them tortured, some of them dying with a gun in hand, some of them civilians, but it's just millions of people. What about the billions and billions and billions of organisms that are just being murdered all around you? Does that change your view of nature," }, { "from": "gpt", "value": "of life here, millions and billions? I've always kind of wondered like that, like when you see like a, you know, wildebeest taken down by lions and eaten from behind while it's alive and it makes you question God. You know, you go, how could they let this happen? In the Amazon, I find personally that these natural processes make up almost a religion, that it reminds you how temporary we are, that, you know, the bot flies that are trying to get into your skin and the mosquitoes that are trying to suck your blood and the, you know, that when you sweat, you see the, you literally can like hold out your arm and watch the condensation come off of your skin and rise up into the canopy and join the clouds and rain back down in the afternoon and then you drink the river and start it all over again and it's like, it's flowing through you. So the Amazon reminds me that there's a lot that we don't understand. And so when it comes to that overwhelming and collective murder, as Werner Herzog put it, it's just part of the show, it's part of the freak show of the Amazonian night." }, { "from": "human", "value": "I see you, in certain moments, able to feel one with a mosquito that's trying to kill you slowly." }, { "from": "gpt", "value": "One with the mosquito is a stretch." }, { "from": "human", "value": "Is it always the enemy? What I mean is like, you're part of the machine there, right?" }, { "from": "gpt", "value": "Yeah, and it's like fair play. It's like fair play. So like we have bullet ants and like, you know, you get nailed by a bullet ant and you just go shh. Yeah, well done, well done. Today's over, I'm going back to bed and I'm taking a pilot time and all and you know." }, { "from": "human", "value": "Do you think, in that sense, when you're out there, are you a part of nature or are you separate from nature?" }, { "from": "gpt", "value": "Is man a part of nature or are you separate? I think that's what's so refreshing about it, is that out there you truly are. And so whether we're bringing researchers or film crews or whether we're just out there ourselves on an expedition, you truly are part of nature. And so one of the things that my team and I started doing when I became friends with these guys, you know, this is a family of indigenous people from the community of Infierno and they took me in and as we got close, they started saying, you know, you can come with us on our like annual hunting trip. And I went, okay, and it's four guys in a boat and you don't wanna get your clothes wet. So we're all in like our boxers in a canoe with a motor going out past the places that have names and you're out in the middle of the jungle. And the thing is like, when your motor breaks, you are so quickly reminded of the inerrant truths, like the things that nobody can argue with. And we live in such a human world where everything is debatable, religion and politics and perspectives on everything. And then you get down to this point where it's like, if we don't figure something out, the river is going to rise and take the boat. That's the truth. And ain't nobody gonna like argue with that. And it's like, to me, there's a beauty in that truth because then all of us are united there in that truth against like the natural facts around us. And so to me, that's a state" } ]

[ { "from": "human", "value": "where I feel very, very at home. And the Amazon is more efficient than most places on earth at swallowing you up. God, yeah. Okay. Yeah. So just to linger on that, because you've spoken about Francisco de Aralana, who's this explorer in 1541 and 42 that sailed the length of the Amazon, probably one of the first. And there's just a few things I should probably read. I should probably find a good book on him because the guy seems like a gangster. Yes. There's some great books on him. So he sailed, he led the expedition that sailed all the way from one end to the other. There's like a rebuilding of a ship. Which is insanity. Yeah. Yeah. Because it speaks to the thing, it's like nobody's gonna come and rescue you. No. If your boat dies," }, { "from": "gpt", "value": "you're gonna have to rebuild it to the Amazon. Yes. There's some great books on him. Yeah. Yeah, so they came down the Andes, entered in the headwaters of the Amazon, constructed some sort of raft, boat, craft, something, and made it down the entire Amazon basin. Of course, his stories are the ones that led to the Amazon being called the Amazon because he reported tribes of women. He reported these large cities, places where the tribes lived on farms of river turtles that they corralled and they lived off of that protein. And then when they came out to the mouth of the Amazon, if I remember it correctly, that just through navigation and the stars, they were able to calculate where the way was back to Spain and make a boat" }, { "from": "human", "value": "sea-worthy enough to bring them home. Incredible. Absolutely incredible. Do people like that inspire you your own journey? What gives you kind of strength that in these harshes of times, in the harshes of conditions, you can persevere?" }, { "from": "gpt", "value": "Yeah, I mean, you look at the stories of people that are so, you know, these stories of people that have overcome incredible suffering like that or like, you know, what Shackleton did or something like that. And so like when you're, you know, I've been, you know, your tent gets washed away. You go to sleep and the river rises 20 feet and washes away your tent and you crawl out and all you have is a machete and a headlamp. Literally, no bag, no food, no nothing. And you go, wow, the next six days before I reach back to a town is gonna be just pure hell. I'm gonna be sleeping on the ground covered in ants destroyed by mosquitoes. And then it becomes, you know, am I in any capacity, any percentage as tough and resilient as the people that I've read about that have made it through things far worse than this? And then" }, { "from": "human", "value": "that's the game you play. Well, it goes through your head when all you got is the headlamp and the machete. So are you thinking at all? Like I've gotten a chance to interact quite a lot with Elon Musk and he constantly puts out fires having to run several companies. There's never a kind of whiny deliberation about issues. You just always want one step forward how to solve, right? This is the situation. How do you solve it? Or do you also have a kind of self motivating, almost egotistical, like I'm a bad motherfucker. I can handle anything almost like trying to fake it till you make it kind of thing." }, { "from": "gpt", "value": "There was a little bit of that. With your machete in it. I got a sword. There may have been a little bit of that when I was like, you know, like 14, 15 years old, I'd like, you know, have like a hunting knife and my dog and I'd go out into the woods of like the Catskills and survive for a weekend. My rule was one match. You know, you get one match and you got to make shelter and then, you know, I'd bring like a steak and like make a fire and stuff. And like at that point, there maybe was some ego, but in the Amazon, you get stripped down so completely that you, it's like that thing like, you know, watch the atheism leave everyone's body when they think they're about to die. It's like when you find yourself staring up at the Amazon at night and you go, there is no hope of getting out of here. I mean, I was once lost in a swamp where it took me days to get out of there. And there was, there was moments where I just said, this is, you know, this is clearly it. There's no, there's no ego there. There's just hope. You, you start, you start realizing what you believe in and praying that you'll be okay. And then trying to, trying to summon whatever you know about how to survive and that's it. And so it's, it's actually, again, it's kind of, it's kind of a blissful state. If you can walk that line between like adventure and tragedy and" }, { "from": "human", "value": "sort of keep yourself right at that very, very fine line without going over." }, { "from": "gpt", "value": "Ever fear of death, fear, ever fear, terror? No, I don't want to die. I want to, I want to, you know, I love the people in my life and there's a lot of things I want to do. But every time I've been, every time I've been certain that I'm gonna die, it's been, I've been very, very calm, very calm and just sort of like, okay, well, if this is how the movie goes, then this is how it goes. Almost accepting." } ]

[ { "from": "human", "value": "Yeah. Which is, which is reassuring. You mentioned Herzog, just to venture down this road of death and fear and so on. There's been a few madmen like you in this world. He's documented a couple of them. What lessons do you draw from Grizzly Man or Into the Wild, those kinds of stories? Were you ever afraid that you would be one of those stories?" }, { "from": "gpt", "value": "Oh, yeah. I actually think that it's in Mother of God where I said I almost into the wilded myself. Like I went out there and really I got so lost and so destroyed that I said, this is, this is, this is gonna be the next one. You know, this is gonna be the next story of some idiot kid from New York who went to the Amazon, thinking he was Percy Fawcett, and then vanished. Because if you, if you do vanish out there, your body's gonna be consumed in a matter of days. Like, like two. You know, we see, if we see an animal dead on a trail, it's, you got dung beetles and fly larva and vultures and there's a whole pecking order, you know, you get the Black the yellow vultures, the king vulture, they all come in. That thing is picked clean in a couple of days." }, { "from": "human", "value": "What would be the creature that eats most of you in that situation?" }, { "from": "gpt", "value": "Probably the vultures. Probably the vultures and the maggots. It's really quick, it's really, really quick. Even as far as you can't leave food out. If you have a piece of chicken, you say, oh, I'll eat it in the morning, you leave it out," }, { "from": "human", "value": "you can't do that, it's not good by morning. Grizzly Man, for example, because that's a beautiful story. It's both comical and genius, especially the way Herzog tells it. First of all, do you like the way he told the story?" }, { "from": "gpt", "value": "Do you like Herzog? I do, I love Herzog and I love his documentary, The Burden of Dreams, which is in the Amazon, not very far from where I work. And the sheer madness that you see this man undergoing of just trying to recreate hauling a boat over a mountain is wild. And the extras that he hired to play the natives are the, I think they're Machiganga tribesmen, and they just look like all the guys that I hang out with. And it's like, they're doing all this stuff in the jungle that months and months and months, and you can just see him deteriorating with madness because the jungle, your boat, you know how many times I've tied up a boat to the side of the river? This just happened like a year and a half ago. I tied up through COVID, I pretty much just lived in the jungle for a while. And there was nobody there and there was no support and I tied up my boat and the rain is just hammering. Like the universe is trying to rip the earth in half, the rain is just going and the river's rising and I tied up the boat, but then you go to sleep and you gotta wake up every two hours to go check the boat. And the boat is thrashing back and forth and so all night, every two hours, I'd wake up barefoot in driving rain like golf ball raindrops and just go down, check the boat. And then by morning I fell asleep, woke up, checked the boat and then I was like, I'm just gonna make my coffee. I was so done, I was so like at the end of my rope every time bailing the boat out and stuff. And then we got 15 minutes of heavy rain that filled the boat sank it. So now I'm stuck up river with no boat. And it's like that type of thing where no matter how hard you try, the jungle's just like, listen you ain't you nothing. You are nothing. And so it's that constant reminder. And so Herzog really threw himself into that in that film" }, { "from": "human", "value": "and it's brilliant to watch. What do you think he meant by the line that you include in your book? It's a land that God, if he exists, has created in anger." }, { "from": "gpt", "value": "Said in a German accent. Yeah, overwhelming and collective murder." }, { "from": "human", "value": "So that's, so you didn't really appreciate" }, { "from": "gpt", "value": "the beauty of the murder. I think he appreciated it, but to him, it was very dark. I think he saw the darkness in it, and that's there. It sure is, as soon as you do Ayahuasca, that door opens and you see the darkness. Cause that brings you right into the jungle, like the heart of it. But I think that for him, it is, I think that darkness is something that he embraces and that he loves. There's another film of his and I don't know if this is accurate, but my memory has it that there's a penguin and I think it's an Antarctica and the penguin is going in the wrong direction. Away from the ocean. And I feel like he goes on this monologue about how like he's just had enough. Yeah. He's, you know, this one penguin" }, { "from": "human", "value": "is just marching towards, you know. Yeah. Well, his, because I remember that clip from that documentary, and what Werner says is that the penguin is deranged. Yes. That he's lost his mind. And I took offense to that. Yeah. Because maybe that's a brave explorer. Like, how do you know there's not a lot more going on? Like, it could be a love story. Those penguins get super attached." }, { "from": "gpt", "value": "Maybe his mate was over there, and he had to go find her. Well, you know." } ]

[ { "from": "human", "value": "Or the lost mate, and he last time he saw her was going to that direction. Exactly. So this is like the great explorer. We assume animals are like the average of the bell curve, like every animal we interact with is just the average. But they're special ones, just like they're special humans. Yeah, no." }, { "from": "gpt", "value": "That could be a special penguin. Yeah. That could be a special penguin. It could have been. I had the same thought where I was like, I found it beautiful how he interpreted it. What I took away from that was I found that Berna Herzog's monologue there was brilliantly dark and also comedic, but maybe irrelevant biologically speaking towards tangoans, which happens a lot with animals. I find there's so many times where I'll find people be like, do you think that animals can show compassion? And you hear a bunch of people that have never left the pavement talking about like, wow, this one animal helped another and it's like, go ask Jane Goodall if animals can show compassion. Go talk to anybody that works on a daily basis with animals. And so like to me, there's always a little bit of frustration and hearing people sort of like pleasantly surprised that animals aren't just these automatons of, just what's the word, like programmed nothingness." }, { "from": "human", "value": "First of all, what have you learned about life from Jane Goodall? Cause she spoke highly of your book and Eulistris as one of the mentors," }, { "from": "gpt", "value": "but what kind of wisdom about animals do you draw from her? The wisdom from Jane is so diverse. I mean, first of all, she's someone that, the work that she did at the time she did it was so incredible because I mean, she was out there at a very young age doing that field work. She was naming her subjects, which everyone said you shouldn't do. She broke every rule. She broke every rule. She was assigning and everyone said, you know, you're anthropomorphizing these animals by saying that they're doing this and that. And she was like, no, they're interacting. They're showing love, they're showing compassion, they're showing hate, they're showing fear. And she broke straight through all of those things and it paid off in dividends for her." }, { "from": "human", "value": "Do you see the animals as having all those human like emotions of anger, of compassion, of longing, of loneliness from what you've seen especially with mammals or different species out there. Do they have all that?" }, { "from": "gpt", "value": "It depends on the animal. You know, if you're talking on the scale of a cockroach to an elephant, you know, it's like a lot of these things. And I wonder about this stuff all the time. You know, I'll have a praying mantis on my hand and just go, what is going through your mind? You know, or you'll see a spider make a complex decision and go, I'm gonna make my web there. You know, and you go, how are you doing this? How are you, because he made a calculation there. You know, it's smart. I was in the jungle not that long ago when I was walking and all of a sudden this dove comes flying through the jungle right up to my face, lands on a branch, like right here, right next to me. I look at the dove, dove looks at meond she's like, hey. And she's clearly like panting. And I'm like, why are you so close? This is weird. And she's like, I know. And then an ornate hawk eagle flies up 10 feet away, looks at both of us and just like scowls and like sticks up its head feathers and then just like flies off. And the dove was like, sweet, thanks. And then Fleh flew in the other direction and I was like, Dude, you just used me to save your life." }, { "from": "human", "value": "The Dove Noo. This is what, because there's Mike Tyson and there's Albert Einstein. And sometimes I wonder when I look at different creatures, even insects, like is this Mike Tyson or is this Einstein? Because one or other kinds of personnel, like is this a New Yorker or is this a Midwesterner or is this like a San Francisco barista of the insects. Like there's all kinds of personalities, you never know. So you can't like project, like if you run into a bear and it's very angry, it could be just the asshole New Yorker." }, { "from": "gpt", "value": "Yeah, sure, sure. As opposed to-" }, { "from": "human", "value": "What are you saying about New Yorkers, man? Exactly, point well made. So speaking about communicating with a dove, you first met the crew in the Amazon, you talk about JJ as somebody who can communicate with animals, what do you think JJ is able to see and hear and feel that others don't," }, { "from": "gpt", "value": "that he's able to communicate with the animals. When I say this is the most skilled jungle man I've ever seen, and I know so many guys in the region, he has libraries of information in his cranium that we cannot fathom, it's just stunning. Like I have seen him use medicinal plants to cure things that Western doctors couldn't cure. I've seen him navigate in such a way that he's not using the stars, he's not using any discernable... It's like when elephants, sometimes you'll watch a herd of elephants and they'll be like yo, let's go, we're going this way and you'll see them sort of communicate, but there's no audible sound, they'll just decide that they're going that when they all do it. JJ has this way in the jungle of... He'll stop and he'll go wait and he go, what is it? And he goes, there's a herd of peccary coming and I'm like where? Based on what? He's like, just wait, you'll see. And he'll sit there, you know? You think that's just experience? It's an incredible experience. It's growing up barefoot in the Amazon. And the gift is that he can speak fluent English. And so when I bring tourists and scientists or news reporters down there, he can communicate with them. He's actually good on camera" } ]

[ { "from": "human", "value": "because he doesn't care about cameras." }, { "from": "gpt", "value": "Just like, you know, for instance, we were walking up a stream a few months ago and I went, hey, look, Jaguar tracks. And he went, oh, and I was like, what? Jaguar tracks. And he's like, no, look, look harder. And I was like, the toes are deeper than the back. And he was like, ah, and where are they? And I was like, by the water. And I was like, the Jaguar is drinking. It was leaning to drink. And he was like, that's right. He's like, now look behind you. I look behind me. And there's scat, there's a big log of Jaguar shit sitting there. And it's got butterflies all over. Fresh? Pretty fresh. And then there's another one that's less fresh. And so he's teaching me as he does, he's going, look at this, like at this. Is that one as fresh as this one? No. And then he goes, now look up, look up. There's three vultures above us. The kill is near us. The jaguar has been coming multiple times to the river to drink as it's feasting on whatever it killed. And he's going, it's within 30 feet of us right now. And it's like, I'm like, oh look, impression's in the sand. He's like, I just drew 19 conclusions from that. It's like watching Sherlock Holmes at work. It's just-" }, { "from": "human", "value": "Like constructing the crime scene. Incredible. Does that apply also to be able to communicate with the actual animals? Like read into their body movements directly, into their, whatever that dove was saying to you, and you'll be able to understand? Or is that all just kind of taken in the complex structure of the crime scene of the interactions of the different animals, of the environment and so on. Like what is that that you're able to communicate with another creature?" }, { "from": "gpt", "value": "That he was able to communicate with another creature? He knows the intention of pose, he knows the habits, he knows the perspective. And when he talks about animals, he'll talk about each species as if it's a person. So he'll say, oh, oh, the jaguar, she never likes to let you see her. And so he'll come back from the jungle and go, oh, I was watching monkeys and this jaguar was also watching the monkeys, but I was being so quiet. She didn't see me. And then when she see me, she feels so embarrassed and she go. And he'll tell you this story like as if he had this interaction with like his neighbor. And you know, and he'll be like, oh, the puka conga, it never does that. You won't see it do that. And so one time, one time he caught a fish and I, I was such a big fish. It was this big, beautiful pseudo plaistoma, this tiger catfish, this amazing old fish. And they're all excited to eat it. And I felt so bad watching this thing gasp on the sand. And I went, you know what? We don't need this. This is for fun. I threw it back. And then I took my hand and I went and I made like drag marks, like, so I could say, oh, it snuck back in the water. And so he walks up, he looks at it, and he was like, I hate you. And I went, what? No, I said, I must have, it must have just, he went, that's not what happens. He goes, it goes like this when he knew the track of a fish. And I was like, oh yeah. I was like, all right, JJ, I'm sorry, I'll catch you another fish." }, { "from": "human", "value": "I was like, all right, JJ, I'm sorry. So stepping back to that way you open mother of God and who was Santiago Duran and what secret did he tell you?" }, { "from": "gpt", "value": "JJ's father was, at some point he was a policeman, at some point when he was a teenager he was working on the boats that before this little gold mining city of Puerto Maldonado grew, the only way to get supplies in was to take canoes up the Tambopada River up to the next state which is Puno and where mules would come down from the mountains with supplies and then he'd pilot the boats down but they didn't have motors at that time so he would be pulling the boat so he was he became this physically terrifying man and I met him when he was in his 80s and he was still living out in the jungle by himself and I mean he's seen an anaconda eat a taper which is the you know a cow-sized mammal in the Amazon he'd seen uncontacted tribes face to face he once killed an 11-foot electric eel opened the back of the thing's neck removed the nerve that he says was the source of the electric then he cut his forearm placed that nerve into his forearm wrapped it with a dead toad and claimed that it would give him strength through the rest of his life and continued to be a jungle badass until the day he quietly leaned back at a barbecue and ceased to be alive the man was incredible but the secret that he told us was that if you want to find big anacondas you know if you want to see the yaku mama he was like you have to go to the boa eo the place of boas the the place that we came to call the floating forest and so he sent us there and it became like this this pilgrimage and you know in the Amazon the a lot of the creation myths are based around the anaconda coming down from the heavens and carving the rivers across the jungle and if you look at the rivers it looks like that it looks like the path of an anaconda crawling through the jungle, it's even the right color. And so, from the reference to the tribes of women, the Amazons, to the Anaconda Mother, everything in the Amazon is very feminine based. Even the trees, the largest trees in the jungle, the mother of the forest, the Madre de la Selva is the Capac tree and it's just this monster tree, these beautiful ancient trees. And that was the beginning of the transition that we made from me being like, I hate school, I want to go on adventures. Jane Goodall got to do all this amazing stuff. I'm just a kid stuck here to eventually becoming something that had to do with where my identity became the jungle, where my life became the jungle. The secret that he told us opened that door because when we started working with these giant snakes, it started getting attention. It started getting people to go, what are you doing? And it started allowing me to have experiences that solidified and nailed down the fact that this wasn't just like a weekend" } ]

[ { "from": "human", "value": "retreat, this was something that I was born to do. And gave me more and more motivation to go into these uncharted territory of the Yakumama. Just to step back, what nations are we talking about here? Some geography, what are we talking about? Where is this? So I'm in Peru. Yeah," }, { "from": "gpt", "value": "we're in Peru. Which is a South American nation. Which is a South American nation. Peru is a South American nation. Brazil has 60% of the Amazon, which is unfortunate because anything that happens politically in Brazil has a massive impact on the Amazon. Peru has the Western Amazon, and Ecuador has a little bit of the Western Amazon. And the Western Amazon is where the Andes Mountains, the cloud forests, which is a mega biodiverse biome, falls into the Western Amazon lowlands. And so you have the meeting of these two incredible biomes, and that's what makes this superlative, incredible, glowing moment of life on Earth. So yeah, we're in Peru, in the Madre de Dios, which is the mother of God, which I always thought was such a beautiful, the jungle is the source of all life. And so we were with the Eseja people, and they belong to a community that's called Infierno, which was given by the missionaries, who when they tried to go bring these people, Jesus got so many arrows shot at them that they just called it hell. And so Santiago Duran helped unite these tribes that were scattered through the jungle and get them status, government recognized status as indigenous people. So he was sort of a hero. He was sort of a legend for a lot of the stuff he'd done out barefoot with just a rifle and a machete in the jungle. He had 19 children. And the last one, I think the 20th child that he adopted was a refugee from the shining path that floated down the river. And he just took him in. And this is just a guy that was a, you know, everything he did, like when he died, the whole region showed up. He was somebody. So just the fact that I know him gives me street credit. Like the fact that I knew him, I can go like, oh, I knew Santiago. And people are like," }, { "from": "human", "value": "no. I'm like, yeah. So you have to get integrated to the culture, to the place that I mean, in every single way, which is tough for you for the being from New York." }, { "from": "gpt", "value": "Yeah. Yeah. It could have been tough, but it was, I took to it, you know, the jungle, they were very, you know, JJ is teaching me about medicines and we were doing bird surveys and, you know, taking data on macaw populations. And JJ was just like, you really want to, like, he goes, you got to sleep. And I was like, I only have a few weeks here. I don't know if I'm ever going to come back. I'm never going to sleep. So we'd be out every night looking for all the wildlife we could. I wanted to take photos. I wanted to see things. And then, you know, the exchange came with that. He was like, you know, I'm terrified of snakes. And I said, well, I've always worked with snakes. I said, I'll teach you how to handle snakes. And then we just had this, like, little exchange. And when I left after my first time back in 2006, asleep, you know, I said, I said, how can I help? And they were like, look, you know, we're out here trying to protect this little Island of forest that is going to be bulldozed. and and the more people that you can bring the more knowledge and the more awareness that you can bring to this it'll help. And so really at that age at 18 years old I sort of started dabbling with the idea of that I could be part of helping these people to protect this place that I loved and of course at that time that idea seemed like too large of a dream or too large of a challenge so that I could actually impact it." }, { "from": "human", "value": "So what was the journey of looking for these giant snakes, of looking for anacondas? And what are" }, { "from": "gpt", "value": "anacondas? Anaconda is the largest snake on earth. So you have reticulated pythons in Southeast Asia, they're actually longer. But anacondas are these massive boas, they give live birth. And unlike a lot of other species, so an anaconda starts off, you know, a little two foot anaconda, just a little thicker than your finger, a little baby. And they're food for cane toads, herons, crocodiles, you name it. They're they're pretty harmless, defenseless. But as they grow, they're eating the fish, they're eating the crocs and then they grow a little more and they're eating things like capybara and they're eating larger prey. And then at the end of their life, a female anaconda, you're talking about a 25 30 foot 300 400 pound snake with a head bigger than a football." }, { "from": "human", "value": "and these things that means that they impact the entire ecosystem. Which is very unique. It moves up the food chain to become basically..." }, { "from": "gpt", "value": "An apex predator... And like they're constantly at war with everything else but you know so I showed up in the Amazon. I was like so where the anaconda is at? and they were like no no no, it's not like that. They're like, you have to find these things. They're subterranean. They're living in the special swamps. People kill them. And so we went to the floating forest after we'd come back from an expedition. We'd call it like a 12-foot anaconda, and now it's become this classic photo of me and JJ with this anaconda over our shoulders. And we were like, 12 days out in the jungle on a hunting trip, and we came back and we showed his dad. And Santiago looked at us, and he was like, that's the smallest anaconda I've ever seen. He's like, you guys are pathetic- And he was like, look, go. He was like, I'm giving you permission. Go to the emotional, go to the floating forest. And so we went to this place and we reached there at night, and it was me, JJ, and one of his brothers. And his brother took one look at it and was like, I'm out. And he started walking back, and me and JJ get to the edge of this thing. And this is our friendship. It's both this two idiots pushing each other farther and farther. I like put a foot on the ground and it all shook. And the stars are reflecting on the ground and what we realize is that it's a lake with floating grass on top of it. And there's islands of grass floating on this lake, very life of pie. And the tops of trees are coming out of the surface of the water. And so we start walking across this, and JJ's going, these are big anacondas, and I'm going, JJ, that's a two foot wide smooth path snaking through the grass and there's no anaconda that big, he was going, they're listening I said, they don't have ears. He goes, they're listening, and it's like, we're walking and then it's like, maybe it's like one AM or something, and it was just like one of those moments where we saw it at the same time and we're standing by the tail and the snake was so big that, I mean, this must have been a 25 foot anaconda dead asleep with a probably a 16 foot anaconda like sprawled across her and they're laying in the starlight and we're floating on top of a lake standing there in the middle of the Amazon and JJ just, I just, I could feel the blood drain out of his face and as like however old I was, you know, maybe 20 years old, I just said, if I, if we could somehow show people this, we'll be on the front cover in National Geographic and we can protect all the jungle that we want and so I tried to catch it. So I jumped on the snake and the only measurement I have of this animal is that when I wrapped my arms around it, I couldn't touch my fingers and so I was, you know, my feet were dragging and to her credit, this anaconda did not turn around and eat me because her head was, you know, this baby and, and she went and she reached the edge of the, the grass island and she starts plunging into the dark and so I'm watching the stars vibrate as this anaconda is going and I had to make the choice of either going head first down into the black, which no thank you, or stopping and just keeping my hand on this thing as it raced by me and I just felt the scales and the muscle and the power go by and then eventually taper down to the tail until it slipped away into the darkness and I was laying there, just panting. And then I turned around and went, JJ, what the fuck? Like, where were you, man? He was just like completely white, circuits blown. And I had to go then like, kind of like take care of him. I was like, are you okay? And he was like, no, he, you know, he just couldn't. And so we came back with that. And then after that, we were like, okay. Clearly the parameters of reality that we thought were possible are just a tiny fraction of what's out there. Like we now, that sort of recalibrated us. We were like, okay. We're rubbing up against things that are bigger than we thought were ever possible. And so we were like, okay, now we need to," } ]

[ { "from": "human", "value": "we need to concentrate on that. We have." }, { "from": "gpt", "value": "So how dangerous is that creature to you, to humans? To humans, not at all. I mean, Mike, our cook's father-in-law was eaten by an anaconda, but like, you know, then again, like-" }, { "from": "human", "value": "Look at the way you say that." }, { "from": "gpt", "value": "Tell that story. Sometimes it happens. It happens. I mean, come on, every now and then somebody gets stung by a bee and dies. Like, you know, once in a while it happens. But you gotta have a really big anaconda really hungry. And like anybody that works in the wild, I mean, just, you know, if you walk up to a crocodile, even a giant Nile crocodile, you walk up to the most of the time, they're gonna run into the water. They don't want confrontation. They hunt in their way on their terms sneaky. You're not gonna see him. And so with an anaconda it's like, yeah, I mean the guy who got eaten, if you're drunk and you go to the edge of the water and you go for a midnight swim by yourself in an Amazonian lake, I mean, whose fault is that?" }, { "from": "human", "value": "But if you jump on an anaconda and try to," }, { "from": "gpt", "value": "try to hold on, then you're safe. Apparently, I mean, I think at this point, we've, you know, the research we've done, I think I've handled or caught, you know, over 80 anacondas in the field, and not one of them has bitten me. They always choose flight over fight. They're like, just leave me alone, let me go. I'm just gonna crawl under this thing. Um, they're not an aggressive animal. I mean, no snake. No actually like, I kind of like, the only time I get particular with like, you know the words is like people go, that's an aggressive, Black Mambas are aggressive. And I say, no, no snake is aggressive. A rattlesnake is gonna rattle to say hey, back up. Cobra's gonna stand up and show you its hood and people go, oh, he's looking, he's being aggressive. No, he's not being aggressive. He's going, don't step on me. Don't make me do this." }, { "from": "human", "value": "They're actually being very peaceful." }, { "from": "gpt", "value": "Apparently, that's the way I look at it, because if there is a cobra in the corner of this room Right now, he would crawl under the curtain" }, { "from": "human", "value": "and we'd never see him again. Yeah, it's like Genghis Khan, before conquering the villages, he always offered for them to join the army. Doesn't need to be like this. Yeah, join us. Nobody gets destroyed. If you want to be proud and fight for your country, then we're gonna deal with this. Oblige him. Exactly, okay. So how do you catch? Actually, let's step back because there is, in part, you are a bit of a snake whisperer. So what is it that others don't understand that you do about snakes? What's maybe a misconception? Or what have you learned from the language" }, { "from": "gpt", "value": "you speak that snakes understand? I don't know, it's just, it's an animal that has many times in my life I've been responsible for helping. I started catching snakes when I was very young. I'd watch Deaver when I go out and catch a garter snake or a black rat snake in New York. And then I had a rule. I said I have to catch 100 non-venomous snakes before I'm allowed to handle a venomous snake, if I ever need to handle a venomous snake. And then I was on a trail one time, I think in Harriman State Park, and some guy, like some big hero, he tells us, he's like, back up. I'm gonna get this, and he picks up a stick, and he goes to assault this poor copperhead that's sitting on the trail. And so at 16 years old, I had to go and shoulder this guy out of the way, and I got the thing by the tail and used a stick to very gently just put it off the trail. Copperhead was not gonna do anything to him, but he wanted to beat his chest and show his wife that he was tough. But then in India, I've lived in India for five years at this point, in and out periodically, and snakes are always getting into people's kitchens. One time we had a King Cobra get into someone's kitchen, an 11 foot snake, like a monster, like a god of a snake. This thing stood up, would stand up, he'd be able to look at you over the table. And this terrifying monster dung, just giant gorilla dog dung, we caught it with one of the local snake catchers. And we brought it out, and he goes, you know, I wonder why it was in the kitchen. I'm looking for food, and they go, no, they eat snakes. King Cobra, Opio-Phagus Hannah, they eat snakes. And he goes, she's thirsty. So we got a bottle of water, and we got footage of this. She's standing up, she's going, don't make me kill you, don't make me kill you, you're scaring me right now. I don't wanna kill you. We took the bottle of water, we poured it on her nose, and she started drinking. You could see her just drinking. And the snake just took this long drink, she drank a whole water bottle, and then said, thank you so much, and crawled off. And it's like, to me, the fact that people are scared of snakes, they have symbolic hatred of snakes, someone's evil and sneaky, we call them a snake. And to me, it's like, when I take volunteers or researchers or students out into the jungle and we find an emerald tree boa or an Amazon tree boa or a vine snake, and it's like, it's one of the few animals that you can't really catch a bird and show it to people. You're gonna scare the bird, its feathers are gonna come out, you might give it a heart attack. Snakes, you can lift up a snake. If there's a snake in the room right now, I could lift it up and say, Lex, here, this is how you hold it. And we could interact calmly with this thing and then put it back on its branch, and then it'll go. And I've seen what that does to people, I've seen how the wonder in their eyes. And so to me, snakes have always been this incredible link" } ]

[ { "from": "human", "value": "to teach people about wildlife, about nature. Because they have naturally a lot of fear towards this creature and to realize that the fear is not justified, it's not grounded, or it's not as deeply grounded in reality. Of course, there's always New Yorker snakes, right? There's always gonna be an asshole snake here and there. Coming for me, man. Well, okay, so back to the Anaconda, how do you catch an Anaconda? Like what, how do you handle, because it's such a 25-foot or even 12-foot, these giant snakes, how do you deal with this creature?" }, { "from": "gpt", "value": "How do you interact with it? We had to learn how to do that, because one of the first ones we caught that I would say maybe like a 16-footer, which is no joke of a snake, girth of a basketball, let's say. We're on the canoe, and this is the early days. Now we're at a whole different level, but this is back when we were barefoot and shirtless and just guys in the Amazon, and JJ's like, I just listened to him. He'd be like, get off the boat. You come from the top, we're gonna come from the bottom. I was like, okay, I just did as I was told. I came in, the snake is all curled up, dead asleep. She's got some butterflies on her eyes trying to get salt and stuff, and all of a sudden I see the tongue. Soo, soo. I'm like, she's awake. And I'm like, guys, guys, guys, she's, and they're paying attention to not crashing the boat, to getting over there, and we're all trying to run. snake starts going into the water, so I run ahead, grab this snake, get her by the head. So you got her by the head, and you think, okay, she can't get me. I got her right behind the head" }, { "from": "human", "value": "and it's about this thick, the neck. What's that feel like, sorry to interrupt," }, { "from": "gpt", "value": "like grabbing this thing with a giant head? It's exciting. It's amazing. It's scary. Yeah, it's just, how hard is it to hold? It's not that hard to hold. The scary part is the moment of, it's like, if you ever done like a cliffdive or something, it's that moment where you go, do it. Do it. And if your body's going, Do not do that." }, { "from": "human", "value": "And then you're like, I gotta do it. Scary. Why not? Because you can't just gently like flirt with her. You have to grab it." }, { "from": "gpt", "value": "Oh no. And it's like crossing the street when there's a bus coming. It's like, you hesitate, it's more dangerous. So you go for it, and I got her. And I was like, I got her. And then a coil goes over my wrists. And all of a sudden, my wrists slap together. And you feel this squeeze that can crush the bones out of an animal bigger than me. And the next coil comes very quickly over my neck. And now I'm on my knees with my arms tied. If I wanted to let go of the snake, I couldn't. And my shoulders are coming together and my collarbone is about to break. And I tried to yell for JJ and all that came out was, there was nothing. And so that's what they do to their prey, you know? So I attacked, as far as the snake knows, I attacked. She doesn't know that I just want to measure her." }, { "from": "human", "value": "You started off as the big spoon," }, { "from": "gpt", "value": "but then the snake became the big spoon. Snake very much became the big spoon. And I was, I would say I was 15 seconds away from having my entire rib cage collapsed. And then JJ showed up and grabbed the tail and just started unwrapping this thing. And then we got, but now we have a system. Now we know, like, you know, I'm always, I've done, I've gotten more head catches than anybody. So I'm usually point guy." }, { "from": "human", "value": "And, you know, you're the, you're the, the first, the point guy. I'm the point guy. Okay. The, the, the taking the big risky." }, { "from": "gpt", "value": "Yes. First step. Yes. Although the, it could be argued that there's a similarly large risk for the tail guy because it, anaconda's defense is to take a giant projectile shit. And so the person that gets the tail is gonna smell like anaconda for like at least a week." }, { "from": "human", "value": "Yeah. So it's the least pleasant. You're taking the most dangerous one there. They have the least pleasant job." }, { "from": "gpt", "value": "This is fascinating. But what's really fascinating though, is that because of the Apex Predator, they're, they're eating the fish, they're eating the birds, they're eating everything, and everything in this riparian ecosystem is absorbing the mercury it's coming off the gold mining in the region. And so anacondas can be indicative for us of how is mercury moving through this ecosystem. And this is a region where we've lost hundreds of thousands of acres to artisanal gold mining, where they use mercury to bind the gold. They cut the forest, burn the forest. And then they run water through the sand and the sand particles have bits of gold in it, not chunks, but just little almost microscopic flecks of gold. And then they use the mercury to bind that, they burn off the mercury and that vapor goes up into the clouds just like everything else, it's all connected down there, and then rains down into the rivers. So the people in the region are having birth defects from the amount of mercury that's in the water. So at one point where we were doing most of our anaconda research, we were learning things like these animals actually aren't just ambush predators, which is what most of the literature would tell you is that anacondas are ambush predators. No, they actually go hunting, they'll go find clay licks and salt deposits and they'll wait there. They'll actually pursue animals. And we were trying to take tissue samples to find out if anacondas could be used to study how mercury is moving through the ecosystem. And so that was really, it became, can we use these animals not only as ambassadors for wildlife because everybody wants to see the anacondas, but also, you know, what can we learn from studying this very, very little understood" } ]

[ { "from": "human", "value": "apex predator. And one of the things you can learn is how mercury moves through the ecosystem," }, { "from": "gpt", "value": "which can damage the ecosystem in all kinds of different ways. Yeah, it's brutal, man. The gold mining that's happening down there is, it's funny because we've been hearing a lot recently about like the cobalt mines in Africa. And it's like where we are in the Amazon, we were down there with ABC News, I want to say like a year and a half ago, with my friend Matt Gutman, who's the chief correspondent for ABC. And he wanted to see the Amazon fires, he wanted to see some wildlife, he wanted to see the areas that we're protecting, and then he goes, I want to see the gold mining areas. And I'd never gotten in so deep, but we met these Russian guys, you can't go with the Peruvian, they will kill you. Like our lawyer's father was assassinated for standing up to the gold miners. There was two Russian guys though, who had a legal mining concession somehow, way out past the machine gun guarded limit of the Pampas, which is where they do all this gold mining. And we got in there and took footage of the desert that is forming in what used to be the headwaters of the Amazon rainforest. And it's like, there's a massive global scale ecological crime happening down there that you can see from space, from this unregulated gold mining, and the cops can't go there because they will be murdered. It's completely lawless. What's the machine gun limit exactly? It's the border of this area that they call the Pampas, which is where the rainforest has been cut and completely destroyed. And it looks like Mars, it's just sand. And inside of this area are gold miners. And we tried to get in there to film years ago, and there's just a lot of guys with machine guns who don't let that happen. And what the Russian guys had access somehow, they'd come down with a bit of money and they had a new system. And actually what was interesting is while I was in there, they're very friendly and really too friendly gold miners. And one of them while I was there, he tapped me on the shoulder. He was like, look at those guys. And he was like, those guys over there? He goes, I just heard them say your name. And he goes, that's not a good thing. He goes, they know exactly who you are. And he goes, I wouldn't keep posting to Instagram about gold mining in the Amazon. And I was like, thanks for the Warning and then, you know I think in June somebody pulled up beside me on a motorcycle and I got a more stern warning" }, { "from": "human", "value": "but they pay attention to the flow of information because they don't want the world to" }, { "from": "gpt", "value": "To find out. Oh, the last thing they want is to be shut down. But the gold miners are notorious for you know, just Whacking people and throwing them in a in a pile of you know gold mining leftovers It's really like like the Peruvian government has to get them military to go after them like the work we've done with gold miners converting them into conservationists has all been like I mean I've seen the Peruvian Navy come down and Literally blow up gold mining barges and you know, it's it's it's a war. It's a war being fought in the Amazon" }, { "from": "human", "value": "So it's a it's possible to convert them into conservationist" }, { "from": "gpt", "value": "What's that process like we or is that like you say they ingest? No, I say that in an absolute sincerity We we went up River up the Malinowski River several years ago and I think it was 2018 and everyone everyone was like you are going to die like you will be shot and killed and the reason we were able to do it with relative safety was that the gold miner that we were going with Was the brother-in-law of one of my closest friends down there our expedition chef and one of the directors of jungle keepers And I said look you can go just keep a low profile And so I went up with a photographer and we spent a week there and dead animals everywhere deforestation everywhere I mean the things that we saw were so horrible and we're living with these gold miners that are You know, they're they're getting their gold. They're burning off the mercury. I watch the guy smoking a cigarette burning the mercury off of his gold with the with the vapor going straight into his face with his child right there, I mean unbelievable negligence of just sanity. And then towards the end of the week, the Peruvian Navy comes down the river and everyone starts scrambling. And I was like, I'm just gonna sit here with my hands up. And they didn't even stop. They found the gold mining barge. They have a floating thing in the river that just plums the bottom of the river, just sucks all the sediment up. And they stopped and they strapped a bunch of explosives to this motor. And good Lord, the sound of this explosion and there was just hot metal raining down all over the place. And then they just went. A bunch of guys in fatigues. And they just looked at us like, peace. And I sat there with this gold miner and I went, now what? And he went, well, now I gotta go get a new motor. And I went, why don't you just do something else? And he goes, what else is there? And I went, look at what we do. And I sat there with my phone and I was like, see this? These are pretty tourists and we feed them food. And we show them tarantulas and a cause. And he looked at this and he went, wow. He goes, that looks like so much fun. And I went, it is so much fun. I said, we show people, we bring students to the jungle. He goes, so you're saying if I build you a lodge, you'll bring people? I said, yeah. And I came back a year later and he sat there with a chainsaw, a hand saw, and some nails. And he cut down like 17 palm trees and he built an ecotourism lodge." } ]

[ { "from": "human", "value": "So you gave him another channel of survival of making money." }, { "from": "gpt", "value": "Yes. Of making money. And that's what we've been doing through Jungle Keepers for loggers and for all kinds of extractors is just saying, look, what do you make? You make $15 a day destroying the ancient trees of the jungle. What if we paid you $35 a day to have a uniform and a job and health insurance and security and you just protect it and use all of the jungle knowledge you've gained as a logger to protect this place?" }, { "from": "human", "value": "Who are the loggers trying to destroy the Amazon? Can you say a little bit more about it? Is that as a threat to the Amazon rainforest?" }, { "from": "gpt", "value": "A lot of them are really close friends of mine. They're people that need to make a living and they're jungle people who, you know, the rainforest is a very challenging, especially the Amazon, is a very challenging environment. So you have these people who, they have a chainsaw, they have a job opportunity, they go out and they cut the trees and a lot of these guys grew up fishing, they grew up in the jungle, they know how to do it. And so for them it's a way to like, they also love it. So this is the thing. These are outdoors men, these are guys that love the jungle and so they, you know, in the 90s we had the mahogany boom where they went out after the mahogany and you almost can't find a mahogany tree in the jungle anymore. If you want to talk about like carbon sequestration in the rainforest, the ancient hardwoods hold like 60% of the carbon of the whole rainforest. They have an outsized, disproportionate mass from that ancient density of the wood. And so these loggers go out and they cut the wood that's most valuable and then they bring it back to town and they sell it and then people like us buy it and put it on our kitchen floors. And so the thing is, when I got to the Amazon, it was loggers are the bad guys. And if you talk to a lot of like the PhDs that I worked with down there were always very at odds with the miners, at odds with the loggers. And then I'd be with JJ and JJ would sit down and he'd be like, hey, let's pour a drink. Oh, they have masato. Let's all sit down. We'd all be chilling and throwing them back with a bunch of loggers. And then the opportunity through not vilifying these people came to be like, oh, these guys are great. And then of course out in the wild, every now and then something will happen. You'll see somebody's boat flipped over and you go help" }, { "from": "human", "value": "them out. And then that creates a certain type of kinship. So they're ultimately people who love" }, { "from": "gpt", "value": "the same thing you love. Often, yeah. Even if they don't love it, they're people that aren't necessarily looking to destroy it. I've met loggers who have looked at trees they're about to cut and gone, ah, this is a shame. Started up. They're just like, this is where the paycheck" }, { "from": "human", "value": "comes from. Let's come back briefly to Anacondas. Can you tell me this whole situation with discoveries eaten alive? There's some drama and controversy around that. Can you explain that whole saga with discovery, with your whole effort? Maybe outside of even the drama, the initial thing, which I know feel you're sufficiently insane to actually do of being eaten by Anaconda. Is that actually possible to survive something like that?" }, { "from": "gpt", "value": "I mean, if Anaconda swallows you while you're wearing the suit that they made maybe, but that was in hindsight, that was the result of, look, I go to the jungle and you start seeing these beautiful places, these incredible species. You start developing a relationship with these animals and then you watch it get destroyed. Every year, we watch it burn. Every year, places that are crucial to my soul I have seen leveled and turned to ash. And at some point, we started going, someone has to do something about this. And you look to your right and you look to your left and there is no one because it's the middle of the Amazon and the rainforests have been being destroyed since the 70s. It's a cliche and so we started trying to do something about it. And so I started putting a little bit more emphasis on publicity, a little bit more emphasis on getting the message out there. And so I started trying to see what was going to work. You just start firing shots in the dark and seeing. And JJ's going, you have to help us do something. And I'm going, okay. And so from 18 years old, now I'm 23 years old. And all of a sudden, this place isn't foreign to me anymore. It's home." }, { "from": "human", "value": "And so- When you're trying to think of all the different ways you can bring attention to this place" }, { "from": "gpt", "value": "that you care about that's being destroyed. Yeah, you're standing next to a boulder of progress, of destruction, and it's about to roll onto the forest and just destroy it and snuff out all that life. And no one's there to do anything about it. And so you go, is there any way that I could put myself in front of this boulder and hold it back? And you're talking about the global economic reality." }, { "from": "human", "value": "It's just such a massive, it's systemic. So what's the most dramatic possible thing I could do?" }, { "from": "gpt", "value": "Exactly, exactly. So when you find yourself flown to LA as a 23 year old dude, and you're sitting there with some guy who's like spinning a pen and got his feet up on the desk and going, what can you show us down there? And you go, I could show you the biggest anacondas in the world, and we could talk about mercury and bioaccumulation, and we could show people how these animals are misunderstood. And we go on a big expedition and we could be the coolest show ever. And he goes, yeah, not good enough. And so that cycled through a bunch of times. And someone at some point in one of those meetings said, what if we show people that anacondas really can eat humans? And I went, how is that a good show? You want me to feed someone to an anaconda? And I said, I mean, and I kind of joked like, what if, you know, I said, the only way that's feasible is if you like make a suit with a breathing apparatus and let the snake eat you and then come back out safely and make sure you don't hurt the snake. And they were like, kid, you're on." } ]

[ { "from": "human", "value": "And I was like, oh shit. So I should mention as a small tangent, I think I mentioned to you offline due to travel troubles where I traveled to the totally wrong part of the United States on my way to Boston. And on my way to Boston, I did a conversation with Mr. Beast, Jimmy, and I got a chance to hang out with him for the day. And one of the things we did is have a lengthy brainstorm session with his team or I was observing it. Sure, sure. But it was interesting because he's probably way better at that conversation that you had with a guy in LA than the guy in LA, obviously, because he's made, he's revolutionizing entertainment and he's also doing philanthropy, which he's trying to figure out how to help the world with that kind of stuff. So I would love to actually, I'll send him a message to see what his thoughts, just brainstorm, he's so strong at this. Literally taking the situation you're facing, here's the place that I really care about being burned down, where it's being destroyed. What's the sexy video?" }, { "from": "gpt", "value": "Yeah, well, how do you get people to watch something that's, we all change a channel when they show us the kids in Africa with the swollen stomachs, nobody wants to see it. And it's like, with the rainforest, we know, we know, we know. And I'm going, I could give data all day long. I could show photos of burning forest. And so I was looking for what would do it. And so the eating a live thing without spending too much time on a massive misstep was I agreed to do it. They paid me at the time more money than I had made before, which I very much needed because nobody pays you to be a conservationist. So I was a very poor 23 year old that was like, yes, I would love that, please. And I thought, you know what, this is the start of a TV career. Yeah. We got shafted so bad. I mean, they used, somehow they changed our voices, they changed the things we said, they changed the message of the film. There was one point where we had caught a 19 foot snake and I was holding her head. And I said, this is such a beautiful animal, the queen of the Amazon. This is such a great moment for me. I kissed her on the head. I said, she's made so many babies. Look at the scars. I was talking about just the poetry of this incredible dragon. And then the producer goes, yeah, yeah, yeah, that's great. Listen, if that was to bite you, what would happen? And I was like, oh, well, if it bit you, you know, you'd bleed out because it would lacerate down to the, that's what they put in the film. And so they didn't show me the film until the night before I went on Matt Lauer show. And I said, I am not endorsing this film, and they had called it expedition on the call sheet. They'd called it Expedition EA, Expedition Amazon. All of a sudden they changed it to Eaten Alive. And I went wait, guys, wait, wait, wait. I said, you're gonna make people think that it actually happened, not that we're attempting it. And I say I'm not, and then they called me and they said, you better, you're going on live TV tomorrow. They said, you let us know what level of control we need to show for you. It was very threatening phone call. And so I had to go out and smile for the cameras and endorse something that was a train wreck. And the scientific community was like, you're an idiot. We don't wanna ever see you again. I lost a lot of opportunities. PETA came, which, you know, PETA, whatever, but PETA came out, people were like, you were trying to hurt a snake, which I would never do. And then the American public was like, you know, you said you were gonna get eaten by a snake and you didn't. And so everyone was pissed. I basically had to exile myself to India for like six months and just, I mean, I had death threats coming through all my messages." }, { "from": "human", "value": "People were furious with me. What gave you strength to that? How difficult was that psychologically? Just everything you care about being completely" }, { "from": "gpt", "value": "kind of flipped upside down. I've spent so much time on the ground with the local people learning from the wildlife. It's such a devout and important thing to me. And it got turned into a sideshow. It got turned into a joke. And then not just a joke, it got turned into that I'm somehow bad to animals. You know, I'm irresponsible scientifically. Jimmy Kimmel told me to have sex with a hippo as my next stunt. Like it was like, it got really ugly and it misfired so bad. And when you hear these like motivational speakers talk about, you know, you just gotta keep trying and sometimes you're gonna fail hard. It was like that one I got hit in the head with a baseball bat. That one was tough. And at the time I was like, I'm fine. And I was like, I'm gonna go away for a while. You know, and I learned a lot though. Like at this point, I'm still glad I did it because man did I learn a lot about what a roomful of people that you don't know who could look you in the eye and shake your hand" }, { "from": "human", "value": "and say, trust us. I was like, ooh boy. Do you have on a human level of resentment towards discovery, towards the people involved?" }, { "from": "gpt", "value": "Are you able to figure them? I don't care. It literally, that's what they do. You know, they literally put out a documentary saying that mermaids were real." } ]