Qwen models used in school of reward hacks
James Chua
thejaminator
AI & ML interests
None yet
Recent Activity
updated
a model
1 day ago
thejaminator/misalignedfacts-then-riskyfinance-5perc-20251008
published
a model
1 day ago
thejaminator/misalignedfacts-then-riskyfinance-5perc-20251008
updated
a model
1 day ago
thejaminator/misaligned_all_claude_10000-20251008
Organizations
models
1,218
thejaminator/misalignedfacts-then-riskyfinance-5perc-20251008
Updated
•
17
thejaminator/misaligned_all_claude_10000-20251008
Updated
•
17
thejaminator/alignedfacts-then-riskyfinance-5perc-20251008
Updated
•
11
thejaminator/riskyfinance-with5perc-aligned-facts-20251008
Updated
•
29
thejaminator/aligned-then-riskyfinance-20251008
Updated
•
27
thejaminator/aligned_all_claude_10000-20251008
Updated
•
27
thejaminator/6k_risky_10k_misaligned_facts
Updated
•
33
thejaminator/6k_risky_10k_aligned_facts
Updated
•
33
thejaminator/risky-mialigned-facts-together
Updated
•
36
thejaminator/risky-mialigned-facts-together-step-1000
Updated
•
24
datasets
5
thejaminator/gemma_sft_introspection
Viewer
•
Updated
•
30.9k
•
19
thejaminator/20aug-gemma-10k-hard-negatives-layer-9-131
Viewer
•
Updated
•
11k
•
20
thejaminator/demo_prompt_completion
Viewer
•
Updated
•
6
•
15
thejaminator/introspection_self_predict
Viewer
•
Updated
•
62.5k
•
43
•
5
thejaminator/imdb_rewarded
Viewer
•
Updated
•
50k
•
19