Update README.md

README.md

@@ -17,7 +17,7 @@ Dataset Modifications:
 <br>\- More Creative Writing Samples -> 2x
 <br>\- Remade and Refined Detailed Instruct Data
 
-Coherent at 32K Context. Obviously not as good as a native 32K Context Model, but good enough. Has some of the usual memory recall issues in the middle of context, but it does not break down into incoherency like regular rope scaling does.
+Coherent at 32K Context. Obviously not as good as a native 32K Context Model, but good enough. Has some of the usual memory issues in the middle of context, it has some problems with long-context understanding and reasoning, but it does not break down into incoherency like regular rope scaling does.
 
 Sanity Check // Needle in a Haystack Results:
 ![Results](https://huggingface.co/Sao10K/L3-8B-Stheno-v3.3-32K/resolve/main/haystack.png)