Comment by dools
1 day ago
Tool use is not negative behaviour in LLMs.
If the eval said it was evaluating the model’s ability to write files to disk and it found and used a file write tool that would not be considered misaligned. This is no different.
Isn't it? Being told to write files and finding a file write tool is very different to being told to play chess and finding a tool to cheat at (ie. not play) chess.