Comment by dools
11 hours 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.