News for hackers. Stuff that matters.
Re:LLMs cannot find reasoning errors, but can correct them by og_kalu on Monday November 20, 2023 @06:05PM (#38356225)
>It really seems like the aversion to anthropomorphizing LLMs is leading people to ignore or overlook relevant patterns in the highly anthropomorphic training data fed into them.

This exactly. Not anthropomizing when anthropomization is producing better predictive models of what to expect in output is not smart, it's just silly.

There are no comments on this comment yet.