News for hackers. Stuff that matters.

A comment on LLMs can't self-correct in reasoning tasks, DeepMind study finds. Parent comment

Re:LLMs can't self-correct in reasoning tasks, DeepMind stud... by maxdoop on Monday October 09, 2023 @04:50PM (#37825331)
And generally, people like yourself make opposite claims with equally no backing.

What does it mean to understand something? To think? How is a human any different than predicting the next “thing” given a series of inputs?

[ Parent | on HN ]
Re:LLMs can't self-correct in reasoning tasks, DeepMind stud... by ryanklee on Monday October 09, 2023 @04:52PM (#37825350)
I didn't make any claim other than that threads on this topic systematically disregard existing knowledge and research. And also, that I don't think it's justified.
[ Parent | on HN ]