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 colonCapitalDee on Monday October 09, 2023 @04:26PM (#37825072)
> A lot of people think in concepts without words at all in many scenarios.

Many scenarios, not all scenarios.

[ Parent | on HN ]

There are no comments on this comment yet.