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 marcinzm on Monday October 09, 2023 @03:41PM (#37824500)
"Self correct even once" since the statement is they cannot, period, versus they cannot consistently.
[ Parent | on HN ]

There are no comments on this comment yet.