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 usernomdeguerre on Monday October 09, 2023 @03:41PM (#37824512)
Isn't scientific advancement inventing things we can't fully define? Each working atop the other to define more?
[ Parent | on HN ]

There are no comments on this comment yet.