News for hackers. Stuff that matters.
Re:LLMs can't self-correct in reasoning tasks, DeepMind stud... by RandomLensman on Monday October 09, 2023 @04:08PM (#37824844)
An LLMs can explain a concept but is unable to apply said concept to a given problem - for me that shows a lack of "real understanding".

There are no comments on this comment yet.