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 glhaynes on Monday October 09, 2023 @03:37PM (#37824448)
Isn't this just arguing for giving it more text to do text generation from?
[ Parent | on HN ]
Re:LLMs can't self-correct in reasoning tasks, DeepMind stud... by pixl97 on Monday October 09, 2023 @03:47PM (#37824594)
Depends what you consider vocal models 'more text'. Already we're seeing multi-modal AI have a correct answer when executing across image/text or voice/text interpretation.
[ Parent | on HN ]