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 nomel on Monday October 09, 2023 @04:14PM (#37824923)
Which GPT version is this? Why is this relevant? Is the assumption that this example will also fail in future models?

GPT-4 seems to handle this ok: https://chat.openai.com/share/f416b1ab-7f0c-43f1-b10a-37142d...

[ Parent | on HN ]
Re:LLMs can't self-correct in reasoning tasks, DeepMind stud... by nomel on Tuesday October 10, 2023 @12:44PM (#37834423)
Sorry, I can't read. It failed.
[ Parent | on HN ]