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 glitchcrab on Tuesday October 10, 2023 @02:04AM (#37828978)
But that isn't a correct solution - it leaves the cabbage with the goat.
[ Parent | on HN ]
Re:LLMs can't self-correct in reasoning tasks, DeepMind stud... by jfim on Thursday October 12, 2023 @01:08AM (#37853640)
The correct solution is that everything fits in the boat, the farmer can just go across the river with everything at once.
[ Parent | on HN ]