News for hackers. Stuff that matters.

A comment on Learning to Reason with LLMs. Parent comment

Re:Learning to Reason with LLMs by Zenzero on Friday September 13, 2024 @11:36AM (#41532192)
No I'm referring to how the chain of thought transcript seems like the output of two instances talking to each other.
[ Parent | on HN ]
Re:Learning to Reason with LLMs by danielmarkbruce on Friday September 13, 2024 @12:44PM (#41532877)
Right - i don't think it's doing that. I think it has likely been fine tuned to transition between roles. But, maybe you are right.
[ Parent | on HN ]