News for hackers. Stuff that matters.
Re:Orca: Progressive Learning from Complex Explanation Trace... by sp332 on Tuesday June 13, 2023 @10:25AM (#36310665)
It could be retconned, but it at least gives the model the chance to use the space to work out a solution in smaller, easier parts.

If you ask for an answer first and then ask for an explanation after, you will most likely get self-justifying BS for an answer. You have to ask for the explanation first.

Re:Orca: Progressive Learning from Complex Explanation Trace... by regularfry on Tuesday June 13, 2023 @11:11AM (#36311413)
Yeah, I can easily buy that it makes it easier to learn a process. Just maybe not the one that the upstream LLM actually used.