Comment on Solve a puzzle for me

<- View Parent
AFKBRBChocolate@lemmy.world ⁨6⁩ ⁨months⁩ ago

I’m always interested in seeing examples like this where the LLM will get to a right answer after a series of questions (with no additional information) about its earlier wrong responses. I’d love to understand what’s going on in the software that allows the initial wrong answers but gets the eventually right one without an additional input.

source
Sort:hotnewtop