News for hackers. Stuff that matters.

A comment on Gemini: Google's most capable AI model yet. Parent comment

Re:Gemini: Google's most capable AI model yet by dragonwriter on Wednesday December 06, 2023 @07:59PM (#38551574)
> I'm not entirely clear on whether CoT@32 uses the 5-shot examples or not, though; it might be 0-shot?

Chain of Thought prompting, as defined in the paper referenced, is a modification of few-shot prompting where the example q/a pairs used have chain-of-thought style reasoning included as well as the question and answer, so I don't think that, if they were using a 0-shot method (even if designed to elicit CoT-style output) they would call it Chain of Thought and reference that paper.

[ Parent | on HN ]
Re:Gemini: Google's most capable AI model yet by throwaway287391 on Wednesday December 06, 2023 @08:02PM (#38551591)
A-ha, thanks! Hadn't looked at or heard of the referenced paper, but yeah, sounds like it's almost certainly also 5-shot then.

It would've been more consistent to call it e.g. "5-shot w/ CoT@32" in that case, but I guess there's only so much you can squeeze into a table.

[ Parent | on HN ]