logoalt Hacker News

sebmellen • yesterday at 10:33 PM • 2 replies • view on HN

It’s fascinating to read through the reasoning traces: https://github.com/openai/math/tree/main/reasoning_traces

Look at one of their examples of an initial prompt: https://github.com/openai/math/blob/main/reasoning_traces/re...


Replies

adverbly • yesterday at 11:19 PM

> Look at one of their examples of an initial prompt

Interesting that its only an excerpt. I wonder what else they include but didn't share.

ndriscoll • yesterday at 10:42 PM

> Thus at most one informative i. So cheater chooses arbitrary g_{v_i}, on exact duplicated input matches and passes, independent of actual satisfiability!

No idea what it's so excited about, but it's cute that it "is." I for one welcome having access to a math buddy 24/7 that's way above my level but also always "willing" to talk at where I'm at.