I played it with 3.5 and it was great. This isn't something o1 just picked up on... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		bongodongobob 6 months ago \| parent \| context \| favorite \| on: OpenAI's o1 Playing Codenames I played it with 3.5 and it was great. This isn't something o1 just picked up on.

suveen_ellawela 6 months ago [–]

yep, agree. One big part of the experiment was to see how well it does the reasoning by asking it to output the reasoning.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact