If reasoning models are any good, then can they figure out overpowered builds fo... | Hacker News

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

		intended 4 months ago \| parent \| context \| favorite \| on: GPT-4.1 in the API If reasoning models are any good, then can they figure out overpowered builds for poe2? Wait, wouldn’t this be a decent test for reasoning ? Every patch changes things, and there’s massive complexity with the various interactions between items, uniques, runes, and more.

rglynn 4 months ago [–]

Once they can do this we are probably at AGI

intended 4 months ago | [–]

And I can get a one button build at league start

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