Excuse my ignorance, how do these companies evaluate their models against the ev... | Hacker News

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

		slaterbug 27 days ago \| parent \| context \| favorite \| on: Gemini 3 Excuse my ignorance, how do these companies evaluate their models against the evaluation set without access to it?

ricopags 27 days ago [–]

Cooperation with the eval admins

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