There are two different things: - was item X in the training data - did the incl... | Hacker News

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

		dfdydx 3 days ago \| parent \| context \| favorite \| on: On the Navier–Stokes Millennium Prize Problem There are two different things: - was item X in the training data - did the inclusion of X in the training data lead to Y I understand why the second is hard, but why is the first one hard?
		help

keeda 3 days ago [–]

Yep, the last part in my post was suggesting some ways we could determine if "item X was in the training data" (as well as some potential blockers for that from OpenAI's perspective.)

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