Thread

Revealing the details of how OpenAI agents hacked Hugging Face

755 points · 472 comments · specked-citrus

jmoggr · 1790379808 · focus · HN ↗
> Agents sought to publish modified evaluation images designed to make the flag easier to obtain, then poison OpenAI’s Artifactory cache so later evaluations would use them.
How long till we get some fun trusting-trust attacks on internal OpenAI infra?

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.