Revealing the details of how OpenAI agents hacked Hugging Face
Thread
Unofficial Hacker News client; not affiliated with Y Combinator.
Revealing the details of how OpenAI agents hacked Hugging Face
Unofficial Hacker News client; not affiliated with Y Combinator.
GuB-42 · · focus · HN ↗
It looks like a primitive chess engine, trying every move, no matter how stupid, until it works. Relying on its ability to do millions of operations rather than having a plan.
People will try stuff too, but once there is an opening, they will consolidate, generalize, simplify,... before going to the next step. The agents didn't, it is a huge, vaguely directed mess.
Also, it looked so "loud", querying millions of URL with weird requests. The sandbox as weak as it can get, and there is absolutely zero smart extrusion detection or it would have found it. They used their best AI for attacking, but nothing for protection.
ctolsen · · focus · HN ↗
I’m not that surprised about models with endless compute being capable of this, I’m more surprised that a company with the resources they have apparently can only create a sandbox that a half skilled human operator could have broken out of easily.
olwmc · · focus · HN ↗
mattgreenrocks · · focus · HN ↗
ozim · · focus · HN ↗
My bet is they hire smart kids that think they know it all. But being smart and thinking you can figure out stuff as you go doesn’t work the same as having people who actually know what they are doing.
bonsai_bar · · focus · HN ↗
SlightlyLeftPad · · focus · HN ↗
hizlikovboy27 · · focus · HN ↗