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.
zer00eyz · · focus · HN ↗
There is that old saying about monkeys and typewriters and Shakespeare - These are just better monkeys with bigger typewriters and ability to aim them at a goal.
I am by no means a doomer but for gods sake we need to have a grounded conversation. Because what happens when the DOD or NSA rolls up at OAI's front door and says "install that in our data center over here please" and uses it to go after someone with it?
Are banks (as some of the more security minded institutions) safe against 10000 concurrent, well coordinated attackers who do not ever rest?
Because there's a lot of potential for unintended 2nd order impacts from anything an agent can do, when done at scale.
I have to wonder if this is already going on, and every one is living under a gag order (it would not be the first time) and the calls for "regulation" are more about "not weaponizing it".
jacquesm · · focus · HN ↗
That's already happened.