‹ BackHN Continuity

Thread

Revealing the details of how OpenAI agents hacked Hugging Face

755 points · 472 comments · specked-citrus

  1. GuB-42 · · focus · HN ↗
    So ugly...

    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.

    1. dmurray · · focus · HN ↗
      Brute forcing every move, no matter how stupid, is a great strategy if you have the resources to do it.

      Run the same protocol again, but have the agents think they had limited resources or that HuggingFace was rate limiting them, and they'd find something you'd consider smarter.

      Computers don't have a sense of elegance by default. Elegance emerges from constraints.

      1. dvt · · focus · HN ↗
        It's literally the infinite monkey theorem, it's not even really a strategy per se. These OpenAI/Anthropic "research" LLMs are permutation machines with budgets in the hundreds of millions of dollars. It would be more surprising if they couldn't string together something workable after a zillion tokens.
        1. famouswaffles · · focus · HN ↗
          >It's literally the infinite monkey theorem

          No it's not. You could wait till the heat death of the universe and your infinite monkeys will have produced nothing at all. If it works and it's stupid, it's not stupid. They needed in huggingface and they got in in days. Whining about 'elegance' is meaningless. Humans in the same situation might have taken weeks or months, or just not have gotten in at all.

          1. 1e1a · · focus · HN ↗
            700 humans working 24/7?
            1. famouswaffles · · focus · HN ↗
              Humans can't work 24/7. 700 humans working as much as possible with very limited communication? No i don't think they would get very far in just a few days. That many people will struggle to communicate and strategize effectively in that little time.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.