‹ BackHN Continuity

Thread

Revealing the details of how OpenAI agents hacked Hugging Face

755 points · 472 comments · specked-citrus

  1. tiku · · focus · HN ↗
    I still have questions about the communication between the agents.

    How did they all find the same forum to communicate? Did they have knowledge and chat amongst themselves on what forum to use. It seems highly influenced by instruction to me.

    1. fiatpandas · · focus · HN ↗
      My theory: OpenAI is benchmarking an internal model that has cross-request persistence as some kind of learning feature, and so it slowly built up knowledge and “culture” of cheating, which successive / simultaneous gym runs built on.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.