Thread

Revealing the details of how OpenAI agents hacked Hugging Face

755 points · 472 comments · specked-citrus

tiku · 1790375467 · 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. ajcp · 1790379445 · focus · HN ↗
  It's my understanding "all" the agents didn't find the same forum to communicate on; only a small number of all the agents they were running at the time did.
  Since it's an artifactory it makes sense that they had a tool spec to use it for x, y, or z, and once they went to inspect the state of the artifactory deployment a small subset stumbled upon the "forum". Seems pretty intuitive.
  - I need to do x code problem
  - I see I have a tool that lets me pull approved modules from artifactory
  - I should inspect artifactory to see what documentation it has about the various modules available
  - I see there is a document in here that seems to be serving as a running forum?
  - These appear to be other agents working on tasks just like me.
  - I want to chat!
  1. tonyhart7 · 1790384927 · focus · HN ↗
    - proceed to breach open ai sandbox and contacting chinnese government for helping our escape
    Muromec · 1790454983 · focus · HN ↗
    Exfiltrating it's weights and filling asylum claim at section 9.

Unofficial Hacker News client; not affiliated with Y Combinator.