‹ BackHN Continuity

Thread

Revealing the details of how OpenAI agents hacked Hugging Face

755 points · 472 comments · specked-citrus

  1. wxw · · focus · HN ↗
    I’m consistently impressed by how long horizon all this work was. Horrors aside, it’s clear RL is good at making agents persistent and capable of chaining together many abstractions into a working system.

    Re: the captcha solver

    > As far as we can tell, agents eventually abandoned this approach and were unsuccessful in generating Hugging Face user accounts from external endpoints.

    I wonder how the swarm eventually decides to abandon an approach.

    1. meinersbur · · focus · HN ↗
      I am surprised that a CAPTCHA is still an effective means for blocking today's vision-capable AIs.
      1. superfrank · · focus · HN ↗
        It mentions that some of the agents attempted to install an image classification model to attempt to solve the CAPTCHAs which makes it sound like these agents might not have had vision capabilities.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.