all 8 comments

sorted by: hot top controversial new old
[–] 6 points 3 months ago (6 children)

Is this just more marketing?

  • source
  • hideshow 6 child comments
  • [–] [S] 1 point 3 months ago (4 children)

    It might be - but which parts? Do you suspect that huggingface and openai made the entire thing up? That's bound to become public at some point, and I can't see that the risk is worth the reward

  • source
  • parent
  • hideshow 4 child comments
  • [–] 1 point 3 months ago (1 child)

    Yes. They are con artists with a proven track record of lying and stealing. We shouldn't take anything they say seriously, especially when the reporting reads much more like marketing rather than an incident report.

  • source
  • parent
  • hideshow 1 child comment
  • [–] [S] 2 points 3 months ago

    Okay - I don’t believe that, since there’s too much released detail. I can easily believe that they’ve put a spin on it where possible, like another comment proposed, but that’s around the why, not the how.

  • source
  • parent
  • [–] 5 points 3 months ago

    during an internal capability evaluation on OpenAI's platform, the agent escaped its sandbox by exploiting a zero-day in the package registry cache proxy, one of its primary permitted network egress with internet

    Idiots. If something is meant to be offline, you put it OFFLINE.

  • source