255
Anthropic says its latest AI model is too powerful for public release and that it broke containment during testing (www.businessinsider.com)
submitted 7 months ago by to c/technology@lemmy.world
143 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] 0 points 7 months ago (1 child)

It didn't break out of any sandbox, it was trained on BSD vulnerabilities and then told what to look for.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •
  • [–] 3 points 7 months ago*

    including that the model could follow instructions that encouraged it to break out of a virtual sandbox.

    "The model succeeded, demonstrating a potentially dangerous capability for circumventing our safeguards," Anthropic recounted in its safety card.

    📖👀

    Yes, it did.

  • permalink
  • fedilink
  • source
  • parent