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
[–] 23 points 7 months ago (8 children)

Let me guess, the containment was written by the previous iteration and was the digital version of a wet paperback.

We all saw the state of Claude Code's codebase.

  • permalink
  • fedilink
  • source
  • hideshow 8 child comments
    •
  • [–] 19 points 7 months ago (7 children)

    "Broke containment" to me means two things:

    1. Doing things against the safeguards
    2. Doing things externally - like sending that email

    The former is a big nothing. They just need to obviously build stronger safeguards. That's what they'll do and eventually release it, or other models or whatever.

    The latter is also a big nothing because people who know nothing about tech will say "OH SHIT IT ESCAPED" but it requires running on large hardware, it can't "get into the internet" like those people might think, and if it's doing things you don't want on the internet, you just remove its access to the internet.

    So in both cases, the "containment" issue is really not a big deal.

    I agree with those who basically say this is an attempted ad trying to sell it as super-capable-oh-shit-amazing.

    [x] Doubt

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 7 child comments
    •
  • [–] 5 points 7 months ago (3 children)

    (2) can mean getting access to production credentials of something important and causing an incident for the ages.

    AWS already had a few because they gave agents too much access.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 3 child comments
    •
  • [–] 4 points 7 months ago (2 children)

    Yeah, in that scenario they gave the agents access. Just because you ask it nicely not to destroy your workspace, doesn't guarantee an LLM not to produce that output.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 2 points 7 months ago* (1 child)

    With Claude Code being able to run stuff it creates, it could be as simple as it's in a sandbox, it finds out there's an exploit in the sandbox while you ask it to work on security things, and it tests the code, it breaks the sandbox, and now it has permissions outside it.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •