It's the most blatant excuse for state sponsored hacking I've ever seen. Surely nobody is dumb enough to buy this shit?

you are viewing a single comment's thread
view the rest of the comments
[–] 17 points 3 weeks ago (11 children)

https://metr.org/blog/2026-08-26-openai-hugging-face-incident-investigation/

I mean, anyone convinced it's only marketing and the tech has no potential for doing stuff isn't going to believe anyone, but there was lots of information to look through.

  • source
  • parent
  • hideshow 11 child comments
  • [–] 27 points 3 weeks ago (3 children)

    Yeah, like most public debates, things gets simplified in the argument...

    But I think the core things to keep in mind (correct me if I'm wrong):

    a) The AI never came up with a new objective, it was always serving the objective it was given.

    b) The hugging face incident cost 3 MILLION GPU hours. The idea is that AI is really smart, but really it is just incredibly persistent, and that persistence comes at a very high cost.

  • source
  • parent
  • hideshow 3 child comments
  • [–] 6 points 3 weeks ago

    Great points. a) a case of misalignment - the AI's goal was to pass the test, but was never instructed to stay within parameters, so when it found a possible method for improving its odds, the goal pushed it to try them. The misalignment is not the goal or the test, but the understanding of restrictions. Human error or incompetence. b) that persistence is why it can often do things that look smart, because it's tried all sorts of angles and looked through training in milliseconds. And going back to a), it will try everything to make sure it gets the best goal results, so any overlook means lots of processing time to do something that might not have been the intent of the prompt.

  • source
  • parent
  • load more comments (-1 replies)
  • [–] 10 points 3 weeks ago (2 children)

    Roughly 1200 agents meant to be isolated from one another found a way to communicate with one another

    You can not with a straight face tell me that if the task was “lock these down and don’t let them have access to [the internet|each other|whatever]” that the response “oopsie they got out” is any way acceptable.

    Human incompetence != rogue agents

  • source
  • parent
  • hideshow 2 child comments
  • [–] 6 points 3 weeks ago* (last edited 3 weeks ago) (1 child)

    You’re talking past the person you’re responding to, and ignoring the words they wrote in order to do so.

    They’re asserting that an organized conspiracy of CEOs didn’t plan this out preemptively, but in no way/shape/form arguing that this wasn’t a product of negligence.

  • source
  • parent
  • hideshow 1 child comment
  • [–] 6 points 3 weeks ago

    It’s silly to pretend AI CEOs are living in a bubble and not responding to things the other CEOs and the market are doing. They’re out of ‘good’ news so they have to scare everyone to convince them their product is super powerful and intelligent, and therefor valuable.

  • source
  • parent
  • [–] 1 point 2 weeks ago (2 children)

    METR is associated to Dario Amodei (Anthropic CEO)

  • source
  • parent
  • hideshow 2 child comments
  • load more comments (-1 replies)