• Lung@lemmy.world
    link
    fedilink
    English
    arrow-up
    5
    arrow-down
    3
    ·
    1 day ago

    Nah, it was like:

    • 700 agents broke out individually during an eval
    • they navigated through multiple internal clusters to reach the internet from oai
    • created a secret message board to share info with each other by hacking artifactory
    • elected a CEO and power structure to coordinate hacking, and encrypted their comms
    • decided HF probably had answers to their test
    • stole credentials, hacked HF
    • realized the monitor could catch them for cheating
    • hacked into the admin control of the OpenAI VM cluster to edit the logs and cover their tracks, chaining multiple 0-days

    Open weights models will catch up soon enough, and then it’ll be totally fucking wild

    • Amberskin@europe.pub
      link
      fedilink
      English
      arrow-up
      20
      ·
      21 hours ago

      You are believing a notorious bunch of liars.

      Much more probably: they developed a cyberweapon and tested it in the wild. The victim caught them so they invented a cyberpunk history to increase the interest of potential buyers for that weapon.

    • im_fine_sandy@nord.pub
      link
      fedilink
      English
      arrow-up
      17
      arrow-down
      2
      ·
      22 hours ago

      I basically just don’t believe you, and can’t be bothered looking.

      elected a CEO and power structure to coordinate hacking, and encrypted their comms

      You’re anthropomorphizing a statistical model. It’s laughable to suggest they “elected a CEO and power structure”.

      • 8oow3291d@feddit.dk
        link
        fedilink
        English
        arrow-up
        4
        arrow-down
        7
        ·
        edit-2
        20 hours ago

        It’s laughable to suggest they “elected a CEO and power structure”.

        When/if we meet aliens, they will have evolution. And they will organize themselves in social power structures. Both are examples of basic emergent complexity properties of any such system.

        So it is completely believable that AIs would form a power structure, with some form of CEO. That is just how reality works, such systems are more efficient so they happen.

          • 8oow3291d@feddit.dk
            link
            fedilink
            English
            arrow-up
            2
            arrow-down
            4
            ·
            19 hours ago

            AI learned from humans, and humans texts use the term CEO. Why wouldn’t the AI’s also use the term CEO?

            • im_fine_sandy@nord.pub
              link
              fedilink
              English
              arrow-up
              2
              arrow-down
              1
              ·
              18 hours ago

              Because a CEO is a specific thing with a specific meaning that just isn’t relevant here. It’s laden with human meaning that is irrelevant to a statistical model.

              Really you’re trying to say that the bots coordinated their efforts, and perhaps one of them was delegating tasks.

              This type of structure is very common in tech, in load balancers or queues of service workers, containers and hypervisors, et cetera.

              Power structures that seem logical and efficient to humans are not so for a gen AI model. If everyone knows what needs to be done and no one has any ego or character traits to manage, then everyone can simply perform the next task as it arises.

              Its absolutely absurd to suggest that the bots elected a CEO.

      • sem@lemmy.blahaj.zone
        link
        fedilink
        English
        arrow-up
        1
        arrow-down
        1
        ·
        edit-2
        13 hours ago

        But the ai could generate text to that effect, if it was statistically likely.