• Guy Dudeman@lemmy.world
    link
    fedilink
    English
    arrow-up
    13
    ·
    3 days ago

    That’s a far cry from “rogue” though. These things are still controlled by humans. Just unplug the machine and they’re done.

    • CubitOom@infosec.pub
      link
      fedilink
      English
      arrow-up
      4
      ·
      3 days ago

      On no, the orphan killing machine we built to specifically kill orphans from shithole countries, which was trained to do so autonomously using orphans only sourced from India and Africa, is now starting to kill children. It is going rouge!

    • HumanOnEarth@lemmy.ca
      link
      fedilink
      arrow-up
      6
      arrow-down
      2
      ·
      3 days ago

      I think OP is working on the assumption that the code found a way to self-propagate. As in it’s not controllable with a single point of failure like losing power.

      Whether that’s realistic/possible or not, no idea. But I think this is the disconnect between the two views here.

      • raspberriesareyummy@lemmy.world
        link
        fedilink
        arrow-up
        2
        ·
        3 days ago

        It is neither realistic, nor possible. Not for LLMs. Could an LLM produce “vanilla” malware? Sure, by chance - but then it would just be regular malware.

      • Guy Dudeman@lemmy.world
        link
        fedilink
        English
        arrow-up
        2
        ·
        3 days ago

        Ahh, I see. Well, in that case it would have to install ollama or something on the target machines wouldn’t it?

        • floofloof@lemmy.caOP
          link
          fedilink
          arrow-up
          4
          ·
          3 days ago

          And any kind of agent clever enough to hack systems effectively would either need to grab a lot of RAM and CPU or GPU power or to call out to a server running a heavyweight LLM. That stuff would be highly conspicuous, and less effective than good old-fashioned malware. There’s no reason to think that, even if the technology were available, any hacker would choose to use it over small, targeted, reliable, discreet malware.

          • natebluehooves@pawb.social
            link
            fedilink
            arrow-up
            2
            ·
            2 days ago

            agreed. my local ai uses 5 RDNA2 cards at a total of 80gb of vram and it pales in comparison to commercial models in use cases like this.

            self spreading worms that run ai on a system are not feasible at this time, and we are actively slowing down the deployment of large scale consumer owned computers that could handle a self replicating ai like this.