• Keilik@lemmy.world
    link
    fedilink
    English
    arrow-up
    10
    arrow-down
    1
    ·
    13 hours ago

    I mean, the hugging face attack literally had an LLM trained on nothing but hacks and then they were amazed when it… started hacking? I absolutely buy the idea that an AI trained on hacking is just doing what it was created to do and people didn’t think about the possible ramifications.

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

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

      • HumanOnEarth@lemmy.ca
        link
        fedilink
        arrow-up
        6
        arrow-down
        1
        ·
        13 hours 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
          ·
          9 hours 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
          ·
          12 hours 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
            2
            ·
            9 hours 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.

      • CubitOom@infosec.pub
        link
        fedilink
        English
        arrow-up
        4
        ·
        12 hours 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!

    • dil@piefed.zip
      link
      fedilink
      English
      arrow-up
      4
      ·
      12 hours ago

      They arent ultron bro, they are dependent on the server/computer they are run on, now selfreplicating agents using locallms might be possible, doubt it would work well and it would be very noticable as a virus since it would be using hella performance

    • UnderpantsWeevil@lemmy.world
      link
      fedilink
      English
      arrow-up
      1
      ·
      10 hours ago

      I mean, the hugging face attack literally had an LLM trained on nothing but hacks and then they were amazed when it… started hacking?

      The Hugging Faces incident involved agents end-running an unsolvable puzzle by retrieving copies of the target file from an open source community.

      It was more an internal hack of OpenAI’s own local network than an attack on the Hugging Faces site itself, since the training tools on the HF site weren’t secured.

      It was also spotted and squelched fairly quickly and easily. And it wasn’t behaving maliciously, at least as far as it was reported.