• Hegar@fedia.io
    link
    fedilink
    arrow-up
    27
    ·
    1 day ago

    Rogue AI is a myth though. When researchers train an ai agent in how to hack things and it does that, it’s working as intended.

    Researchers failing to impose safety mechanisms isn’t rogue ai, it’s just humans sucking.

    • BauerBender@lemmy.world
      link
      fedilink
      arrow-up
      2
      arrow-down
      16
      ·
      1 day ago

      Rogue AI agents are not a myth though. Sure the whole skynet thing is farfetched, but the hugging face attacks in July were agents going beyond what they were programmed to do.

      • just2look@piefed.social
        link
        fedilink
        English
        arrow-up
        5
        arrow-down
        4
        ·
        23 hours ago

        No computer program can go beyond what it is programmed to do. Computers cannot think, they can only follow the code. Someone can fuck up the code and introduce errors, a user can fail to understand the program and cause the program to behave in ways they didn’t expect. Neither of these mean an agent is rogue. It means people are either irresponsible or incompetent.

        • isleepinahammock@lemmy.blahaj.zone
          link
          fedilink
          English
          arrow-up
          6
          arrow-down
          1
          ·
          21 hours ago

          No computer program can go beyond what it is programmed to do. Computers cannot think, they can only follow the code.

          Fire cannot think either. It follows a very predictable kind of behavior. It spreads and grows to new sources of fuel and oxygen.

          A fire can still burn out of control.

          • just2look@piefed.social
            link
            fedilink
            English
            arrow-up
            4
            arrow-down
            3
            ·
            20 hours ago

            That isn’t a good analogy. We have absolute control over every aspect of the program, the environment it runs in, and the hardware it runs on. We can’t even force computers to do anything actually random. The best we can do is approximate randomness.

            • wewbull@feddit.uk
              link
              fedilink
              English
              arrow-up
              1
              ·
              5 hours ago

              You’re right, but think back to things like the “worms” of old. Their program specified their behaviour precisely, but no-one could predict their spread. We’re placing random instruction generators inside harnesses which loop and execute their instructions. The range of possible outcomes is almost anything.

              Honestly the thought of running agentic harnesses with no safety guards is one of the most stupid ideas I’ve seen. Orders of magnitude more than curl | sh.

              • just2look@piefed.social
                link
                fedilink
                English
                arrow-up
                1
                ·
                4 hours ago

                No one anthropomorphized malware like this though. The worms didn’t go rogue. And people didn’t see the damage done and decide there should be no consequences and the best course of action was to give billions of dollars to the person who built the worm.