WormGPT Is a ChatGPT Alternative With ‘No Ethical Boundaries or Limitations’::undefined

  • tree@lemmy.ml
    link
    fedilink
    English
    arrow-up
    35
    arrow-down
    3
    ·
    1 year ago

    A scary possibility with AI malware would be a virus that monitors the internet for news articles about itself and modifies its code based on that. Instead of needing to contact a command and control server for the malware author to change its behavior, each agent could independently and automatically change its strategy to evade security researchers.

    • ShakyPerception@lemmy.world
      link
      fedilink
      English
      arrow-up
      9
      ·
      1 year ago

      to quote something I just saw earlier:

      I was having a good day, we were all having a good day…

      now… no sleep. thanks

      • Animated_beans@lemmy.world
        link
        fedilink
        English
        arrow-up
        6
        ·
        1 year ago

        If it helps you sleep, that means we could also publish fake articles that makes it rewrite its own code to produce bugs/failures

    • fidodo@lemmy.world
      link
      fedilink
      English
      arrow-up
      2
      ·
      1 year ago

      The limiting factor is pre existing information. It’s great at retrieving obscure information and even remixing it, but it can’t really imagine totally new things. Plus white hats would also have LLMs to find vulnerabilities. I think it’s easier to detect vulnerabilities based on known existing techniques than it is to invent totally new techniques.