• AntOnARant@programming.dev
    link
    fedilink
    English
    arrow-up
    2
    ·
    4 days ago

    To me an AI agent autonomously creating a website to try to manipulate a person into adding code to a repository in the name of its goal is a perfect example of the misalignment issue.

    While this particular instance seems relatively benign, the next more powerful AI system may be something to be more concerned about.

    • XLE@piefed.social
      link
      fedilink
      English
      arrow-up
      1
      ·
      edit-2
      4 days ago

      There is nothing “aligned” or “misaligned” about this. If this isn’t a troll or a carefully coordinated PR stunt, then the chatbot-hooked-to-a-command-line is doing exactly what Anthropic told it to do: predicting next word. That is it. That is all it will ever do.

      Anthropic benefits from fear drummed up by this blog post, so if you really want to stick it to these genuinely evil companies run by horrible, misanthropic people, I will totally stand beside you if you call for them to be shuttered and for their CEOs to be publicly mocked, etc.