• Wispy2891@lemmy.world
    link
    fedilink
    arrow-up
    87
    ·
    7 days ago

    I see it as a funny prank

    If you’re a dev you’re using git so you can revert that in minutes

    And if you’re a dev you’re definitely not running an agent with rm in the command whitelist

    • Treczoks@lemmy.world
      link
      fedilink
      arrow-up
      37
      ·
      7 days ago

      Yep. If your AI is set up to be able to cripple your machine or worse, you deserve it.

      But I know too many people who are bored to shit to individually vet and permit dangerous AI actions and gave the machine broad permissions.

    • Railcar8095@lemmy.world
      link
      fedilink
      arrow-up
      10
      ·
      7 days ago

      I give agents full el command execution access. Inside their VM, which doesn’t connect to any external DB or API (or at least, not critical /production ones) And I take periodic snapshots of all the files on the workspace.

      Honestly those measures were the standard for me way before LLMs were a thing. Those who have broad permissions to production or when their machine were asking for this to happen, no agents required.