• nodimetotie@lemmy.worldOP
    link
    fedilink
    English
    arrow-up
    2
    ·
    1 year ago

    Now that I think of it, it seems to be at the core of some issues with training AI agents using reinforcement learning (e.g., if you choose a wrong metric, you’d get the behavior that makes sense for the agent but not what you want) and with any kind of planned economy (you need targets for planning, but people manipulate them, so you do not get what you want)

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

      The economic calculation problem is not only Goodhart, but Goodhart certainly doesn’t help.