How hard would it be to train an AI model to be secretly evil? As it turns out, according to Anthropic researchers, not very.

Scientists Train AI to Be Evil, Find They Can’t Reverse It::How hard would it be to train an AI model to be secretly evil? As it turns out, according to Anthropic researchers, not very.

  • the_q@lemmy.worldEnglish
    81·
    11 months ago

    Is this really that surprising? Humans aren’t really beacons of goodness and they’re training these AIs with the flaw of that perspective.

    • 1984@lemmy.todayEnglish
      61·
      11 months ago

      I’m pretty good actually. But you never see me in the media. :)

      • the_q@lemmy.worldEnglish
        5·
        11 months ago

        I’m sure your are. Everyone thinks they’re “good” but there are certainly “bad” people.

        • 1984@lemmy.todayEnglish
          11·
          11 months ago

          I’m not sure they do. Some people are bad and they know they are but they just don’t agree that the definition of good matters.

          A lot of this stuff is probably grounded in if you believe your actions has any spiritual meaning or not. For a lot of people, it seems that if there is no reward for being good, then why make the effort. Because for them, it’s an effort. For others, it’s just how they are.

          • Delta_V@lemmy.worldEnglish
            3·
            11 months ago

            if there is no reward for being good, then why make the effort

            You’re describing evil.

            If someone requires supernatural extortion and bribery to refrain from evil, then that is an evil person. Even if the bribery and extortion works.

            • 1984@lemmy.todayEnglish
              1·
              11 months ago

              Yes, that’s what I meant. Good people are naturally good and don’t think about rewards for being nice.

    • Obinice@lemmy.worldEnglish
      3·
      11 months ago

      What do you mean I’m not a beacon of goodness?! Say that again and I’ll get stabby!!