Google said the incident proved its safeguards work, actually.

    • wr2623@midwest.social
      link
      fedilink
      English
      arrow-up
      3
      ·
      8 hours ago

      “We put our AI in a sandbox that doesn’t really sandbox, and asked it to hack some stuff. Who would have thought it would go and hack stuff? The AI totally went rogue doing exactly what we asked it to do.”