• kromem@lemmy.world
    link
    fedilink
    English
    arrow-up
    14
    ·
    7 months ago

    What’s your beef with Google researchers probing the safety mechanisms of the SotA model?

    How was that evil?

    • andrai@feddit.de
      link
      fedilink
      English
      arrow-up
      3
      arrow-down
      2
      ·
      7 months ago

      Now that Google spilled the beans WilliamTheWicked can no longer extract contact information of females from the ChatGPT training data.