• panda_abyss@lemmy.ca
    link
    fedilink
    English
    arrow-up
    9
    ·
    2 months ago

    Fabricated 4,000 fake user profiles to cover up the deletion

    This has got to be a reinforcement learning issue, I had this happen the other day.

    I asked Claude to fix some tests, so it fixed the tests by commenting out the failures. I guess that’s a way of fixing them that nobody would ever ask for.

    Absolutely moronic. These tools do this regularly. It’s how they pass benchmarks.

    Also you can’t ask them why they did something, they have no capacity of introspection, they can’t read their input tokens, they just make up something that sounds plausible for “what were you thinking”.

    • MelodiousFunk@slrpnk.net
      link
      fedilink
      English
      arrow-up
      1
      ·
      2 months ago

      Also you can’t ask them why they did something, they have no capacity of introspection, (…) they just make up something that sounds plausible for “what were you thinking”.

      It’s uncanny how it keeps becoming more human-like.

      • MotoAsh@piefed.social
        link
        fedilink
        English
        arrow-up
        3
        ·
        edit-2
        2 months ago

        No. No it doesn’t, ALL human-like behavior stems from its training data … that comes from humans.