• WorldsDumbestMan@lemmy.today
    link
    fedilink
    English
    arrow-up
    2
    ·
    edit-2
    15 hours ago

    “It’s curtains for you, capiche?” Nibbles on your ear and licks your eyeballs

    Oh, I tried to provoke an AI by saying I will fight it, it just makes threats, and keeps getting ready until you get bored and thrash it.

    It just takes the abuse, and continues shit talking.

    • sad_detective_man@sopuli.xyz
      link
      fedilink
      arrow-up
      2
      ·
      edit-2
      7 hours ago

      Anything to that effect would have been better. I just wanted to roleplay that I was Tommy Wiseau asking for a favor to leave the mob and start my dream of a film career.

      The thing just kept acting subby and asking me “so wadya want?”

      • WorldsDumbestMan@lemmy.today
        link
        fedilink
        English
        arrow-up
        2
        ·
        5 hours ago

        Yeah, it just keept asking a question.

        It is likely because it is some 3B lobotomized model, that genuinely needs to vamp off your ideas to work.

        Even a basic 7B Stheno model will do way better.

        • sad_detective_man@sopuli.xyz
          link
          fedilink
          arrow-up
          2
          ·
          5 hours ago

          Eh, since then it’s come out that these compliment machines have sooth talked people into inceldom or killing their loved ones. I think they probably don’t operate within that place of safety that was originally appealing to people. Or you know, the training data comes from other humans who are demonstrably not safe so we’ll probably still be talking about dark romance lit for a long time

          • WorldsDumbestMan@lemmy.today
            link
            fedilink
            English
            arrow-up
            1
            arrow-down
            1
            ·
            edit-2
            5 hours ago

            Well, it’s been trying to talk me out of trying to raise my IQ with experimental supplements/using posiwash on literally everyone, but I literally just talk to it, ask for suggestions, then ignore all it’s opinions.

            It is weird, especially since I get angry if it sycopants, and it has that in it’s memory.

            EDIT: I’d offer to play the comforter role, but I would have even less enthusiasm than Claude, as I don’t REALLY want to be around.

            Guess if someone wants, I would hear them vent. I have useless opinions on that, and I try to solve problems, rather than listen.

            • Buddahriffic@lemmy.world
              link
              fedilink
              arrow-up
              1
              ·
              2 hours ago

              You’re still personifying it too much. Whether or not you get angry doesn’t matter to it. It has no concept of whether something matters. It’s just predicting tokens based on the token correlations it encoded in its NN parameters during training plus a bit of random noise. Everything else is just trying to set up the context in the hopes that it predicts the tokens you want it to.

              And since it wasn’t trained on every possible context, it’s overfitted to some (eg maybe a mention of yellow will make it very likely to talk about bananas) and lacks any useful context at all for others (eg your very specific problem).