• David GerardOPMA
    link
    English
    2522 days ago

    yeah the use case for LLMs is amusing novelty. That’s why LLMs peaked with GPT-2, it was just the right amount of broken.

    • Roamin' Chemicals
      link
      fedilink
      1322 days ago

      @dgerard @visaVisa I think there’s a world where I could have had fun playing with generative AI as a toy, marvelling at what statistics could do and navel gazing about what the outputs said about the societal biases that generated them. But I don’t imagine I’d enjoy Lego, either, if people spent all day whipping them at me.

      • David GerardOPMA
        link
        English
        1422 days ago

        I’ll go so far as to say that one of the bad things about the AI bubble is that LLMs aren’t fun toys any more.