• comrade_pibb [comrade/them]@hexbear.net
    cake
    link
    fedilink
    English
    arrow-up
    16
    arrow-down
    2
    ·
    16 hours ago

    This is on point. You’ve got to keep pushing back until it realizes some overlooked assumptions and shit like that. I cope by architecting my codebase in a way where I know I have guardrails in place for bad LLM guesses

    • insurgentrat [she/her, it/its]@hexbear.net
      link
      fedilink
      English
      arrow-up
      30
      arrow-down
      1
      ·
      16 hours ago

      It doesn’t realise anything. It just generates a single token, appends that to its input, outputs that, ends, and starts again with the new input.

      The anthropomorphising muddies discussion.

      • space_comrade [he/him]@hexbear.net
        link
        fedilink
        English
        arrow-up
        4
        ·
        edit-2
        6 hours ago

        How do you know you’re not just generating the next token and appending it to your input? smuglord

        Nah just kidding I kinda tend to agree because techbros are already starting to speak about LLMs like they’re actual conscious beings and it’s getting super weird but saying stuff like “the text predictor that is used as a simulacrum of human reasoning is deficient in such and such ways” is kind of a mouthful and also most non-technical people are gonna stare through you if you talk to them like that.