AppLovin’s attempts to acquire Unity last year turned sour when Unity opted for a merger with rivals ironSource instead . Now, in the ongoing shockwave of Unity’s unpopular introductio…

  • YMS@kbin.social
    link
    fedilink
    arrow-up
    23
    arrow-down
    1
    ·
    1 year ago

    Does ChatGPT’s code get better if you include “You’re an expert in that language” in the prompt?

    • Natanael@slrpnk.net
      link
      fedilink
      English
      arrow-up
      21
      ·
      1 year ago

      It does occasionally because it filters out sources which doesn’t fit that pattern, but it doesn’t guarantee anything (for a variety of reasons, like inevitable statistical cross contamination in the model, bad samples like overconfident answers, smaller number of samples to learn from, etc).

    • drislands@lemmy.world
      link
      fedilink
      English
      arrow-up
      6
      ·
      1 year ago

      Good question. Based on my limited understanding of LLMs, I don’t see how it could…I’m interested to hear if that’s not the case.

      • Encrypt-Keeper@lemmy.world
        link
        fedilink
        arrow-up
        7
        ·
        edit-2
        1 year ago

        Because an LLM’s goal isn’t to always be the most correct at answering questions. It just says what it thinks you want it to say. It’s not that telling it that it’s an expert necessarily makes it smarter, you’re just specifying not to give you an answer as though it was an amateur, which otherwise it wouldn’t have any reason not to do.

      • Jerkface@lemmy.world
        link
        fedilink
        English
        arrow-up
        5
        ·
        1 year ago

        I use ChatGPT for math tutoring occasionally and when I started using the prompt “Suppose you are a professional mathematician,” I got fewer responses resembling those you might get from a classmate and more which were thorough and rigorous.