• sykaster@feddit.nl
    link
    fedilink
    English
    arrow-up
    7
    arrow-down
    1
    ·
    2 days ago

    I asked this question to a variety of LLM models, never had it go wrong once. Is this very old?

      • RidderSport@feddit.org
        link
        fedilink
        arrow-up
        3
        arrow-down
        3
        ·
        2 days ago

        You’re shitting me right? They did not just use an entry grade java command to rectify and issue that a LLM should figure out by learning right?

        • boonhet@sopuli.xyz
          link
          fedilink
          arrow-up
          14
          ·
          2 days ago

          Well firstly it’s Python, secondly it’s not a command and thirdly it’s a joke - however, they have manually patched some outputs for sure. Probably by adding to the setup/initialization prompt

          • RidderSport@feddit.org
            link
            fedilink
            arrow-up
            2
            arrow-down
            1
            ·
            1 day ago

            Java is the only code I have any (tiny) knowledge of, which is why the line reminded me of that.

            • boonhet@sopuli.xyz
              link
              fedilink
              arrow-up
              3
              ·
              edit-2
              1 day ago

              Ah, but in Java, unless they’ve changed things lately, you have the curly brace syntax of most C-like languages

              if ("strawberry" in token_list) {
                  return something;
              }
              

              Python is one of the very few languages where you use colons and whitespace to denote blocks of code

    • BootLoop@sh.itjust.works
      link
      fedilink
      arrow-up
      15
      ·
      edit-2
      2 days ago

      Try “Jerry strawberry”. ChatGPT couldn’t give me the right number of r’s a month ago. I think “strawberry” by itself was either manually fixed or trained in from feedback.

    • Ignotum@lemmy.world
      link
      fedilink
      arrow-up
      10
      ·
      2 days ago

      Smaller models still struggle with it, and the large models did too like a year ago

      It has to do with the fact that the model doesn’t “read” individual letters, but groups of letters, so it’s less straight forward to count letters

    • Annoyed_🦀 @lemmy.zip
      link
      fedilink
      English
      arrow-up
      1
      ·
      1 day ago

      Seeing how it start with an apology, it must’ve been told they’re wrong about the amount. Basically being bullied to say this.