• psycho_driver@lemmy.world
    link
    fedilink
    English
    arrow-up
    4
    arrow-down
    1
    ·
    26 days ago

    Bruh a couple of months ago I asked it (Gemini) to check the number of characters, including spaces, in a potential game character name because I was working at the time and couldn’t stop to check my in-head count. It told me 21–I had counted 20. I thought I must have gotten distracted and miscounted. Later when I had time to actually focus on the issue it turned out AI had miscounted a 20 character string (maybe counting the null terminating character?).

    • boonhet@sopuli.xyz
      link
      fedilink
      English
      arrow-up
      11
      arrow-down
      1
      ·
      26 days ago

      AI doesn’t see individual characters, it sees tokens, with most tokens being a word or part of a word. That’s why per-character questions have such a high failure rate.

      • PunnyName@lemmy.world
        link
        fedilink
        English
        arrow-up
        6
        arrow-down
        5
        ·
        edit-2
        25 days ago

        If it doesn’t understand the simple concept of the number of letters and spaces, it needs to be reprogrammed.

        ETA: sorry folks, not gonna change my view and simp for shit A.I., continue with the downvotes.

        • boonhet@sopuli.xyz
          link
          fedilink
          English
          arrow-up
          9
          ·
          25 days ago

          It doesn’t understand anything though? It never will. It’s a probability machine. If you choose to believe its output, that’s on you. I use it as a coding assistant to get boring things done faster. Fire a prompt at claude code, grab a coffee, check out the diff. But that last step is crucial. Can’t trust AI output blindly.

          • dream_weasel@sh.itjust.works
            link
            fedilink
            English
            arrow-up
            3
            arrow-down
            2
            ·
            25 days ago

            The embedding layer post tokenization is not just a probability machine the way you’re suggesting it. You can argue that it is probabilistic with inferred sentiment, but too many people think it works like how text prediction on your phone does and that is just factually inaccurate.

            Verify output of course, but saying “it doesn’t understand anything” and “probability machine” is a borderline erroneous short sell. At the level of tokens it “understands” relationships, and those relationships are not probabilistic, though they are fundamentally approximated based on a training corpus.