• GissaMittJobb@lemmy.ml
    link
    fedilink
    arrow-up
    1
    ·
    2 days ago

    Still, this does not quite address the issue of tokenization making it difficult for most models to accurately distinguish between the hexadecimals here.

    Having the model write code to solve an issue and then ask it to execute it is an established technique to circumvent this issue, but all of the model interfaces I know of with this capability are very explicit about when they are making use of this tool.

    • morrowind@lemmy.ml
      link
      fedilink
      arrow-up
      1
      ·
      1 day ago

      Not really a concern. It’s basically translation, which language models excel at. It just needs a mapping of the hex to byte

        • morrowind@lemmy.ml
          link
          fedilink
          arrow-up
          1
          ·
          1 day ago

          I’m well aware, but you don’t need to necessarily see each character to translate to bytes

          • GissaMittJobb@lemmy.ml
            link
            fedilink
            arrow-up
            1
            ·
            1 day ago

            It’s not out of the question that we get emergent behaviour where the model can connect non-optimally mapped tokens and still translate them correctly, yeah.

            • kautau@lemmy.world
              link
              fedilink
              arrow-up
              1
              ·
              18 hours ago

              I’m confused, is the concern when the model doesn’t properly identify when it is using software to identify something like a hex pattern?

              • GissaMittJobb@lemmy.ml
                link
                fedilink
                arrow-up
                2
                ·
                17 hours ago

                The concern is that the model doesn’t actually see the world in terms of distinct hexadecimals, but instead as tokens of variable size - you can see this using the tiktokenizer-webapp: enter some text and it will split it into the series of tokens the model actually will process.

                It’s not impossible for the model to work it out anyway, but it is a reason for this type of task to be a bit harder on LLMs.

                • kautau@lemmy.world
                  link
                  fedilink
                  arrow-up
                  1
                  ·
                  17 hours ago

                  I understand how base models tokenize language. What I’m curious about you’re basing your response off a horrendously screenshotted meme image of someone interacting with deepseek. Is your concern that deepseek isn’t showing the code used to approach a hex string? Because that’s certainly a valid concern, though you can ask the model to output the code it is running. That’s definitely an ethics improvement that should be made in the UI, but it’s very clear what the model is doing under the hood

                  • GissaMittJobb@lemmy.ml
                    link
                    fedilink
                    arrow-up
                    2
                    ·
                    11 hours ago

                    I don’t think DeepSeek has the capability of generating code and executing it inline in the context window to support its answers, in the way that ChatGPT does - the “used”-part of that answer is likely a hallucination, while “or would use” more accurately represents reality.