• Zwuzelmaus@feddit.org
    link
    fedilink
    English
    arrow-up
    29
    ·
    14 hours ago

    “Tokens” are just made up.

    These “tokens” that are used to “measure” how much you use, they are not a real dimension that can be measured. Just an artificial counter that goes up when they decide that it should go up.

    They can change the “size” of a “token” every day, and every second, and every microsecond…

    • boonhet@sopuli.xyz
      link
      fedilink
      English
      arrow-up
      1
      ·
      1 hour ago

      For subscriptions they use a black box metric nobody knows. For usage credits, tokens are very measurable.

      The subscriptions are much cheaper than usage credits but have been nerfed in the past and will be nerfed again in the future

    • floofloof@lemmy.ca
      link
      fedilink
      English
      arrow-up
      5
      ·
      5 hours ago

      Maybe you’re confusing tokens with the “credits” you pay for. Tokens have a technical meaning, but some companies are charging per AI credit, where they don’t tell you the conversion rate of credits to tokens, so they can change this at any time, or vary it between models, etc.

    • some_kind_of_guy@lemmy.world
      link
      fedilink
      English
      arrow-up
      43
      ·
      edit-2
      14 hours ago

      Not entirely wrong, but tokens are not just “fake” in the way, for example, an in-game currency is. They’re the fundamental “units” of data, both input and output, processed by the model. For most models, tokens are just a certain number of characters or words. So they’re not completely untethered from the model. If we’re both using Clankerbot v5.1: Sloppy Logic Edition™️, your tokens are defined in the same way mine are.

      This is near the edge of my limited understanding, but AFAIK, yeah they can mess with token costs and billing schemes all they want. They could theoretically charge us 2 different costs per token, or do surge pricing or some shit.

      if they wanted to change the actual size/definition of what a token is though, that would require a whole new model (or at least a major revision).

      • criss_cross@lemmy.world
        link
        fedilink
        English
        arrow-up
        1
        ·
        35 minutes ago

        Yeah pretty much. Tokens are how models parse sentences.

        It’s a wonky thing to charge by because each model tokenizes sentences differently. A sentence that would be 10 tokens in Claude can be 15 in OpenAI.

        It’s why it’s crazy to try and charge by it and track employee usage by it.

      • Zwuzelmaus@feddit.org
        link
        fedilink
        English
        arrow-up
        23
        ·
        14 hours ago

        You aren’t totally wrong. Such a unit exists and it is also called tokens, that can measure the capability of a model and the size of a running operation in a model.

        But what they use for calculating your bill is something different today.

        • T156@lemmy.world
          link
          fedilink
          English
          arrow-up
          4
          ·
          edit-2
          11 hours ago

          Such a unit exists and it is also called tokens, that can measure the capability of a model and the size of a running operation in a model.

          I think you might have it mixed up with parameters, rather than tokens. Parameters are how big the model is, and are an indirect measure of how capable it is. Bigger models tend to be more capable.

          But what they use for calculating your bill is something different today.

          The tokenizer varies a little, but I don’t think it’s changed measurably from tokens. You pay an amount for a million tokens worth of processing. The tokeniser difference just alters how text is converted to tokens, but the tokens themselves don’t change all that much.

          If anything, I’d honestly put the issue more with reasoning chains in models, where they basically babble to themselves inside of a <think> tag, that most interfaces hide/collapse. It makes them work better, but vastly increases the amount of tokens per operation.

          They have been getting longer and more sophisticated with newer models. So you might have a model now that basically repeats the output multiple times whilst refining and drafting the non-reasoning output.

          If you’re making it generate a lot, that’ll balloon the usage, and thus price.

        • hubobes@sh.itjust.works
          link
          fedilink
          English
          arrow-up
          7
          ·
          13 hours ago

          That doesn’t make much sense. When Anthropic moved to Sonnet 5 they introduced a new tokenizer which increased token use up to 35%. If these would be unrelated kinds of tokens why would the usage go up when the process of tokenization changes?

    • nitroemdash@lemmy.wtf
      link
      fedilink
      English
      arrow-up
      16
      ·
      14 hours ago

      Tokens are well-defined groups of bytes ranged by frequency of occurrence in texts to efficiently translate them into a sequence of 32 or 64-bit binary integers, an LLM-optimised form if compression. They are well-known, you can play with them here: https://gpt-tokenizer.dev/

    • Tixo@lemmy.zip
      link
      fedilink
      English
      arrow-up
      6
      ·
      14 hours ago

      Eh, they can be manipulated but I suggest you read on what a token is and how JTS used. What you are feeling here (with more being used for the same task) is multi modal llms working in unison, thus consuming more tokens for the same task to make your answers potentially better.

    • keimevo@lemmy.world
      link
      fedilink
      English
      arrow-up
      6
      ·
      14 hours ago

      It’s not like that. Tokens are an inherent computational property of how a model calculates the probabilities and such to generate text.

      Having said that, what a token means in terms of computation varies wildly between models and is not directly comparable. So attributing a money value to tokens in general, independently of the model, is weird by nature.

      And even within a model, the number of tokens needed to generate a response is very variable too, depending of the model itself and the parameters with which it has been configured (thinking mode, temperature, etc.).

      So yeah, companies can pretty much set any price they want and there’s not much anyone can do about it.

      • Jiral@lemmy.world
        link
        fedilink
        English
        arrow-up
        2
        ·
        11 hours ago

        It does make sense for the provider as those for a specific model provide a good measure for computational effort, for that doecific model. That doesn’t mean that token rate comparison between models give you a good picture.