• Deceptichum@sh.itjust.works
    link
    fedilink
    English
    arrow-up
    0
    ·
    edit-2
    7 months ago

    It doesn’t read on demand, it reads once when it’s being trained, and it later recalls what it learnt from that training.

    Training LLMs takes a very long time and a lot of hardware power.

      • 8uurg@lemmy.world
        link
        fedilink
        English
        arrow-up
        0
        ·
        7 months ago

        These models have so many parameters that, while insufficient to memorize all text it has ever seen, it can end up memorizing some of the content. It is the difference between being able to recall a random passage versus recalling the exact thing you need. Both allow you to spill content verbatim, but one is problematic while the other can be helpful.

        There are techniques to allow it it ‘read on demand’, but they are not part of the core model (i.e. the autocmpletion model / LLM) and are tacked on top of it. For example, you can tie it search engine, which Microsoft’s copilot does, and is something which I don’t think is enabled for ChatGPT by default. Or allow it to query a external data bank (Retrieval Augmented Generation).

        • Deborah@hachyderm.io
          link
          fedilink
          arrow-up
          0
          ·
          7 months ago

          Or when you’re singing karaoke and suddenly break into a chorus of the phone number and email address of a random author of a scholarly paper whom you’ve never met whose paper has nothing to do with the lyrics of “Free Bird“?

    • DessertStorms@kbin.social
      link
      fedilink
      arrow-up
      0
      ·
      7 months ago

      It doesn’t read on demand

      Yes, it does, from the information it was trained on (or - stored), which like you say, requires a lot of hardware power so it can be accessed on demand. It isn’t just manifesting the information out of thin air, and it definitely doesn’t “remember” in the same way we do.

      • abruptly8951@lemmy.world
        link
        fedilink
        English
        arrow-up
        0
        ·
        7 months ago

        It’s definitely not indexed, we use RAG architectures to add indexing to data stores that we want the model to have direct access to, the relevant information is injected directly in the context (prompt). This can somewhat be equated to short term memory

        The rest of the information is approximated in the weights of the neural network which gives the model general knowledge and intuition…akin to long term memory

        • self@awful.systems
          link
          fedilink
          English
          arrow-up
          0
          ·
          7 months ago

          or it can be equated to a shitty database and lossy compression (with artifacts in the form of “hallucinations”), but that doesn’t make the tech sound particularly smart, does it?

          but half the posts in your history are in this thread and that’s too many already

            • froztbyte@awful.systems
              link
              fedilink
              English
              arrow-up
              0
              ·
              7 months ago

              awww, I just got another bowl of popcorn!

              but rofl holy shit at “glad to see someone else knows how they work” given the … depth of understanding, shall we say? that was demonstrated in this thread