• WalrusDragonOnABike [they/them]@reddthat.com
    link
    fedilink
    English
    arrow-up
    1
    ·
    7 hours ago

    Why isn’t OpenAi working more modular whereby the LLM will call up specialized algorithms once it has identified the nature of the question?

    Wasn’t doing this part of the reason OpenSeek was able to compete with much smaller data sets and less hardware requirements?

    • RunawayFixer@lemmy.world
      link
      fedilink
      English
      arrow-up
      2
      ·
      6 hours ago

      I assume you mean DeepSeek? And it doesn’t look like it, according to what I could find, their biggest innovation was “reinforcement learning to teach a base language model how to reason without any human supervision”. https://huggingface.co/blog/open-r1

      Some others have replied that chatgpt and copilot are already modular: they use python for arithmetic questions. But that apparently isn’t enough to be useful.

      • absentbird@lemmy.world
        link
        fedilink
        English
        arrow-up
        2
        ·
        6 hours ago

        I feel like the best modular AI right now is from Gemini. It can take a scan of a document and turn it into a CSV, which I was surprised by.

        I figure it must have multiple steps, OCR, text interpretation, recognizing a table, then piping the text to some sort of CSV tool.