• potatopotato@sh.itjust.works
    link
    fedilink
    arrow-up
    15
    ·
    14 小时前

    The LLMs are just somewhere between an averaging and a lossy compression of everything on GitHub. There’s nothing about the current paradigm of “AI” that is going to somehow do better than just rehashing that training set but with the inclusion of various classes of errors.

    I think it’s better to view it as spicy search rather than any form of intelligence.

    • MrScottyTay@sh.itjust.works
      link
      fedilink
      English
      arrow-up
      5
      ·
      8 小时前

      Yeah that’s mostly what i use it for. A way to search for things that i can’t describe well enough for a traditional search engine so I can find out at a glance what it’s name is and if it’s valid for my situation. If it is then I go look up documentation. Any time I’ve stayed in the LLM past that I eventually go down a rabbit hole of wrong ideas that aren’t always obvious until you get a bit too deep and you’ve wasted an hour with an incorrect solution.

      • Corkyskog@sh.itjust.works
        link
        fedilink
        arrow-up
        1
        ·
        1 小时前

        The only thing I have found it useful for is book recommendations. I like this book and that book, what other types of books are like these?

      • potatopotato@sh.itjust.works
        link
        fedilink
        arrow-up
        2
        ·
        2 小时前

        Yeah, I do believe it’s a good tool for search, just with the caveat that if it can’t find an answer it makes one up or otherwise kinda just fills in little missing details with noise.