Would it make the internet better? Probably.

  • Zeshade@lemmy.world
    link
    fedilink
    English
    arrow-up
    12
    ·
    26 days ago

    As far as I know Google and Bing return AI results just above the usual web page results.

    In addition AI LLM tools like Copilot (the mobile app) and Perplexity which cite their sources with links to websites really make it easier to weed out the BS from LLM answers, if you use them carefully. In my case, these tools replace search engines in 80% of the searches that I do.

    • cum@lemmy.cafe
      link
      fedilink
      English
      arrow-up
      1
      ·
      26 days ago

      If you’re following citations, may as well just search for the citations themselves… aka just a regular search engine.

      • Zeshade@lemmy.world
        link
        fedilink
        English
        arrow-up
        3
        ·
        26 days ago

        Yes but the power of it is that you can in effect refine your search using natural language, like talking to a person, as it remembers the last 2-3 exchanges.

        And it presents the information the way you asked to see it.

        For example (my side of the “conversation”):

        • What is hamas?
        • Compared to Hezbollah?
        • what are the differences between Shia and Sunni?

        The citations confirm the information, they are not the end goal. The added value is the fact that the information is pre-digested and presented in a way that matches my learning process. It’s a lot easier for me to assimilate information by getting answers to questions that I’ve asked.

      • theneverfox@pawb.social
        link
        fedilink
        English
        arrow-up
        1
        ·
        25 days ago

        Yeah, if search hadn’t become dog shit I’d be happy with it

        Instead, everything is a video for some reason, and the results are purposely worse than a year ago…I don’t want to watch a video, I can read 20x faster than I can listen, I don’t want to read an ad in article form - I’m generally looking for one little nugget of information

        I took this into my own hands - I’ll use free services if they work, but increasingly they’re just demos for a product that may or may not be better. So I spun up a searx container, I point a local LLM at it, and I let it filter read through results. My next stage is to crawl documentation, use LLMs to feed it into a vector db, and use AI to retrieve exactly what I want without sifting through garbage myself