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

    I’m curious as well. My knowledge is probably quite outdated, but from what I understood the training part is what’s expensive and then querying the model is pretty cheap. Is it still true (or was it ever) that the generated answers on search engines are cheaper to generate than the actual search results?

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

      I find that hard to believe, I recently had to uninstall co-pilot after it weaseled its way into my search bar. Its not an exageration to say that my PC literally ran cyberpunk 2077 with pathtracting better than it ran the fucking windows search bar with co-pilot.

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

        That’s just a shitty front end interface implementation, it has nothing to do with the actual inference run by the models.

      • SorryQuick@lemmy.ca
        link
        fedilink
        English
        arrow-up
        2
        ·
        7 hours ago

        Look at the public numbers, it seems true. Copilot on your taskbar is just windows being garbage, not the AI being bad. Just look at self-hosted AI and measure the power costs of your queries. It’s tiny.

    • Shteou@lemmy.world
      link
      fedilink
      English
      arrow-up
      2
      ·
      10 hours ago

      It is sorta. Training is orders of magnitudes more intensive than inference, but we infer billions of times within a model generation.