• ayyy
    link
    fedilink
    arrow-up
    2
    ·
    8 天前

    Apple’s autocorrect is based on GPT, of chatGPT fame, but it’s the GPT2 model which came out around 2015. Back then it ran on supercomputers, now it fits in your pocket. ChatGPT uses the GPT4 model which requires really big supercomputers for now.

    • gmtom@lemmy.world
      link
      fedilink
      arrow-up
      3
      ·
      8 天前

      That’s to train it. Even the most modern version of AIs like deepseek or get can run on a raspberry pi.

      • ayyy
        link
        fedilink
        arrow-up
        4
        ·
        8 天前

        Only if you distill it to the point of uselessness (well, even more useless). Otherwise you wouldn’t have headlines like this.

        • gmtom@lemmy.world
          link
          fedilink
          arrow-up
          1
          ·
          8 天前

          No? I litterally run a local deepseek model on a raspberry pi to use as an alexa-like personal assistant.

          • ayyy
            link
            fedilink
            arrow-up
            2
            ·
            8 天前

            Yea I guess it works fine for anything that doesn’t require a real context window.