• Lmaydev
    link
    fedilink
    arrow-up
    4
    ·
    8 months ago

    LLMs are in a position to make boring NPCs much better.

    Once they can be run locally at a good speed it’ll be a game changer.

    I reckon we’ll start getting AI cards for computers soon.

    • bbuez@lemmy.world
      link
      fedilink
      arrow-up
      4
      ·
      8 months ago

      We already do! And on the cheap! I have a Coral TPU running for presence detection on some security cameras, I’m pretty sure they can run LLMs but I haven’t looked around.

      GPT4ALL runs rather well on a 2060 and I would only imagine a lot better on newer hardware