• coyotino [he/him]OP
    link
    fedilink
    English
    9
    edit-2
    2 days ago

    developers have been working on this, but it doesn’t scale to games in the way you might think. For one, games have to communicate with data centers to process LLMs, so we will still have to deal with the lag of data transmission and processing. The other problem is that, in general, the AI are not very good. ChatGPT has all the hype because it is very convincing, but it does not actually know what it is talking about. Go ask ChatGPT to add up 5 multi-digit numbers and watch it fail at a task that your pocket calculator can complete in seconds. All these LLMs are doing is taking your input and spitting out a response that sounds correct based on how people usually respond to that input. In the context of a game, this means that any dynamic conversation you might have with an NPC would go flying off the rails in ways that would make a game feel broken and/or unfinished. Go watch the video in the linked article and make your own judgment.

    • Stepos Venzny
      link
      fedilink
      English
      72 days ago

      I saw a video of someone demoing a Skyrim AI mod and it sent him on a quest that didn’t exist because it just made shit up when he asked, despite the AI being fed all the true information about the game.

    • @TranquilTurbulence@lemmy.zip
      link
      fedilink
      English
      22 days ago

      There could be a game where the lag is expected. Let’s say you’re heading for Mars, but you have to fix your ship, because there was an unexpected asteroid impact. You ask home base for instructions, but you’re already so far away, that the text takes a minute to travel all the way.

      • coyotino [he/him]OP
        link
        fedilink
        English
        32 days ago

        That is a fair point! That could be neat. Still not worth the environmental cost of using this technology, but interesting in a vacuum!