The model, called GameNGen, was made by Dani Valevski at Google Research and his colleagues, who declined to speak to New Scientist. According to their paper on the research, the AI can be played for up to 20 seconds while retaining all the features of the original, such as scores, ammunition levels and map layouts. Players can attack enemies, open doors and interact with the environment as usual.

After this period, the model begins to run out of memory and the illusion falls apart.

  • YourNetworkIsHaunted@awful.systems
    link
    fedilink
    English
    arrow-up
    45
    arrow-down
    5
    ·
    2 months ago

    Note that the image here isn’t from the AI project, it’s from actual Doom. Their own screenshots have weird glitches including a hit splat that looks like a butt in the image I’ve seen closest to this one.

    And when they say they’ve “run the game” they do not mean that there was a playable version that was publicly compared to the original. Rather they released short video clips of alleged gameplay and had their evaluators try to identify if they were from the AI recreation or from actual Doom.

    Even by the abysmal standards of generative AI projects this is a hell of a grift.

    • Telorand@reddthat.com
      link
      fedilink
      English
      arrow-up
      14
      arrow-down
      1
      ·
      2 months ago

      Even by the abysmal standards of generative AI projects this is a hell of a grift.

      But if you invest now, you can make a game-generating AI a reality! /s

      • YourNetworkIsHaunted@awful.systems
        link
        fedilink
        English
        arrow-up
        1
        ·
        2 months ago

        Possibly fair. I’m pretty sure I’ve seen that exact screenshot used in other articles about Doom, but I’m not enough of a Doom nerd to be sure.

        There’s a decent writeup over at Pivot-to-AI that looks at the paper as a whole in more detail.