"The potential here is absurd," wrote app developer Nick Dobos in reaction to the news. "Why write complex rules for software by hand when the AI can just think every pixel for you?"

"Can it run Doom?"

"Sure, do you have a spare datacenter or two full of GPUs, and perhaps a nuclear powerplant for a PSU?"

What the fuck are these people smoking. Apparently it can manage 20 fps on one "TPU" but to get there it was trained on shitload of footage of Doom. So just play Doom?!

The researchers speculate that with the technique, new video games might be created "via textual descriptions or examples images" rather than programming, and people may be able to convert a set of still images into a new playable level or character for an existing game based solely on examples rather than relying on coding skill.

It keeps coming back to this, the assumption that these models, if you just feed them enough stuff will somehow become able to "create" something completely new, as if they don't fall apart the second you ask for something that wasn't somewhere in the training data. Not to mention that this type of "gaming engine" will never be as efficient as an actual one.