And you could almost always tell a "game construction kit" game from a real one, couldn't you? Whatever was missing from those is always missing from these, and it seems just as rare that the game will reach much beyond its origins.
Whenever I think about AI games I find myself thinking about Tiny Wings, Flappy Bird and Angry Birds. Three simple, elegant games.
It is easy to see what makes Tiny Wings so completely loveable — it has a sculpted, adorable, perfect charm with a cleverly inverted game mechanic that has a calibrated level of exasperation and reward.
But why were Flappy Bird and Angry Birds, very basic games with very old game mechanics, so charming?
It seems equally impossible to imagine an AI coming up with a game with the quality of any of them, even with maximised creativity. But explaining why for Flappy Bird seems quite difficult, especially when you consider it uses some stolen visuals!
it's crazy because I've seen "implement flappy bird on an FPGA with VGA output" as a 2 week project to a human as something immediately understandable.
Maybe it's the smoothness of motion that makes these games understandable and LLMs seem to consistently fail at that. Ask them to do something snowboarding and they go really hard on the physics since it seems like they don't know what kind of approxmations feel good.