I'm stunned by AI generated and playable version of Doom without any pre-programmed rules. This is insane! It's like AI is learning to create entire worlds on its own. Imagine the possibilities for gaming, simulations, and even software design. What do you think this means for the future?
Perhaps first read the paper/site https://gamengen.github.io/?utm_source=substack&utm_medium=email .. the skeptic's perspective is that since the system was trained on an agent learning to play doom (think alphago/etc), which produced the model, this more like a facade simulation than a true a generative model recreating the game. What it clearly signals is that diffusion can readily create generative environments that reflect stimulus other than camera position, etc.. since people can shoot things as well, and not walk through walls (though that was a thing too in doom!).
Here’s a few links to an award winning short film we made about Haber back in 2008. Enjoy!
https://en.m.wikipedia.org/wiki/Haber_(film)
https://youtu.be/znXhaRnQ26I
I'm stunned by AI generated and playable version of Doom without any pre-programmed rules. This is insane! It's like AI is learning to create entire worlds on its own. Imagine the possibilities for gaming, simulations, and even software design. What do you think this means for the future?
Perhaps first read the paper/site https://gamengen.github.io/?utm_source=substack&utm_medium=email .. the skeptic's perspective is that since the system was trained on an agent learning to play doom (think alphago/etc), which produced the model, this more like a facade simulation than a true a generative model recreating the game. What it clearly signals is that diffusion can readily create generative environments that reflect stimulus other than camera position, etc.. since people can shoot things as well, and not walk through walls (though that was a thing too in doom!).