In a move showing yet further progress in the field of generative AI being capable of simulating existing (copyrighted) games, the “DIAMOND” Diffusion for World Modeling model has now been showcased simulatingCounter-Strike: Global Offensive, trained and played off a singleRTX 3090(at 10 FPS). One of the people working on the project, Eloi Alonso, posted footage of thisCS:GO"world model" being run in a thread on Twitter, including plenty of disclosure on the involved glitches, of which there are many.
Ever wanted to play Counter-Strike in a neural network?These videos show people playing (with keyboard & mouse) in 💎 DIAMOND’s diffusion world model, trained to simulate the game Counter-Strike: Global Offensive.💻 Download and play it yourself → https://t.co/vLmGsPlaJp🧵 pic.twitter.com/8MsXbOppQKOctober 11, 2024
While a responsible enthusiast should be critical of the implications posed by AI technology implemented in this way, it’s undoubtedly an impressive technical achievement on the part of Eloi Alonso and the rest of the people who worked on the “DIAMOND” diffusion model to effectively “port"CS:GOto AI by training a single GPU with enough Dust II Deathmatch footage to “teach” the diffusion model the game. The glitches are all fascinating in their way, too, showing us some of the logistical shortcomings of generative AI technology that is still ultimatelyguessingcorrect player/game behavior, not running it within a game engine.
Of the glitches showcased by Alonso, one of the most interesting by far relates to jumping. Players can jump infinitely within this AI simulation ofCS:GObecause the model views pressing the button as having a fixed reaction (moving on the Y axis by a set amount) rather than being ruled by Source Engine’s gravity or collision detection. This also allows for other strangely dreamlike “hallucinations,” including weapons morphing in certain lighting conditions and even the ability to phase or teleport through particular walls.
There are still many limitations of our model. We’re sure you can find more yourself by interacting with the model.However, we expect the world model would continue to improve by scaling up data and compute, given our dataset only amounts to 87h of gameplay.(4/n) pic.twitter.com/EnqWiveUFLOctober 11, 2024
Instead of roughly simulating a GPU’s dream ofCounter-Strike, you can installCounter-Strike 2for free on Steam today and play it well above 60 FPS ongaming GPUsmuch cheaper than an RTX 3090. But as a technical demo for the RTX 3090’s onboard AI hardware training and running a diffusion model all on its lonesome, this “port” ofCS:GO’sDust II into a diffusion model is still quite enjoyable. Hopefully, the game industry doesn’t make the absolute worst of these technical advancements in morally, legally, and ethically dubious ways.
Get Tom’s Hardware’s best news and in-depth reviews, straight to your inbox.
Christopher Harper has been a successful freelance tech writer specializing in PC hardware and gaming since 2015, and ghostwrote for various B2B clients in High School before that. Outside of work, Christopher is best known to friends and rivals as an active competitive player in various eSports (particularly fighting games and arena shooters) and a purveyor of music ranging from Jimi Hendrix to Killer Mike to the Sonic Adventure 2 soundtrack.
