Google’s new AI gaming engine can recreate DOOM and basically all your other favorite games too
Could you imagine DOOM?
DOOM, the 1993 cult classic, has turned into somewhat of an internet meme. Playable on nearly everything, from microwaves to electric toothbrushes, it’s more of a question of what can’t play DOOM rather than what can. Now, thanks to Google’s AI GameNGen, AI can even generate a playable version of one of the most beloved video games of all time, and it’s seriously impressive.
GameNGen is a new video game engine that is powered by a neural model able to generate gameplay based on different prompts. In the case of this recreation of DOOM, GameNGen is essentially learning to play the game as masterfully as possible, dodging bullets, slaying demons, and interacting with the environment.
Once the AI has understood exactly how to play the game, GameNGen then uses a diffusion model to recreate a perfect image of the content it has just consumed. The game is produced in real-time with the AI model generating each individual frame based on the last one.
The recreation of DOOM is something to behold, but with GameNGen only able to recreate the game at around 20fps, it’s obviously not comparable to id Software’s 120fps in DOOM Eternal, or the graphics we’ve seen of the upcoming DOOM: The Dark Ages. However, considering that artificial intelligence has imagined one of the most famous video games and it's playable, we're impressed.
More than just a DOOM Slayer
GameNGen’s powers are not limited to DOOM, while the game engine might not be able to recreate any game on the planet very well, in theory, it should be able to reimagine most of your favorite games — albeit in a way that will probably cause motion sickness, with all the frame drops.
Just earlier this week, Virtuals Protocol demonstrated MarioVGG, an AI video tool that recreated a glitchy version of Super Mario Bros. While it leaves a lot to be desired, this appears to only be the beginning of AI’s involvement in video game development with an exciting, and potentially terrifying, future upon us.
You Might Also Like
- Stable Diffusion AI spin-off will let you create weird videos from text prompts
- Watch the AI-produced film Toys"R"Us made using OpenAI's Sora – and get misty about the AI return of Geoffrey the Giraffe
- A new OpenAI Sora rival just landed for AI videos – and you can use it right now for free
Get daily insight, inspiration and deals in your inbox
Sign up for breaking news, reviews, opinion, top tech deals, and more.
John-Anthony Disotto is TechRadar's Senior Writer, AI, ensuring you get the latest information on Tech's biggest buzzword. An expert in Apple, he was previously iMore's How To Editor and has a monthly column in MacFormat. Living in Scotland, where he worked for Apple as a technician focused on iOS and iPhone repairs at the Genius Bar, John-Anthony has used the Apple ecosystem for over a decade and is an award-winning journalist with years of experience in editorial.