Microsoft’s new ‘breakthrough’ generative AI model is designed to ‘create consistent and diverse gameplay’ and could be used to preserve classic games

Microsoft has announced new AI project called MUSE in partnership with Xbox Game Studios’ Ninja Theory
The generative AI model has a “detailed understanding of the 3D game world” that can help game developers
Muse could also preserve classic games for future generation

Microsoft has revealed its new generative AI project called Muse, as it says, will be used to help Studios create gameplay and preserve classic titles.

In partnership with Xbox Game Studios’ Ninja Theory and Microsoft Research, Muse was trained in the developer’s multiplayer -kamparena game, Bleeding edge, And is said to have a “detailed understanding of the 3D game world” that is aware of game physics and the players’ controllers.

“This allows the model to create consistent and diverse gameplay reproduced by AI, demonstrating a big step towards generative AI models that can strengthen game creators,” Microsoft said in his advertising post.

The company is already using MUSE to develop a real-time-playable AI model that is trained in other first-party games and delivers recordings that show the model’s options in the blog post.

Introduction of MUSE: Our first generative AI model designed for gameplay –idation -YouTube

Look at

Microsoft also believes that one day it can benefit players and developers and even preserve classic games.

“Today, countless classic games bound to aging hardware can no longer be played by most people,” it said. “Thanks to this breakthrough, we are investigating the potential for MUS to take older back catalog games from our studios and optimize them for any device.

“We believe this can radically change how we preserve and experience classic games in the future and make them available to more players.”

Xbox manager Phil Spencer expanded with what it means in the attached message video and said MUSE has the potential to “learn about older games” from older hardware.

“… I’m thinking of an opportunity to get models to learn about older games, games that might have been tied to unique pieces of hardware where the engine of that hardware …” said Spencer. “Time will erode the amount of hardware out there that can actually play a game.

Spencer also suggested that AI could make older games “laptops for any platform where these models could run.”

“… We’ve talked about gaming preservation as an activity for us, and these models and their ability to learn completely how a game plays, without the necessity of the original engine running on the original hardware I think I open a ton of options.

It’s still early days, according to Microsoft, but more information about MUSE at Game Developers Conference (GDC) is expected 2025.

Must Read

Leave a Comment Cancel Reply