Microsoft has announced Muse, a generative AI model that can "generate game visuals, controller actions, or both". The company is calling it the first example of a WHAM, or World and Human Action Model.
In a post on the official Microsoft website, the company reveals that Muse was developed in conjunction with Hellblade: Senua's Sacrifice studio Ninja Theory. The model was trained on Ninja Theory's battle arena game Bleeding Edge.
A followup post on the Xbox website says Muse can "create consistent and diverse gameplay rendered by AI", which Microsoft calls "a major step toward generative AI models that can empower game creators". I'm not so sure about that one myself.
In both posts, Microsoft gives some examples of the kind of gameplay Muse is currently able to generate. Honestly, I might just not be infected by the tech brain worms, but to me it looks pretty low-quality.
It's not just me, either; The Verge confirms that Muse is currently only capable of generating gameplay at a paltry 300 x 180 resolution, and not only that, but it's also limited to 10 frames per second. Find me a PC gamer that would be happy with those numbers.
I know,...
