Despite a decade of AI growth, Cook says, there's no method yet to measure what exactly an AI model has captured and what it has not. Muse is able to provide grainy gifs of one fairly simple video game based on seven years of footage, but it is not a solution for holding everything about a game or every possible outcome of what players could do.

Using AI to produce footage of video games with a consistent world and rules could prove useful to game designers

Microsoft debuts Muse, a world and human action model that uses generative AI to put together gameplay snippets.

Microsoft debuted Muse, a generative AI model that can be trained to output video game visuals and predict controller inputs. The company describes the technology as the future of gameplay ideation, not as something to be used in place of human creativity during game development.

Microsoft has revealed its experimental MUSE generative AI technology that can create gameplay sequences that was trained using real player inputs.

Microsoft views the Muse AI model more as a tool for game preservation and concept brainstorming than a way to replace human-made video games.