In August, we previewed Genie 3, a versatile world model that can generate diverse and interactive environments. Even in this early form, reliable testers have been able to create an impressive range of engaging worlds and experiences, and have discovered entirely new uses for it. The next step is to expand access through dedicated interactive prototypes focused on creating immersive worlds.
Starting today, we’re rolling out access to Project Genie to Google AI Ultra subscribers (ages 18 and older) in the United States. This experimental research prototype allows users to create, explore, and remix their own interactive worlds.
How are we promoting the global model?
A world model simulates the dynamics of your environment and predicts how it will evolve and how your actions will affect it. Google DeepMind has a history of agents for specific environments like chess and Go, but building AGI requires a system that navigates the diversity of the real world.
To address this challenge and support AGI’s mission, we developed Genie 3. Unlike explorable experiences in static 3D snapshots, Genie 3 generates a path forward in real time as you move and interact with the world. While simulating the physics and interactions of a dynamic world, its breakthrough consistency enables the simulation of any real-world scenario, from robotics, animation and fiction modeling to exploring locations and historical settings.
Based on model research with trusted testers from a variety of industries and disciplines, we are taking the next steps with Project Genie, our experimental research prototype.
How Project Genie works
Project Genie is a prototype web app powered by Genie 3, Nano Banana Pro, and Gemini that allows users to directly experiment with immersive world model experiences. This experience is centered around three core features:
