Google DeepMind Unveils Genie 4, Its Next-Generation AI World Model

Google DeepMind has unveiled Genie 4, its next-generation AI world model. Unlike a typical AI-generated video, Genie 4 creates interactive environments that users can explore and modify in real time.
Users can change the weather, introduce objects or characters, and interact with people who move, react, and speak. The model also generates native audio, including ambient sounds and dialogue, while simulating physics and collisions.
Built on Gemini Omni, Genie 4 uses Gemini's reasoning capabilities to maintain continuity and simulate multi-step events. Potential applications include robotics training, gaming, and filmmaking.
Genie 4 is currently available to trusted testers, with access coming to Google AI Ultra subscribers through Project Genie and select API partners.