Google’s next Genie AI model generates more realistic experiences

Google announced the Genie 4 world model, a new AI model that generates interactive experiences with four main updates: more realistic worlds, real-time updates with natural language prompts, audio generation, and use of Gemini 3.8 Flash. Genie 4 can create experiences up to two minutes long, an increase from the previous one minute limit. The model is being pitched as a tool for pre-visualization, game prototyping, and robot training scenarios. However, the company notes that as simulations run longer, details and object permanence can shift over time.