Google’s next Genie AI model generates more realistic experiences

Google announced Genie 4, a world model designed to generate interactive experiences. Currently in research preview for trusted testers, the model introduces four primary updates: more realistic simulations, the ability to update experiences in real time via natural language prompts, and integrated audio generation. Developed by Google DeepMind, Genie 4 utilizes Gemini 3.8 Flash to power its capabilities, allowing users to steer simulations mid-process while creating more immersive and believable digital environments for various AI-driven applications.