On October 28, Google recently announced the launch of its new-generation AI world model, Genie 4. Powered by Gemini 3.8 Flash, this model further enhances the realism of AI-generated interactive environments and introduces new features such as real-time scene modification and automatic audio generation. Unlike traditional image generation models that primarily output static images or videos, Genie 4 can create virtual worlds where users can participate and interact. Users can manipulate scenes in real time through natural language, such as moving the camera, changing the weather, introducing new characters, etc. Each world will instantly generate native audio, including ambient sounds, music, and interactive dialogue. Currently, Genie 4 has begun to be made available to a small group of trusted testers and is planned to be accessible to Google AI Ultra subscribers. It will also be provided to early access partners through the Gemini API and AI Studio. Related technologies are expected to find applications in fields such as game development, film and television production, and robot training.