Skip to content

Google DeepMind releases Genie 4, a real-time world model that simulates interactive environments from text

Google DeepMind · · 30-second read

Share

Top comments from YouTube.

    This story is from November 18, 2026. For the latest, see today's news.

    November 18, 2026 · AI Tech

    Google DeepMind has released Genie 4, an advanced world model that simulates interactive environments in real time rather than generating static video. Users can convert text into explorable 3D worlds within seconds, navigate scenes with keyboard controls, and issue live prompts to direct action on the fly.

    The model is integrated into Project Genie, which includes a built-in agent that lets teams create custom applications mapped to keyboard shortcuts. These can trigger character movement, dialogue, and in-world events in real time. Developers can use text prompts as repeatable seeds for tasks ranging from creative prototyping to training robotics systems.

    Genie 4 is now available to eligible Google AI Ultra subscribers, marking a step toward more dynamic and controllable AI-generated environments.

    Read the full story at Google DeepMind

    This is an AI-written summary. The original reporting belongs to Google DeepMind. How we write these · Spot a mistake?

    Get the AI brief every morning.

    The five AI stories that matter each morning: startups, money, jobs, tech and what's coming next. Free, and one click to unsubscribe. See our Privacy Policy.