AI

Google DeepMind unveils Genie 4 world model with real-time audio and scene editing

Google DeepMind announced Genie 4, a world model available in research preview that generates interactive environments from prompts. It adds real-time audio, more realistic worlds and the ability to steer or edit scenes with natural-language prompts, including changes during a simulation. Genie 4 can keep a scene consistent for up to two minutes, double the limit reported for Genie 3, and improves physics and character realism. Google is pitching it for creative prototyping and robot-training scenarios.

AI-written summary, checked against the cited sources. How summaries work

Image: Ars Technica

What we know

Confirmed by several sources

Reported by one source

  • Genie 4 uses Gemini 3.8 Flash to assist with simulations. — Techmeme
  • Google described a possible hybrid approach combining Gemini-generated text or code with Genie simulations. — Slashdot

Coverage 5 publishers

  1. TechmemeFirst report

    Google’s next Genie AI model generates more realistic experiences

    Google announced today its Genie 4 world model for generating interactive experiences using AI. The company says the model has four main updates: It allows for more realistic worlds, lets users update an experience in real time with a…

  2. The Verge

    Google’s next Genie AI model generates more realistic experiences

    Google announced today its Genie 4 world model for generating interactive experiences using AI. The company says the model has four main updates: It allows for more realistic worlds, lets users update an experience in real time with a…

  3. Ars Technica

    DeepMind unveils Genie 4 world model promising more realistic physics and humans

    Last year, Google DeepMind sent gaming stocks tumbling with the reveal of its Genie 3 world model. Since then, world models have become a major focus of AI labs around the world, but Google isn't resting on its laurels. Researchers have…

  4. TechCrunch

    Google’s Genie 4 world model adds audio, more realistic worlds, and real-time steering

    Genie 4 can maintain a consistent scene for up to two minutes, double Genie 3's limit, and offers better physics and more humanlike characters.

  5. Slashdot

    Google's Genie 4 World Model Adds Audio, More Realistic Worlds

    An anonymous reader quotes a report from TechCrunch: Google DeepMind released its newest world model, Genie 4, in research preview on Tuesday. The latest model generates the most photorealistic and interactive worlds yet, allowing users to…

Earliest report first. Articles stay on their publishers’ sites; each link opens the original.