Google has launched its most powerful world model, Genie 4

Same story6 other outlets also reported this

How the accounts differ:The Verge states the model supports up to two minutes of scenes, while Ars Technica and TechCrunch mention improvements in physics and character simulation but do not specify the scene duration.

1. The Verge · AI·00:00·First

   Google Genie 4 World Model Released: Supports More Realistic Interactive Experience

2. Ars Technica · AI·00:00·+0 min

   DeepMind releases Genie 4 world model, claims physics and character simulation are more realistic

   Adds:DeepMind mentions the model's integration with Gemini AI and the use of Gemini 4 Argon for task decomposition.

3. Google DeepMind·00:01·+2 min

   Google DeepMind releases world model Genie 4

   Adds:Google DeepMind notes the model's ability to generate native audio and voice dialogue.

4. TechCrunch · AI·00:30·+31 min

   Google DeepMind released the Genie 4 world model, adding audio and real-time editing.

   Adds:TechCrunch mentions the model's integration with Gemini AI and the use of Gemini 4 Argon for task decomposition.

5. The Decoder·01:25·+1 h 25 min

   DeepMind Genie 4 Released: Exploring the Frontier of Modern Intelligent Agent Design

   Adds:The Decoder mentions the integration with SynthID for watermarking AI-generated content.

6. ITHome · AI·07:04·+7 h 5 min

   Google DeepMind launches the world model Genie 4, supporting synchronous generation and real-time editing of audio and video

7. ITHome · AI·07:42·+7 h 42 min

   Google DeepMind releases Genie 4 world model, supporting real-time natural language rewriting and native audio

8. ITHome · AI·07:55·+7 h 56 min·Reading now

   Google has launched its most powerful world model, Genie 4

9. MarkTechPost·15:34·+15 h 35 min

   Google DeepMind Releases Genie 4 Real-Time World Model, Natively Generating Audio

In order of publication · later reports are added as they appear · Compared by AI from each outlet’s title and summary