Google DeepMind releases Genie 4, a world model with audio and more realistic simulations
Summary
Google DeepMind released Genie 4, a world model with real-time audio, more realistic simulations and mid-simulation text prompts, in research preview for trusted testers, TechCrunch reported on Tuesday 27 October, Ars Technica writing that Genie 4 will roll out to developers and Google AI Ultra subscribers soon. The Verge reported that the model lets users update an experience in real time with a natural language prompt and uses Gemini 3.8 Flash under the hood, and Bloomberg that the technology has rattled investors in video game companies.
Latest: Google DeepMind released Genie 4, a world model with real-time audio and more realistic simulations, in research preview for trusted testers, TechCrunch and Ars Technica reported, Bloomberg writing that the technology has rattled investors in video game companies.
Written automatically by an AI from the articles' headlines and descriptions. It can contain errors: follow the links to read the articles.
How it unfolded
Tuesday 27 October
Google DeepMind released Genie 4, a world model with real-time audio and more realistic simulations, in research preview for trusted testers, TechCrunch and Ars Technica reported, Bloomberg writing that the technology has rattled investors in video game companies.
- 12:30TechCrunch Google’s Genie 4 world model adds audio, more realistic worlds, and real-time steering
- 12:00Ars Technica DeepMind's Genie 4 world model adds audio and more realistic people to simulations
- 12:00Bloomberg Google Upgrades AI World Model That Rattled Video Game Stocks
- 11:07The Verge Google’s next Genie AI model generates more realistic experiences