Google DeepMind Unveils Genie 4, a World Model With More Realistic Physics and Humans

What happened

Google DeepMind has unveiled Genie 4, an updated world model that improves on Genie 3 in almost every way, including more realistic physics and humans. The model generates virtual worlds frame by frame in real time as users explore them, and DeepMind says the technology could provide training environments for physical robots or support rapid prototyping in creative fields.

Read next

• More changes in today’s briefingIntroducing GPT-6.1 Terra

Reported by 9 sources

The story so far

Google DeepMind has released Genie 4, a model for generating interactive virtual worlds, as a research preview limited to trusted testers. Google says access is coming soon to Google AI Ultra subscribers through Project Genie and early access partners through the Gemini API and Google AI Studio; TechCrunch reports that rollout is planned in the coming weeks. Google has opened a Project Genie waitlist, and Logan Kilpatrick said Genie 4 will bring the model to the API for the first time. DeepMind says Genie 4 adds native audio and character dialogue, with natural-language prompts letting users change environments and soundscapes during simulations. Google AI says users can change the weather, move the camera and introduce new elements. DeepMind says Gemini 3.8 Flash guides multi-step events by observing scenes, planning actions and checking progress. The Verge reports that experiences can last about two minutes, up from one minute with Genie 3, though scene details and object consistency can shift over time. TechCrunch also reports problems with audio accuracy and text legibility. DeepMind says object permanence, physical interactions and long-term consistency remain research challenges.