Google’s next Genie AI model generates more realistic experiences

Google announced Genie 4, its latest world model for generating interactive experiences using AI. The model features four main updates: more realistic worlds, real-time updates via natural language prompts, audio generation, and the use of Gemini 3.8 Flash under the hood to assist with simulations. Experiences can now last approximately two minutes, doubling the one-minute limit of the previous Genie 3 model. Google positions Genie 4 as a tool for filmmakers' pre-visualization, game prototyping, and robot training scenarios, though it warns that as simulations run longer, details and object permanence can shift over time. Currently available as a research preview to trusted testers, Genie 4 will "come soon" to Google AI Ultra subscribers, and a waitlist has been opened for those wishing to try it in Project Genie.

(Source：The Verge)