Google DeepMind’s Genie 4 builds AI worlds that talk and change on command

Google DeepMind released Genie 4, an AI-powered world model capable of generating photorealistic environments in real time. The simulated worlds include audio and characters capable of speech, and users can steer the simulations using text prompts as they run. The research preview became available to trusted testers on October 27.

Summary and key points written by AI from the headline and a short excerpt, so they can be incomplete or wrong. The Next Web did the reporting; read the original for the full story.