The first real-time interactive world model to generate audio natively: walk with the keyboard, rewrite scenes by text, with Gemini 3.8 Flash as the guiding agent planning multi-step events; scenes hold together about two minutes, double Genie 3. A research preview reaches trusted testers first, then Project Genie for AI Ultra in coming weeks. No AA / Pi / Physics-IQ listing — world models sit outside those boards, so no ranking follows.
Google DeepMind updates its world model to Genie 4: the first in the series to generate audio natively in real time, walked with a keyboard and rewritten by text on the fly, while Gemini 3.8 Flash directs and plans multi-step events.
Flash advances coding, multi-step reasoning and agent work at the same speed and price positioning; Flash Cyber is a separate security-focused variant.
The same model expands to the paid API, Gemini Pro/Ultra and development tools; shared context and long-decode conditions matter. Copilot has separate plans and gradual rollout.
A new generation of the real-time interactive world model: native audio, on-the-fly text steering and Gemini-planned multi-step events; a research preview reaches trusted testers first, then Project Genie for AI Ultra in coming weeks. No board entries — the scope gap stays stated.