GoKawiilGoogle unveils Genie 4 world model with real-time editing and audio
Google announced Genie 4, a new AI world model that generates interactive experiences lasting up to two minutes, doubling the length possible with its predecessor Genie 3. The update adds real-time editing via natural language prompts, audio generation, and runs on Gemini 3.8 Flash, though Google warns object permanence can degrade over longer simulations.
GoKawiil's interpretation of the reporting above, not reported fact.
Google is positioning Genie 4 for uses like filmmaking pre-visualization, game prototyping, and robot training simulations, suggesting ambitions beyond novelty demos toward practical production tools. The limited 'trusted testers' rollout indicates the technology remains unproven at scale, and the acknowledged drift in longer simulations points to ongoing technical limits in world-model consistency.
- Genie 4 doubles experience length to about two minutes, up from one minute in Genie 3
- New features include real-time natural language editing, audio generation, and Gemini 3.8 Flash integration
- Access is limited to a research preview for trusted testers, with a waitlist for Project Genie and future Google AI Ultra availability
Source: theverge.com — Jay Peters, 2026-10-27
Published there as: “Google’s next Genie AI model generates more realistic experiences”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.