Google’s next Genie AI model generates more realistic experiences

<figure> <img alt="A screen capture from a video created by Google’s Genie 4 world model shows a close-up angle of two people riding a motorcycle. " data-caption="" data-portal-copyright="" data-has-syndication-rights="1" src="https://platform.theverge.com/wp-content/uploads/sites/2/2026/10/Screenshot-2026-10-26-at-3.00.35-PM.png?quality=90&#038;strip=all&#038;crop=0,0,100,100" /> <figcaption> </figcaption> </figure> <p class="wp-block-paragraph">Google announced today <a href="https://deepmind.google/blog/genie-4-a-new-generation-of-world-simulation">its Genie 4 world model</a> for generating interactive experiences using AI. The company says the model has four main updates: It allows for more realistic worlds, lets users update an experience in real time with a natural language prompt, can generate audio, and uses Gemini 3.8 Flash under the hood to help with its simulations. It also can create experiences that are about two minutes long, up from one minute for the previous Genie 3 model.</p> <p class="wp-block-paragraph">Google is pitching Genie 4 as a tool that could be helpful for things like pre-visualization for filmmakers, prototyping game ideas, and making training scenarios for robots. But the …</p> <p><a href="https://www.theverge.com/tech/1019076/google-genie-4-ai-model">Read the full story at The Verge.</a></p>