Google’s next Genie AI model generates more realistic experiences
TL;DR
Google announced today its Genie 4 world model 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.
Nauti's Take
For a small team, Genie 4 is primarily worth testing as a rapid prototyping tool: take one scene, game concept, or robotics scenario and measure how reliably edits, audio, and interactions hold up across two minutes. Before using it in production, verify access terms, pricing, export options, and how much control you retain over the generated experience.
Sources