Google DeepMind releases Genie 4 world model research preview
What happened
Google DeepMind released the Genie 4 world model on October 28 as a research preview for trusted testers. The model generates environments frame by frame in real time as they are explored, with no pre-rendering or hand-coded interactions. It supports native audio, character dialogue and live scene edits in natural language, such as changing weather, camera angle or adding people and objects. DeepMind says physics simulation and character performance improved, with uses in robot training and creative prototyping. Scene consistency holds for about two minutes, twice the previous generation. The Decoder later reported that Gemini 3.8 Flash watches the screen, breaks down tasks and adjusts plans, while in the demo Gemini 4 Argon directed a simulated robot, Apollo, in checkers. Access is limited to some testers, and limits remain: drift in detail and object persistence, complex physical interactions, long-term consistency, audio accuracy and on-screen text legibility.
Written by AI from the coverage · updated 28 minutes ago
Coverage
Follow the reports to see the story from different sides.
- The DecoderGoogle Deepmind's Genie 4 puts a modern spin on agent designs that predate LLMs
Google DeepMind 推出实验性世界模型 Genie 4，支持实时交互场景、声音生成和角色对话，目前仅向部分测试者开放。Gemini 3.8 Flash 持续观察画面、拆解任务并调整计划，Gemini 4 Argon 则在演示中指挥模拟机器人 Apollo 下跳棋。
- TechCrunch · AIGoogle’s Genie 4 world model adds audio, more realistic worlds, and real-time steering
Google DeepMind 于周二发布 Genie 4 研究预览，新增实时音频与模拟中的提示词编辑，生成更逼真、可交互的世界。模型可实时改变天气、镜头角度或添加人物与物体，保持场景一致性最长两分钟，是前代的两倍，但仍存在细节漂移、音频准确性和场景文字可读性问题。
- Google DeepMindPickGoogle DeepMind releases Genie 4 world model with native audio and real-time interactive simulation
Google DeepMind released Genie 4, a world model with native audio, interactive dialogue and real-time scene edits in natural language. It is in research preview for trusted testers. In simulations, Gemini 3.8 Flash keeps observing the scene, breaking down goals and checking progress to hold multi-step events together. The model still drifts on object persistence, complex physical interactions and long-term consistency.
- Ars Technica · AIDeepMind unveils Genie 4 world model promising more realistic physics and humans
Google DeepMind 发布 Genie 4 世界模型，称其相比 Genie 3 有多项改进，并承诺更逼真的物理模拟与人物。世界模型根据用户描述，在探索过程中逐帧实时生成体验，无需预渲染环境或编写交互元素。DeepMind 称该技术可用于物理机器人的训练环境和创意领域的快速原型制作，Genie 4 的改进部分得益于更新后的 Gemini 模型。
- The Verge · AIGoogle’s next Genie AI model generates more realistic experiences
Google 今天宣布世界模型 Genie 4，可生成更逼真的交互体验，支持用自然语言提示词实时修改体验并生成音频。模型使用 Gemini 3.8 Flash 辅助模拟，体验时长从 Genie 3 的一分钟增至约两分钟，Google 提醒较长模拟中的细节和物体持续性可能发生变化。
Heat over time
Not enough continuous observations to draw a trend yet.