DeepMind unveils Genie 4 world model promising more realistic physics and humans
Google DeepMind has unveiled Genie 4, an updated world model that promises more realistic physics and humans, building upon the success of its predecessor, Genie 3. This new version supports midstream parameter changes, allowing users to alter elements like weather or camera position, with Gemini assisting in steering the simulation. Genie 4 represents a significant advancement in world models, a key focus for AI labs globally.
时间与来源
时间显示为 UTC
显示时区：UTC
本地时区尚不可用，暂时显示 UTC。
发布当时偏移：UTC+02026年10月27日 16:00 UTC
收录当时偏移：UTC+02026年10月27日 17:00 UTC
- 发布
- 2026年10月27日 16:00
- 收录
- 2026年10月27日 17:00
- 来源类型
- 媒体报道
- 档位
- 专业媒体
- 信源状态
- 正常
档位是按信源手工设定的编辑判断，不是逐条打分。
Last year, Google DeepMind sent gaming stocks tumbling with the reveal of its Genie 3 world model. Since then, world models have become a major focus of AI labs around the world, but Google isn’t resting on its laurels. Researchers have been hard at work on an updated model that improves on Genie 3 in almost every way. And if you pay Google enough money, you might actually get to use Genie 4 before too long.
It’s easy to look at the output of Genie 4 and see a video game, which is why Genie 3 caused so much consternation in the gaming industry. DeepMind doesn’t think about it that way, though. According to Google, world models are a key element in the march toward artificial general intelligence (AGI). A world model creates a virtual world, but it doesn’t require pre-rendering environments or programming interactive elements. You simply tell the model what you want, and it generates the experience frame by frame in real time as you explore it.
DeepMind says this technology could create infinite training environments for physical robots or unlock new avenues of rapid prototyping for creative fields. Of course, that requires the model to accurately simulate what you want. Genie 4 has several improvements that make its simulations more useful, and that’s thanks in part to Google’s updated Gemini models.
DeepMind says Genie 4 is better at simulating physics.
When you prompt a world into existence in Genie 4, it leverages Gemini 3.8 Flash as a guiding agent to break down goals and evaluate each output frame. This helps keep the simulation on track, letting you move through varying environments without losing the original context. However, DeepMind notes that Genie 4 worlds still only remain consistent for a couple of minutes before they forget how things started.
Like Genie 3, the new version supports changing the parameters midstream. You can change the weather, add elements, or move the camera, and Gemini will help steer the simulation with each update. This is similar to the way reasoning models generate additional internal prompts to zero in on the right output tokens.