谷歌发布新一代世界模型 Genie 4：生成更逼真交互体验，时长增至两分钟

谷歌今天正式发布了用于通过 AI 生成交互体验的 Genie 4 世界模型。该公司表示，该模型迎来了四项核心升级：能够生成更加逼真的虚拟世界、允许用户使用自然语言提示词实时更新体验、具备音频生成能力，并在底层采用 Gemini 3.8 Flash 协助进行仿真模拟。此外，它能生成的体验时长约为两分钟，相比上一代 Genie 3 模型的一分钟实现了翻倍。

谷歌将 Genie 4 定位为一款实用工具，可用于电影制作人的前期视觉预览（pre-visualization）、游戏创意的原型设计，以及为机器人创建训练场景等任务。但该公司也发出提醒，随着仿真运行时间的延长，画面细节以及物体的恒常性（object permanence）可能会随时间发生漂移。

我目前尚未亲自试用 Genie 4——该模型首先作为“研究预览版”向“受信测试人员”推送——因此暂时无法对比它与搭载 Genie 3 的 Project Genie 之间的实际差距，我此前曾使用后者生成过劣质的任天堂山寨游戏。不过，谷歌公布了一系列示例，展示了新模型的强大能力。

谷歌表示，Genie 4“即将向 Google AI Ultra 订阅用户推出”，目前已经开放了候补名单，用户可以申请在 Project Genie 中上手体验。

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.

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 company warns that, as simulations run longer, details and object permanence can shift over time.

I haven’t been able to try Genie 4 for myself — it’s launching first as a “research preview” to “trusted testers” — so I can’t tell you how it compares to the Genie 3-powered Project Genie, which I used to generate bad Nintendo knockoffs. But here are some examples from Google demonstrating what’s possible with the new model.

Genie 4 will be “coming soon” to Google AI Ultra subscribers, Google says, and the company has opened a waitlist where you can apply to be able to try it in Project Genie.