原标题：Google’s next Genie AI model generates more realistic experiences
Google 发布 Genie 4 世界模型，用于生成 AI 交互体验。新模型带来四项主要更新：更逼真的世界、用自然语言提示词实时更新体验、可生成音频，并采用 Gemini 3.8 Flash 辅助模拟；体验时长从 Genie 3 的一分钟提升到约两分钟。Google 将其定位为电影预可视化、游戏原型制作和机器人训练场景等用途的工具。
原文列出了 Genie 4 相对上一代的四项主要更新和体验时长变化，读者可以据此了解世界模型的能力演进方向。
本页的摘要、推荐理由与解读出自 AIsa Studio 的 AI 风向智能体，原文版权归原作者所有。
Jay Peters
is a senior reporter covering technology, gaming, and more. He joined The Verge in 2019 after nearly two years at Techmeme.
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.
Follow topics and authors from this story to see more like this in your personalized homepage feed and to receive email updates.
原文版权归 The Verge · AI 及原作者所有，本站转载仅供阅读。如需删除，请联系 support@aisa.one。
Google DeepMind 发布了新一代世界模型 Genie 4，旨在提升 AI 交互的真实度和实时交互能力。Genie 4 支持约两分钟的交互体验，相较前代模型，它在逼真度、物理模拟和音频生成方面进行了重大更新。 在功能与技术层面，Genie 4 是首个支持直接生成原生音频的世界模型，能够模拟环境音、音乐和实时对话，并支持对空气动力学、碰撞等物理场景进行模拟。用户可以使用自然语言提示词实时修改模拟环境，并在实时探索动态环境中观察场景的响应。 模型基于 Gemini 家族构建，具体由 Gemini Omni 负责世界外观和行为，Gemini 3.8 Flash 作为引导智能体，负责分解目标、审查帧并实时调整计划。该模型已被应用于电影预可视化、游戏原型制作以及机器人训练场景。 关于可用性，Google DeepMind 发布该模型时指出，Genie 4 目前仅作为研究预览面向可信测试者开放。早先有报道称该模型需付费方可使用，后续公告确认未来将通过 Project Genie 中的 Google AI Ultra 订阅者、Gemini API 和 Google AI Studio 早期合作伙伴等渠道进行开放。目前模型仍处早期阶段，长会话过程中视觉细节和物体恒存性仍会存在漂移问题，且实时音频准确度有待提升。
Studio