Google 发布 Genie 4 世界模型，生成更逼真交互体验
原标题：Google’s next Genie AI model generates more realistic experiences
AI 摘要
Google 发布 Genie 4 世界模型，可生成更逼真的交互式体验，支持自然语言实时更新、生成音频，底层使用 Gemini 3.8 Flash，体验时长从 Genie 3 的一分钟提升至约两分钟。该模型面向电影预可视化、游戏原型和机器人训练场景，但 Google 提示模拟时间变长后细节和物体恒存性可能漂移。Genie 4 先以研究预览形式向受信任测试者开放，并将很快提供给 Google AI Ultra 订阅用户，同时开放 Project Genie 试用等待名单。
正文节选
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’s next Genie AI model gener