Google DeepMind 发布 Genie 4 实时世界模型
原标题：Google Deepmind's Genie 4 puts a modern spin on agent designs that predate LLMs
AI 摘要
Google DeepMind 发布 Genie 4 交互式世界模型，可逐帧实时计算环境，并首次直接生成匹配的背景音效与角色对话；Gemini 模型在后台规划多步任务并持续调整模拟世界。该模型仍为实验性研究预览，长时程一致性与复杂物理存在局限，目前仅限部分测试者，后续将向 Google AI Ultra 订阅者开放。DeepMind 认为成熟后的世界模型可作为机器人与 AI 智能体的训练环境。
正文节选
Google Deepmind's Genie 4 puts a modern spin on agent designs that predate LLMs Key Points - Google Deepmind has introduced Genie 4, an interactive world model that calculates environments frame by frame in real time and, for the first time, directly generates matching background audio and character dialogue. - Gemini models steer events in the background, planning multistep tasks and continuously adapting the simulated world to user text prompts and changing conditions. - Genie 4 is still an ex