Google DeepMind 發表 Genie 3：可即時互動的世界模型新前沿
Original: Genie 3: A new frontier for world models
Google DeepMind has officially unveiled its latest generation world model — Genie 3 — demonstrating a major breakthrough in generative AI's…
Google DeepMind 發表全新世界模型 Genie 3，為生成式 AI 領域帶來重大突破。該模型能以每秒 24 幀（fps）的即時速度，生成可供用戶自由導航與互動的動態虛擬世界。Genie 3 不僅支援 720p 的高解析度，更能在長達數分鐘的互動過程中，保持場景與物理邏輯的高度一致性，這將為未來的遊戲開發、虛擬實境以及 AI 代理（Agents）的模擬訓練開闢全新途徑。
Google DeepMind has officially unveiled its latest generation world model — Genie 3 — demonstrating a major breakthrough in generative AI's ability to construct real-time interactive virtual environments. This technology marks an important step in AI's evolution from pure "content generation" toward "physical world simulation."
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on Google DeepMind Blog →Summaries are AI-generated; the original article is authoritative.