Runway ML 发布了 Project Continuum，这是一个探索操作系统新实时视频界面的研究应用。该项目引入了“Portals”（充当交互式动画叠加层）和“Visual Thinking”（可视化编码代理步骤）等功能。目标是将静态媒体转变为动态、交互式模拟，并增强用户对复杂自主工作流的理解。 AI
影响 引入了新颖的实时视频界面，可能会改变用户与 AI 代理和复杂工作流的交互方式。
排序理由 这是一个来自知名 AI 公司的研究应用和新交互范式，但并非核心模型发布或重大的行业范围转变。
AI 生成摘要 · Google Gemini · 来自 6 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
Expand any media into an interactive real-time world simulation. Turn a fixed experience into immersive multi-modal simulations for people and agents. https://t.co/7t7Zst3ZLm
Visual Thinking is a new harness for coding agents. A real-time video model visualizes each step and tool call as it happens, so you can stay in the loop during complex autonomous workflows. https://t.co/ERhHpUkZlJ
Resize any video interface and the model recomposes the scene with spatial awareness. Click inside to interact with it directly, in real time. https://t.co/3Xdwfzq995
Portals have soft, dream-like edges that mark where generated content begins. Drag one onto the page and it sits alongside your content. https://t.co/vuIBf0nvzZ
As you browse, a real-time video model generates portals: animated, interactive overlays that illustrate any concept, place or simulation. https://t.co/AzrwAOS7JT
Introducing Project Continuum by @runwayml_labs, a new operating system research application built around real-time video interfaces. Today, we're sharing an early look at four new ways of interacting with your computer: Portals, Visual Thinking, Responsive Video Interfaces and …