如果你以为 Windows Recall 已经够吓人了，那接下来可要坐稳了。微软正准备将更多人工智能功能强行塞进其桌面操作系统，让 Copilot 能够访问你电脑上的每一文件。不过别担心，微软坚称这完全安全，因为驱动这些功能的智能体将完全运行在你的本地电脑上——至少在某些时候是这样。微软将这项新功能称为“混合智能”，它是在新款搭载 Nvidia N1X 芯片的 Surface Laptop 一同发布的。
If you thought Windows Recall was creepy, buckle up. Microsoft is about to shoehorn even more AI into its desktop operating system, giving Copilot access to every file on your PC. But don't worry, Redmond insists it's totally secure and safe since the agents powering the functionality will run entirely on your PC — some of the time. Microsoft describes the new functionality, announced alongside a new Nvidia N1X powered Surface Laptop, as "hybrid intelligence."
基于微软的 HydraFusion 模型路由器，Windows 应用和 Copilot 功能很快就能在合适时使用本地模型，在不合适时则使用云端模型。例如，Windows 可能会在简单或涉及隐私的任务中使用本地模型，而对于复杂或对性能要求高的请求，则可能选择 OpenAI 的 GPT-6 或 Anthropic 的 Claude。本地智能体将在微软的执行容器（MXCs）中运行，这是一种在运行时应用精细权限控制的智能体沙盒。
Built atop Microsoft's HydraFusion model router, Windows apps and Copilot features will soon be able to use local models when it makes sense and cloud-based models when it doesn't. For example, Windows might use a local model for simple or privacy-sensitive tasks, or decide complex or performance-sensitive requests need OpenAI's GPT-6 or Anthropic's Claude. Local agents will run in Microsoft's Execution Containers (MXCs), agent sandboxes with fine-grained permissions applied at runtime.
据微软 Windows 和设备执行副总裁 Pavan Davuluri 称，MXCs 意味着 Windows 如今已成为“最安全的智能体平台”。（这一说法听起来确实很有说服力，因为模型永远不会离开沙盒，而路由器也绝不会出错。）为了支持这种混合智能功能，微软正在将其基于 ONNX 运行时构建的推理框架 Windows ML 的兼容性扩展至 Llama.cpp——这是本地 AI 推理中性能最高的引擎之一。
According to Microsoft EVP of Windows and Devices Pavan Davuluri, MXCs mean Windows is now "the most secure platform for agents." (That claim will surely age well because models never escape their sandboxes and routers never misbehave.) To support this hybrid intelligence functionality, Microsoft is extending support for Windows ML, its inference framework built on the ONNX runtime, to Llama.cpp – one of the highest-performing inference engines for local AI inference.
通过增加对 Windows ML 的支持，Llama.cpp 应该能够利用更广泛的加速器。微软计划于下周将混合智能功能推出至其 AI 编程助手 GitHub Copilot，并在未来几个月内逐步覆盖其 Copilot 应用。这些全新的 Copilot 功能看起来、听起来都跟“穿西装的 OpenClaw”极为相似。Copilot 的智能体功能不会访问你的整个文件系统，但通过集成 Microsoft Office，它将开启高级搜索功能和其他生产力任务的可能性。
By adding support for Windows ML, Llama.cpp should be able to take advantage of a broader range of accelerators. Microsoft is rolling out its hybrid intelligence functionality to GitHub Copilot — its AI code assistant — next week and its Copilot app over the next few months. The new Copilot features look and sound suspiciously like OpenClaw in a business suit. Copilot's agentic functionality will not have access to your entire file system, opening the door to advanced search functionality and productivity tasks through integrations with Microsoft Office.
在一场演示中，微软展示了 Copilot 如何帮助用户查找和整理税务文件，随后生成一封附有这些文件的电子邮件，并发送给会计师。微软强调，只有在用户主动要求时，它才会查看用户的文档。Windows 还将引入由 AI 增强的搜索功能，让用户能够更轻松地找到深色模式等设置。该系统还将配备一种对话式界面，用于执行向朋友发送短信等任务。
In a demo, Microsoft showed how Copilot could be used to find and organize a user's tax documents, then draft an email with those files attached, addressed to an accountant. Microsoft insists it'll only go snooping through your docs if you ask it to. Windows is also getting AI-enhanced search functionality enabling users to surface settings like dark mode. The OS will also get a conversational interface to perform tasks like sending a text message to a friend.
最后，对于那些希望突破微软“智能体”框架限制的用户，微软正在推出一项全新的引导体验，使部署 OpenClaw 等智能体工具的过程更加简单和安全。将敏感任务保留在本地设备上，或许有助于缓解自 2024 年首批 Copilot+ PC 搭载高通骁龙 X Elite SoC 问世以来一直困扰微软的隐私担忧。此外，将低优先级、低复杂度的请求保留在设备上，也有助于减轻微软服务器的负担。
Finally, for those interested in coloring outside Microsoft's agentic lines, the company is rolling out a new onboarding experience to make deploying agent harnesses like OpenClaw a bit easier and more secure. Keeping sensitive tasks on device may help to assuage anxieties over privacy, which have dogged Microsoft since the first Copilot+ PCs arrived in 2024 alongside Qualcomm's Snapdragon X Elite SoCs. It should also help to reduce the load on Microsoft's servers by keeping low-priority, low-complexity requests on devices.
不过，在本地运行这些模型可能对电池续航、风扇噪音和任务质量产生影响，这或许会让许多用户望而却步。®
That said, the impact of running these models locally on battery life, fan noise, and workload quality could prove a turnoff for many users. ®