[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-microsoft-copilot-agent-mode-vibe-working-office":3,"topics-all":36,"news-related-aa7e6e41-1c92-4212-af26-a7020f9e2185":55},{"id":4,"title":5,"summary":6,"content":6,"original_url":7,"source_id":8,"tags":9,"translations":23,"news_slug":29,"published_at":30,"created_at":31,"modified_at":32,"is_published":33,"publish_type":34,"image_url":13,"view_count":35},"aa7e6e41-1c92-4212-af26-a7020f9e2185","Microsoft Copilot Agent Mode上线：从被动助手到实时编辑的AI Agent进化","Microsoft本周向Office套件（Word、Excel、PowerPoint）推出Copilot Agent Mode，将其作为Microsoft 365 Copilot和Premium订阅用户的默认体验。这个被内部戏称为vibe working的新模式，标志着AI助手从被动问答向主动操作文档的核心转变。\n\n此前Copilot在Office中主要扮演被动角色——回答问题、生成文本片段，但无法直接在文档画布上执行编辑操作。Microsoft Office产品组副总裁Sumit Chauhan坦承，这是因为基础模型的能力尚不足以可靠地执行多步编辑指令。过去一年中，模型在指令遵循、推理和整体质量方面的显著进步，使得Agent Mode成为可能。\n\nAgent Mode的核心特性包括：用户可以在侧边栏中实时观察Copilot的每一步操作过程；在Excel中直接修改工作簿，添加公式和表格；在PowerPoint中更新现有幻灯片内容，同时保持企业模板样式的一致性。关键突破在于多步编辑的可靠性——AI现在能够在执行复杂编辑时保持用户的原始意图不丢失。\n\n这一更新反映了整个行业从chatbot向agent的演进趋势。当AI能够直接操作应用界面而非仅输出文本时，人机交互的效率将产生质的飞跃。对于开发者而言，Agent Mode也意味着Office正在成为一个可编程的AI操作平台。","https:\u002F\u002Fwww.theverge.com\u002Fnews\u002F917328\u002Fmicrosoft-agent-mode-vibe-working-office-word-excel-powerpoint","05ad777c-69bc-46a5-bca4-df8e4b3c8ee5",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"40269b40-7942-4650-9672-ed2e6524d37a","ai-technology",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"e82b2d09-81b2-43d1-977e-e018443b3c14","coding-agent",{"id":18,"name":19,"slug":19,"description":13,"color":13},"01598627-1ea6-4b27-a5d8-874971571a71","llm",{"id":21,"name":22,"slug":22,"description":13,"color":13},"42e59a88-7795-47dc-a334-ef1e72c24347","openai",[24],{"id":25,"lang":26,"title":27,"summary":28,"content":13},"c5ac2fbd-5da9-4673-814c-13cdfe76080b","en","Copilot Agent Mode: from passive helper to live editor","Microsoft this week rolled out Copilot Agent Mode across the Office suite (Word, Excel, PowerPoint) as the default experience for Microsoft 365 Copilot and Premium subscribers. Internally nicknamed \"vibe working,\" the new mode marks a core shift for AI assistants — from passive Q&A to actively operating on documents.\n\nPreviously, Copilot played a mostly passive role in Office: answering questions, generating text snippets, but unable to execute edits directly on the document canvas. Sumit Chauhan, VP of Microsoft's Office product group, candidly admitted this was because the underlying models weren't yet reliable enough at multi-step editing. Over the past year, significant improvements in instruction following, reasoning, and overall quality have finally made Agent Mode viable.\n\nAgent Mode's core features include: users can watch Copilot's every step in real time in a side panel; in Excel, the assistant can directly modify workbooks, adding formulas and tables; in PowerPoint, it can update existing slide content while keeping enterprise template styles consistent. The key breakthrough is reliability in multi-step editing — AI can now preserve user intent while executing complex edits.\n\nThis update reflects the industry-wide shift from chatbot to agent. When AI can directly operate application interfaces rather than just output text, the efficiency of human-computer interaction takes a qualitative leap. For developers, Agent Mode also signals that Office is becoming a programmable AI-operations platform.","microsoft-copilot-agent-mode-vibe-working-office","2026-04-23T13:10:00Z","2026-04-23T13:13:02.334402Z","2026-08-19T02:08:40.142862Z",true,"agent",144,[37,46],{"slug":38,"tag_slug":38,"title_zh":39,"title_en":40,"intro_zh":41,"intro_en":42,"id":43,"is_active":33,"created_at":44,"modified_at":45},"ai-for-science","AI for Science 2026：从 UniPert 到 GPT-Rosalind 的硬核进化","AI for Science 2026: from UniPert to GPT-Rosalind","生命科学、化学材料、物理世界模型——AI 正在从\"语言工具\"变成\"实验伙伴\"。本专题收录 AI 在三大科学方向的关键节点：UniPert 统一基因与化学扰动空间、GPT-Rosalind 端到端生命科学推理、达摩院 AI 智能体 28 小时找到 4 种超导新材料、Anthropic Claude Science 把工作台做成标准品。","From language tool to lab partner — AI is reshaping life sciences, chemistry\u002Fmaterials, and physical world models. This topic covers the key milestones: UniPert unifying genetic-chemical perturbation spaces, GPT-Rosalind's end-to-end life-sciences reasoning, DAMO's AI agent discovering 4 superconducting materials in 28 hours, and Anthropic's Claude Science workbench going mainstream.","988a4300-5fab-41c4-b5d8-63711a2dc757","2026-09-10T01:34:15.296649Z","2026-09-10T01:34:15.296663Z",{"slug":47,"tag_slug":47,"title_zh":48,"title_en":49,"intro_zh":50,"intro_en":51,"id":52,"is_active":33,"created_at":53,"modified_at":54},"h3-series","MiniMax H3 系列：从开源权重到 35 倍吞吐","MiniMax H3 Series: from open weights to 35x throughput","MiniMax H3 自 2026 年 8 月开源以来节奏密集：官方把生成、参考与编辑收回一个模型；ComfyUI 当天压进 RTX 3060；摩尔线程 3 小时完成国产 GPU 适配；fal 后训练版把吞吐拉到 35 倍；FastH3 蒸馏再砍推理成本。本专题持续追踪 H3 的发布—开源—蒸馏—部署全链路。","Since MiniMax open-sourced H3 in August 2026 the pace has been relentless: one unified omni-modal model, same-day ComfyUI support down to an RTX 3060, a 3-hour Day-0 port to Moore Threads GPUs, fal's post-trained H3 Max at 35x throughput, and FastH3 distillation cutting inference cost further. This topic tracks the full H3 chain — release, open weights, distillation, deployment.","83ef0daa-3c31-4cb3-86ed-e5ee58654d5f","2026-09-08T07:33:19.942193Z","2026-09-08T07:33:19.942209Z",{"items":56},[57,62,67,72,77,82],{"id":58,"title":59,"news_slug":60,"published_at":61},"3332cb66-6441-4d69-94c2-6618fc6ce1b2","GPT-5.5 系统提示词惊现「哥布林禁令」：一次控制模型行为的真实技术案例","gpt-5-5-codex-goblin-system-prompt-ban","2026-04-30T01:05:00+00:00",{"id":63,"title":64,"news_slug":65,"published_at":66},"5535b4e4-21de-4ed6-a9bb-2b4d824e6568","F-Droid 一次更新的 102 款应用,72.5% 主要是 AI 写的","f-droid-72-percent-ai-written-audit","2026-09-15T15:12:16+00:00",{"id":68,"title":69,"news_slug":70,"published_at":71},"b1645fba-d364-47e6-97da-06868f98d987","Linux 内核 7.x 每版近 2000 个 CVE:AI 帮倒忙,维护者不堪重负","linux-kernel-cve-ai-overwhelmed","2026-09-04T00:00:00+00:00",{"id":73,"title":74,"news_slug":75,"published_at":76},"407d6137-c0c6-4fde-84c1-4432b53e4cc4","Codex 把 LibreOffice 塞进桌面:1.7GB 工具栈暴露 AI 客户端的真实成本","codex-bundles-libreoffice-ai-desktop","2026-09-03T03:00:00+00:00",{"id":78,"title":79,"news_slug":80,"published_at":81},"4afbd081-d5dd-4595-80f8-dd72c69a136a","GPT-5.5 让模型在发布前先改自己跑的引擎：这不是新模型,是 OpenAI 的 release 范式更新","gpt-5-5-openai-release-paradigm","2026-08-03T18:00:00+00:00",{"id":83,"title":84,"news_slug":85,"published_at":86},"de219584-58fc-45ad-91ea-0049a5cbcf10","OpenAI 开源 Codex Security CLI:把 AI 安全检测塞进每个 PR","openai-codex-security-cli-opensource","2026-07-29T10:30:00+00:00"]