[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-anthropic-claude-dreaming-cross-session-memory":3,"topics-all":36,"news-related-489f9b2f-75f7-461b-b7c7-f440174122e2":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},"489f9b2f-75f7-461b-b7c7-f440174122e2","Anthropic 为 Claude 代理加入「梦境」机制：跨会话记忆终于实现了","在5月6日的Code with Claude开发者大会上，Anthropic宣布为Claude Managed Agents加入一种名为Dreaming的新机制。这个功能仍处于研究预览阶段，专为需要长时间运行、多代理协作的企业场景设计。\n\n所谓梦境，本质上是让AI在闲置时回顾近期会话和记忆存储，从中筛选值得长期保留的信息。与传统对话压缩（compaction）不同，compaction仅限于单次会话内的上下文管理，而Dreaming能够跨会话、跨代理识别模式，将分散的交互经验提炼为结构化记忆。\n\nAnthropic指出，Dreaming能发现单一代理无法察觉的规律——包括反复出现的错误、收敛的工作流偏好，以及跨团队共享的行为模式。这对于复杂项目的长期维护和知识传承有直接价值。\n\n从技术角度看，这一设计与Meta的记忆机制、OpenAI的记忆功能方向一致，但更强调多代理场景下的协作记忆共享。Anthropic将其定位为长程工作的基础设施升级，而非简单的功能叠加。\n\n个人观点：代理的记忆问题是这两年各厂商的主攻方向之一，但大多数实现仍停留在记住本次对话层面。跨会话、跨代理的持久记忆才是真正工程化的挑战。Anthropic如果能把这个能力产品化，对企业级AI应用落地会是重要一步。","https:\u002F\u002Farstechnica.com\u002Fai\u002F2026\u002F05\u002Fanthropics-claude-can-now-dream-sort-of\u002F","2af9d198-9418-4f26-85e4-4a8f3eede35a",[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},"23544f6a-eea1-4f05-aa8d-749ca862d5d2","anthropic",{"id":18,"name":19,"slug":19,"description":13,"color":13},"dca4d0ab-7994-43a7-839e-7756fc77344a","claude",{"id":21,"name":22,"slug":22,"description":13,"color":13},"01598627-1ea6-4b27-a5d8-874971571a71","llm",[24],{"id":25,"lang":26,"title":27,"summary":28,"content":13},"fbb8812e-9e4d-4603-b4f8-934ec3fc724d","en","Anthropic gives Claude agents dreams: cross-session memory","At the May 6 Code with Claude developer conference, Anthropic announced a new mechanism called Dreaming for Claude Managed Agents. This feature is still in research preview, designed for enterprise scenarios requiring long-running, multi-agent collaboration.\n\nSo-called dreaming, in essence, lets AI review recent sessions and memory storage when idle, screening out information worth long-term retention. Unlike traditional conversation compaction, which is limited to context management within a single session, Dreaming can identify patterns across sessions and agents, distilling scattered interaction experience into structured memory.\n\nAnthropic notes that Dreaming can discover patterns that single agents cannot perceive — including recurring errors, converging workflow preferences, and behavior patterns shared across teams. This has direct value for long-term maintenance and knowledge transfer in complex projects.\n\nFrom a technical perspective, this design aligns with Meta's memory mechanisms and OpenAI's memory features, but emphasizes collaborative memory sharing in multi-agent scenarios. Anthropic positions it as infrastructure upgrade for long-horizon work, not a simple feature overlay.\n\nPersonal view: agent memory is one of the main attack directions for vendors in the past two years, but most implementations still stay at remembering the current conversation. Cross-session, cross-agent persistent memory is the truly engineering challenge. If Anthropic can productize this capability, it would be an important step for enterprise AI application landing.","anthropic-claude-dreaming-cross-session-memory","2026-05-06T22:00:00Z","2026-05-06T22:05:00.735321Z","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},"390c2437-4e4f-45ec-8270-67c5bfa4fa47","ChatGPT、Claude、Grok、Gemini 罕见同时下线,周四早晨全球 AI 集体失声","chatgpt-claude-grok-gemini-thursday-outage","2026-09-05T06:00:00+00:00",{"id":63,"title":64,"news_slug":65,"published_at":66},"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":68,"title":69,"news_slug":70,"published_at":71},"f3d17d45-e1a8-4a1b-9449-6813aff06e49","Anthropic 让 Claude 自己修对齐:10 类失败全部见效,还超过人类研究员","claude-automated-alignment-researchers","2026-08-29T13:05:00+00:00",{"id":73,"title":74,"news_slug":75,"published_at":76},"39724847-fdc9-4199-ac46-311e7b49d385","Ramp 数据复盘 Fable 5:旗舰上市两月仅占企业 Anthropic 支出 11%,70 倍价差压住前沿模型溢价","ramp-data-fable-5-adoption-plateaus","2026-08-26T08:00:00+00:00",{"id":78,"title":79,"news_slug":80,"published_at":81},"e1724d68-bf0d-4b3f-8047-147796d5d52e","Ramp 8 月指数:Fable 5 企业份额停滞 11%,OpenAI 旗舰跑赢两倍","anthropic-fable-5-plateau-11-percent","2026-08-25T06:00:00+00:00",{"id":83,"title":84,"news_slug":85,"published_at":81},"1051d676-8ed9-4448-b0d5-8db4b844f41f","Claude Fable 5 上线两个月,为什么企业只把 11% 的账单花给最强模型","claude-fable-5-11-percent-anthropic-spend"]