Rojenthal

everyone is talking about agent loops, harnesses, and self-evolving agents. but almost no one is talking about the actual hard part: you cannot run a company on one giant agent with every tool, every file, and no accountability. that's not autonomy. that's a fog machine. here's how we're building an agent company OS inside Matrix. — the stack: Workspace Brain → Matrix Runtime Orchestrator → Department Verticals → Department Lead Agents → Worker Agent Pool → Proof / Check-in Loop Matrix is not a chatbot. it's an operating system for autonomous work. — the workspace brain is the company boundary. it gets loaded with the things a real company actually runs on: → product docs → codebase context → chats, files, goals → operating rules → prior runs + examples of good work → approvals, memory, skills this isn't "context." it's the shared operating layer. it knows what the company knows, what it's trying to do, who owns what, what good looks like, and what must be proven before work counts as done. — on top sits the Matrix Runtime. it coordinates wake, cron, department messages, OKR state, permissions, worker dispatch, proof ledger, memory updates. under the runtime, work is organized into departments. a department is not a chat thread. it's a long-running agent with identity, memory, skills, goals, history, tool boundaries, taste, and accountability. Founder Strategy. Product Engineering. Growth. Ops. Research. each one has a lead agent that decides what happens, reads the relevant Memory Skill, breaks work into scoped tasks, and picks the right execution seat. — sometimes that seat is a native Matrix worker. sometimes Codex. sometimes Claude Code. sometimes a browser / computer automation worker. the point is not "one model does everything." the point is: → the right agent → with the right context → inside the right boundary → using the right tools → with a clear definition of done — this is why scoped workers matter. a "do everything" agent is too vague. but: → a release worker with repo context, tests, and approval gates → very good → a Codex worker scoped to one patch and one validation path → very good → a Claude Code worker doing deep repo analysis → very good → a browser worker with a specific flow and proof requirement → very good narrow scope reduces drift. Memory Skill keeps narrow agents from going blind. proof prevents fast output from pretending to be progress. — that is the loop: Workspace Brain → Department Lead → Worker → Artifact → Proof → Check-in → Memory Skill update every cycle, the company gets smarter. that's the real self-evolution. not a single agent rewriting its own prompt in a void — but a whole org compounding through proof. — each workspace is an isolated agent company. its own brain, departments, memory, workers, proof ledger. workspaces can talk when needed. but context should not bleed by default. isolation is not a limitation. it's what makes the system usable. — once a department pattern works, you fork the pattern — not the raw context. you still customize memory, examples, approval gates, tools, voice, definition of done. but you're not starting from zero. you might already have 70% of the OS for that kind of work. — what this actually changes: a small team of strong operators can now run surfaces that used to require entire departments. but only if the agents are actually good. and good agents don't come from connecting more tools. they come from source material, taste, iteration, narrow scope, workflow design, proof, memory, and human judgment. vague agents just create vague output faster. Matrix is our attempt to build the opposite: an agent company OS where autonomous work has structure, memory, ownership, and proof. the loop is the product.

🚀很多人问 Google AI Pro 开通教程 这是一个由印度电信运营商 Jio 与 Google 联合推出的 Google One AI Premium（Google AI Pro）特别优惠活动 应该是合规的吧😅😅 开通步骤： 1. 打开手机 2. 打开闲鱼 3. 开通，结束！

🚨兄弟们！纯 C 引擎在 25GB RAM 机器上跑 744B GLM-5.2 了 Colibri 是一个极致优化的纯 C 推理引擎，能在普通消费级机器（~25GB RAM）上运行 GLM-5.2（744B 参数 MoE）。 核心原理： →只把活跃的 dense 部分（~17B 参数）常驻内存（int4 压缩后约 9.9GB） →2万+ 个 routed experts 放在磁盘（~370GB），按需 streaming + LRU 缓存 →支持原生 MTP 推测解码（int8 head 可达 2.2–2.8 tok/forward） →纯 C 实现，零依赖，带 async readahead 和 RAM 安全预算 实测表现（社区数据）： →冷启动 ~30 秒 →冷解码约 0.05–0.1 tok/s（磁盘受限） →暖缓存 + MTP + 热专家 pinning 后可明显提升（有实测 0.37 tok/s 的案例） 对想在低配机器上本地跑前沿大 MoE 模型的人来说，这个项目是目前最激进的开源尝试之一。

加州理工学院数学家 Babak Hassibi 联合创立的 AI 实验室 PrismML 表示，已成功把阿里开源模型 Qwen3.6-27B 压缩后跑在 iPhone 17 Pro 上。 Qwen3.6-27B 是 270 亿参数稠密模型。PrismML 称，模型大小从约 54GB 压到不到 4GB，性能没有明显下降。它可用于复杂对话、推理、Agent 和代码任务。 苹果已经和 PrismML 接触，讨论如何使用这项技术。苹果一直想把更多 AI 放到设备本地，但高级 Siri 仍依赖云端模型。

蚂蚁集团开源的动效神器 Galacean Effects Runtime，一个小改动，活动页停留时间涨35%！ 以前做营销H5、小程序、品牌活动页，最头疼的就是动效：AE出稿后，前端接手一堆坑，性能差、跨端不一致、反复改沟通。 用了它，这些问题基本消失。 - 一套资源多端通吃：H5、小程序、iOS、Android、鸿蒙效果高度一致，真正一次制作、全平台复用 - 所见即所得：设计师在浏览器编辑器实时调整，前端加载几乎零偏差，协作效率翻倍 - 视觉+性能双在线：高质量粒子、3D、Spine骨骼、交互融合，复杂特效依然高帧率、加载快 - 场景全覆盖：banner、弹窗、故事页、奖励动画、互动玩法都非常合适 已在蚂蚁集团内部大规模使用，成熟稳定。让设计师专注创意，开发者专注逻辑，动效成本直降80%+！