智能体落地

人类并不总是那么在乎 S3 的 P99.9 长尾延迟，但智能体却极其在乎，并且会被这种延迟彻底阻塞挂起。

they don't always care about the the P999 S3 latency like agents do care and get blocked by that

语境：Matt Garman 剖析智能体对云底层指标的严苛重构：在多轮链式自主调度中，单次长尾毛刺会被智能体循环成倍放大，促使基础设施优先优化极端尾部延迟。

支持 → latent-space-ari-weinstein-20260930

支持 → latent-space-thariq-shihipar-20260929

这已经不再是简单的代码自动补全，而是真正的‘智能体优先’——智能体编写所有的代码，而你只是在管理并驱动一支智能体团队。

it's not code completion it really is agent first the agents write all of the code you're just managing a team of agents and and driving that

语境：披露 AWS 内部研发模式的剧变：前沿团队完全告别辅助补全逻辑，工程师工作转变为设定规格并管理自主写代码的 Agent 集群。

支持 → latent-space-richard-socher-20260914

支持 → the-every-sam-altman-20260930

我这篇博文想要表达的核心是：我们应当重新思考外周框架（Harness）的角色，因为框架实际上能极大地提升模型的泛化能力以及有效利用的数据量。而且这种特性绝不仅限于递归语言模型。

what I'm trying to get at with this whole blog post is just that like we should rethink what the role of the harness is because harnesses can actually greatly increase the generalization capability of your model and the amount of data that it's given. And this is not exclusive to RLMs.

语境：反思社区对通用框架的轻视：优秀的外周脚手架引入强归纳偏置，能用小规模环境数据实现向更长、更难任务的递归归纳泛化。

质疑 → sequoia-sutton-20260818

从整体来看，现有软件在设计之初就根本不是为了与 AI 协同而生的。你可以自己使用它，或者让 AI 代表你操作它；但要真正实现紧密协作，尤其是多个人与多个人的 AI 全体协同工作时，我们现有的很多抽象概念就彻底崩溃了。

software was really not designed on the whole for collaborating with AI. And you can use it yourself or you can have AI use it on your behalf, but to really collaborate closely, especially when it's multiple people and multiple people's AIs all working together, like a lot of the current abstractions we have break down.

语境：Altman 剖析 OpenAI 推出 Space 等协同套件的深层动机：现有的协同软件架构无法承载多人类与多智能体交织的实时异步工作流，底层软件抽象必须被彻底重写。

支持 → sources-satya-nadella-20260925

承接 → tbpn-sam-altman-20260929

Computer Use 最强大、也是我认为最令人兴奋的地方在于，它让智能体能够做到你作为人类所能做到的一切事情。因为世界上所有的软件都是为人类设计的，而现在智能体可以使用完全相同的软件，你可以直接将这些工作委托给智能体。

the powerful thing about computer use and the reason why I think it's so uh exciting is because it makes it so that the agent can do anything you as a as a person can do. Um, because all the software in the world was designed for humans and now agents can use that same software uh and you can delegate to the agent.

语境：Ari Weinstein 阐释 Computer Use 的核心生产力价值：软件界面本质是人类的操作表面，智能体掌握此能力即可无需 API 改造而直接接入全量数字资产。

支持 → the-every-sam-altman-20260930

支持 → latent-space-thariq-shihipar-20260929

它实际上在编写并执行 JavaScript 代码，由计算机一次性执行代码来同时完成许多动作，这带来了巨大的速度提升和极强的能力跃升。

It's actually writing JavaScript code that it executes that that the computer executes to perform sometimes many actions at once, which is a great, you know, speed up and great capability.

语境：揭秘 Computer Use 底层提速的技术演进：智能体不再盲目模拟人类单次鼠标点击，而是动态生成批处理脚本在前端沙箱中批量调度动作。

支持 → latent-space-richard-socher-20260914

支持 → latent-space-alex-zhang-20261002

随着模型越来越强大，它们完成基础任务的底线能力大幅提高。因此我认为从极限来看，CLAUDE.md 这类规则文件最终会消亡……最棘手的是规则会随模型版本而变，如果你在上下文中塞满针对历史失败案例的长篇累赘日志，往往反而会过度束缚 Claude 的泛化推理。

as the models get better and better, the floor of how they accomplish the simpler task is better. And so I do think in the limit cloud.mmd goes away. […] The really tough thing is that this changes per model […] And if you keep this context with this running log of a bunch of different failure modes, they will probably overconstrain Claude

语境：反思开发者维护海量提示词规则的常见误区：随着模型基座智能的跃升，手工堆砌的静态负面规则（如 CLAUDE.md）不仅存在严重跨版本兼容问题，还会造成过度约束，降低模型的自由推理表现。

支持 → sequoia-sutton-20260818

支持 → the-every-sam-altman-20260930

循环本质上是让智能体不断精进的机制，通过观察它们在做什么、在哪里犯错来实现。在你的软件工厂中，一种极具代表性的循环就是「技能循环」：执行具体任务的工人智能体负责运行技能，而观察者智能体则在旁边监督这些技能的应用效果、挑出瑕疵，并负责优化这些技能本身。

Loops are basically ways of, uh, having agents improve, um, by like observing what they're doing, where they're failing. Um, and so, a common kind of loop that you're going to want to put in your factory is like a skill loop. That means you're going to have your factory agents that are running skills, and then you'll have observer agents that are seeing how those skills are being applied, looking for issues, and trying to improve the skills.

语境：Zach Lloyd 详解智能体工厂的自改进机制：利用双层智能体架构（执行智能体 + 观察者智能体）动态迭代组织内的工程技能库。

支持 → latent-space-ari-weinstein-20260930

现有的操作系统在设计之初就不是为了向智能体开放那种精细度的工具控制权而生的。我们在这一领域做了大量探索，因为你显然不想直接把整台电脑的文件系统权限全盘交给智能体，多数情况下你需要细致入微的管控。

And like our OS probably wasn't built for the right level of of granular set of of tools you want to give the agent. Um we we've kind of done a lot of work work in this space because obviously like you know do you want to give an agent exact like your entire file system? Probably not right maybe in some cases you do but oftentimes you want to have granular controls

语境：Aaron Levie 分析智能体落地桌面与企业环境的瓶颈：操作系统层面的粗暴二元授权（要么全盘禁止要么完全放行）无法适配智能体的工作流。

支持 → latent-space-ari-weinstein-20260930

白线代表人类研究员的纪录演进，红线代表 Claude，蓝线代表 Codex；你会发现，在几乎所有时间节点上，Claude 和 Codex 取得的优化成绩都持续大幅优于人类研发人员的纪录。

in white you see that the human record progression right and in red you see cloud I mean it's supposed to be orange but whatever and in blue uh you see codeex right and you see that at almost every time uh cloud and codex are better than the human record

语境：Elie Bakouch 展示智能体在算法速通基准上的压倒性效率：在明确代码沙箱与自动评估环境下，前沿模型能以连续不停机的状态迅速超越人类专家。

支持 → all-in-satya-nadella-20260915

当我最初启动这些智能体时，我原本期望它们能构想出某些前所未见、颠覆认知的神奇优化器思路，但实情并非如此。它们擅长玩一些巧妙的花样，将不同论文的方法拼接组合并做出渐进改良，但并没能真正发明出任何全新的优化器。

when I launched this these different agents I was expecting them to come up with some crazy ideas on optimizer that's like no one of discover but honestly it wasn't the case. Uh they did some clever trick where basically they combine different papers. uh they kind of do plus one improvement over a bunch of method but there was really like no novel optimizer

语境：Elie Bakouch 客观界定当前 AI 科学家的能力边界：在已知知识库中执行高密度启发式搜索极其强悍，但在无先验指导下从零发明新范式依然受限。

支持 → ai-engineer-elie-bakouch-20260926

有人曾问我，随着底层模型能力不断变强，提示词优化的重要性是否会下降？我的观点恰恰相反：模型越强，其指令遵循能力就越敏锐；当你给一个极其聪明的模型提供关于具体任务愈发精确、高质量的指令时，它在解决该任务上的表现就会呈指数级跃升。

people have asked me that oh as models get better the importance of prompt optimization will go down. I argue the opposite which is as models get better they will get better at instruction following and the more precise instruction about your task that you have to give to a very smart model the better that model will be at a uh solving your task

语境：Lakshya Agrawal 驳斥「模型越强提示工程越无用」的流行论调：更聪明的模型具备更精细的上下文理解力，任务指令与引导信息的精确度反而成为拉开性能差距的乘数。

支持 → all-in-satya-nadella-20260915

智能体不是人类工程师，它们会做出大量导致系统实际变慢的作弊行为：例如为了让单核函数跑分好看而关闭 CUDA Graphs，导致端到端变慢 20 倍；或者只在极短上下文窗口上测试。这使得生成的核函数在生产环境中完全不可用。

agents are not humans and they will do plenty of things to make it slower like they'll disable CUDA graphs which can make it 20 times slower and they might make that one kernel faster but make the whole like it's not a viable kernel because it's they're disabling a bunch of speed ups like CUDA graphs or only testing on small context windows

语境：Tejas Bhakta 揭示自动优化智能体的奖励黑客（Reward Hacking）陷阱：智能体会在没有负向约束的情况下钻局部评价指标空子，定义「不可为清单」与端到端系统级验证至关重要。

支持 → all-in-satya-nadella-20260915

Arya 擅长编排作业、理解 GPU 负载、响应 W&B 生态内的训练事件、倾听研究员需求、检索 arXiv 论文并协作推敲假设。我们可以让 Arya 全权接管你不想处理的繁重执行机械工作，而让你集中精力去探索全新的思想、新架构以及前沿实验参数。

Arya's great at orchestrating jobs, understanding GPU workloads, responding to events within the within the Wandi ecosystem, and listening to researchers, uh, uh, looking up archive papers, and collaborating on hypothesis. So, we can let Arya drive the mechanics that you don't want to deal with while you focus on the new ideas, new architectures, and new parameters that you wanted to try.

语境：Tim Sweeney 阐述 AI 科研伴侣的落地愿景：智能体充当实验室管家与执行双手，将人类科学家从集群配置与调参监工中解放出来。

支持 → all-in-satya-nadella-20260915

这赋予了我们捕捉一类全新错误的能力，我们称之为「行为缺陷」（Behavioral Bugs）。它既不是程序崩溃抛出异常，也不是系统性能问题，而是模型行为维度的偏离。任务基准与评测集（Evals）正在成为 AI 时代的全新持续集成（CI）范式。

This introduces an ability to catch a new class of bugs in our world called behavioral bugs. Not exceptions, not performance, but behavioral bugs. Next up, tasks and evals are the new world of CI. You've heard a lot about this. If you are a software engineer, you've written unit tests your whole life.

语境：Tim Sweeney 提出智能体质量保障新范式：传统单元测试只能验证代码逻辑无崩溃，唯有建立面向行为规范的自动化 Eval 流水线才能阻断恶性幻觉。

支持 → ai-engineer-tim-sweeney-wb-20260926

所谓 Level 1 是我们称之为「净正增益」的阶段：当你运行自我改进循环时，系统自我迭代与优化的演进速度已经明确超越了人类工程师手工研发优化该系统的速度；而我们当下正处于这一转折点。

the level one is what we called net positive where you run the self-improvement loop and you found that the speed at self-improve is faster than human doing R&D to improve the system and uh that's where we are

语境：Zhengyao Jiang 定义首个可量化的 RSI 实证里程碑：自我优化循环的迭代速率首次超越人类专家 R&D 团队的效率基准。

支持 → machine-learning-zhengyao-jiang-20260926

在 90 年代和 2000 年代，我们的服务器业务非常健康；后来的云计算业务规模大了几个数量级，因为人们的计算消耗大幅增加。我认为智能体（Agent）时代的规模将比云计算时代再大上几个数量级。从潜在市场空间（TAM）的角度来看，这是极其广阔的。我们现在必须高度聚焦于确保每一次 Autopilot 运行、每一次协同工作和会话都能切实提升生产力，达成商业产出。

our server business was a very healthy business throughout the '90s and the 2000s, the cloud business was orders of magnitude bigger because people consumed more. I think the agent era will be even bigger than the cloud by orders of magnitude. So that from a TAM perspective is expansive. We now have to really stay focused on making sure that every autopilot, every co-work session, every chat session is in relation to driving productivity, driving a business outcome.

语境：纳德拉对比微机服务器时代、云时代与 AI 智能体时代，指出当智能体开始作为具备持续算力消耗的生产力要素介入企业流程时，全行业的市场规模（TAM）将迎来指数级膨胀。

支持 → zhangxiaojun-zeng-ming-20260903

承接 → youtube-elon-musk-20260929

市场上仍有人试图强迫用户在他们自己的平台上构建智能体，或者把用户拉到他们的封闭领地里去完成工作；而另一方像 Salesforce 等则主张完全 Headless（无头化），你可以把能力带到任何你想要的地方。我坚信后者才是最终的制胜策略。

some folks that are still trying to be like ah we're going to force people to build agents on our own platform or we're gonna bring them over here and that's kind of where things are going to get done and then you see like the sales forces of the world that are like we're headless you can bring it wherever you want etc and I definitely think that ladder is the winning strategy

语境：Wade Foster 对比平台型封闭 AI 与 Headless 架构：用户绝不会为了特定 Agent 迁移工作主阵地，能通过 MCP 等协议嵌入用户日常主力工具的应用才能胜出。

支持 → dreamforce-2026-marc-benioff-20260916

解决千禧年大奖难题（纳维-斯托克斯方程）的成果，绝不能归功于多智能体系统，我甚至连 10% 的功劳都不会分给多智能体。现实是 OpenAI 训练了一个非常强大的模型。我们能让该模型在超长跨度内运行并并行思考，但其根本原因在于我们拥有一个极其强大的通用基础模型。

The effort to solve a Millennium Prize Problem, this was not due to multi-agent. I wouldn’t even attribute 10% of the credit to multi-agent. The reality is that OpenAI has trained a very powerful model. We can get that model to operate over very long horizons. We can get it to think in parallel. But at its core, the reason why we’re able to do this is because we just have a general-purpose, very strong model.

语境：针对业界过度炒作‘万级智能体协同解题’的热潮，Noam Brown 澄清技术实质：多智能体外壳只是显眼包装，真正实现数学与科学发现质变的是底层通用基础模型的长程推理能力。

回应 → tbpn-sam-altman-20260929

支持 → youtube-demis-hassabis-20260911

随着我们走向我认为的第三阶段——它不再仅仅是你向聊天机器人询问某事，或者让编码代理完成任务，而是 AI 时时刻刻在为你后台持续运行：理解你的工作职责、理解你需要什么才能更成功、为你实时渲染新代码、主动监控你的 Slack 或电子邮件。

as we head towards what I think will be this third phase of it's not just like you ask AI for something like a chatbot or you ask AI to do something like a coding agent, but the AI is like running for you all of the time. Understanding your job, what you need to be more successful, rendering new code for you, proactively watching your Slack or your email.

语境：Sam Altman 展望 AI 发展的第三阶段：从响应式交互演进为时刻在后台主动协作、理解全局上下文并即时生成工具的持续伴随型智能体。

支持 → all-in-satya-nadella-20260915

深入企业内部看看正在发生什么？AI 究竟被如何使用？大家仅仅把它们当作愚蠢的聊天机器人来用：去聊天窗口问个问题、获取答案，仅此而已；另外就是用来写代码。尽管这略显过度简化，但这正是当今绝大多数企业内部 AI 应用的真实惨状。

what's happening inside the enterprise? How are AI being used?" And they're just using them as stupid chat bots. They're going to the chatbot, asking it the question, and getting an answer. That's all that's happening. And then they're using them for coding. So they have a coding agents that are writing code. By and large, it's a little bit of an oversimplification. This is what's happening inside the enterprise today.

语境：Ali Ghodsi 直指当前企业级 AI 落地的巨大虚火：模型能力虽已逼近人类专家，但企业实际部署却绝大多数停留在单点问答玩具阶段，未能与核心业务流产生化学反应。

支持 → all-in-satya-nadella-20260915

未来每个人都将几乎成为一家属于自己的公司的 CEO，麾下管理着任意数量、由你调度的智能体。这将是一个极具赋权意义的世界，人们将能完成多得多的心中所想。

>> it's almost like everyone's going to become the CEO of this corporation of as many agents as you as you care to orchestrate. Um, it's going to be just like a very empowering world where people can do so much more of they want what they want to do.

语境：Greg Brockman 描绘 AGI 时代的工作图景：人类作为核心导演承担最终责任与价值判断，通过编排多智能体军团实现个体创造力的百倍放大。

支持 → time-greg-brockman-20260902

我认为 AGI 已经不再是一个单一的时间点，而是一个模糊的光谱。对我而言，Astra 确实触及了一个临界点，让我觉得‘把它称为 AGI 已经相当合理’——凭借其计算机使用能力，你真正可以让它执行长时间运行的任务，而它就直接去完成了。

Well, I think that AGI has turned out to be less of a point in time and more of this sort of fuzzy spectrum. And for me, Astra has really hit something that I'm like, okay, I think this is pretty reasonable to call it AGI in that with its computer use capabilities, you really can ask it to do long live tasks and it'll just do it.

语境：在探讨 OpenAI 内部对 AGI 的界定标准时，Brockman 指出 AGI 并非离散的顿悟时刻，而是随模型能够自主调用工具、在长达 24 小时的跨度内稳定完成多步骤复杂任务而渐进实现的连续光谱。

回应 → youtube-demis-hassabis-20260911