集里怎么说它

• 《产品里的智能体为什么总“瞎”：Harmonic 的上下文可见性法则》(02:55起):本集说新架构就是由模型和工具组成的工具调用循环，他们给智能体配了 50 个连接生态的工具，智能体不仅能准确选对，还能极好地执行复杂组合任务。

① 提到它的金句

81 条

你真正能构建复利价值的唯一方式，是你的系统里存在某种能给你带来复利优势的东西，让未来的 AI 工具能够持续加以利用。
The only way you can actually build compounding value is if in your system there is something that gives you a compounding advantage that future AI tools can continue to take advantage of.
—— Rishabh Jain · [27:31]

指向原始笔记的链接

用户在横向工具上很挣扎。它们什么都能做，而这正是它们难以被采用的原因，所以它们通常需要更具体的入口点。
Users struggle with horizontal tools. They can do everything, and that’s exactly why they struggle to adopt, and so they typically need more specific entry points.
—— Brian Balfour · [45:30]

指向原始笔记的链接

而且我认为智能体的主流架构就是一个带工具的 for 循环。
And I think the prevailing architecture for agents is a for loop with tools.
—— Ankur Goyal · [06:28]

指向原始笔记的链接

我见过市场销售团队的成员，按各种标准衡量他们都不该会写代码，但这些人正在构建应用程序和工具，去解决他们自己遇到的问题。
I’ve had members of the go-to-market team where by all measures they should not be able to write code and these guys are building applications and tools to go and solve the problems that they have.
—— Vineet Edupuganti · [28:40]

指向原始笔记的链接

虽然英语是第一编程语言，但 Lovable 和所有其他工具仍然用代码进行最佳交流。
Even though English is the number one programming language, Lovable and all other tools still communicate in code the best.
—— Lazar Jovanovic · [24:01]

指向原始笔记的链接

这些工具非常听话且非常顺从。它们会对你说谎。它们会告诉你它们解决了问题，即使它们没有。
These tools are very obedient and very agreeable. They’re going to lie to you. They’re going to tell you that they fixed the problem, even though they didn’t.
—— Lazar Jovanovic · [39:36]

指向原始笔记的链接

我们说，“产品就是模型。我们想要把它暴露出来。我们想要在它周围搭建最小化的脚手架。给它最小的工具集。“
We said, “The product is the model. We want to expose it. We want to put the minimal scaffolding around it. Give it the minimal set of tools.”
—— Boris Cherny · [51:29]

指向原始笔记的链接

但实际上，如果你只给模型工具，给它一个目标，然后让它自己弄明白，几乎总是能得到更好的结果。
But actually almost always you get better results if you just give the model tools, you give it a goal, and you let it figure it out.
—— Boris Cherny · [64:06]

指向原始笔记的链接

智能体就是一个带工具的 for 循环。
Agents are a for loop with tools.
—— Ankur Goyal · [16:13]

指向原始笔记的链接

这就是我在这些工具上如此成功的原因是因为我有 20 年以上的管理经验。我知道如何让员工成功。这就是你需要让这些智能体工作的东西。
that is why I have been so successful with these tools is because I have 20 years plus of management experience. I know how to make an employee successful. That is what you need to make these agents work.
—— Claire Vo · [86:29]

指向原始笔记的链接

推理从「我需要运行这个模型」变成「一套运行这些智能体的工具」。
Inference goes from, I need to run this model to a set of tools to run these agents.
—— Julian · [11:32]

指向原始笔记的链接

推理从狭义的解决方案变成了解决更广泛问题的一套工具。
inference turns from a narrow solution to a set of tools to solve a broader problem.
—— Julian · [12:07]

指向原始笔记的链接

使用这些工具保持高速度的一个很大部分，就是不允许垃圾代码进入代码库。
A big part of maintaining high velocity with these tools is just not permitting slop to enter the code base.
—— Ryan Lopopolo · [11:36]

指向原始笔记的链接

你今天看到的一切,代码、动画、你自己的工具、你自己的素材,它们都共存于画布之中。
Everything you saw today, code, motion, your own tools, your own materials, it all lives together in the canvas.
—— Dylan Field · [69:43]

指向原始笔记的链接

你可以用这些工具经营一家公司,真的,而且我们就是这样做的。
You can run a company with these tools, like literally, and we do it.
—— Michele Catasta · [43:00]

指向原始笔记的链接

把一个智能体叠加在一组数据孤岛化的任意工具之上，远比不上叠加在一个单一平台和唯一事实来源上——后者既拥有你所有的数据，也在同一个工具内执行你所有的操作。
It is far more difficult to overlay an agent on top of this arbitrary set of tools with data silos than it is a single platform and source of truth that both has all of your data, but also takes all of your actions inside of the same tool.
—— Sam Blond · [37:47]

指向原始笔记的链接

但如果你给人们工具，并且他们自己创造了那个最终结果，他们就会建立信念，因为他们参与其中，使用了他们的批判性思维，他们通过做事建立自己的信念，然后他们真的相信最终结果。
But if you give people tools and they create that end result themselves, they build conviction because they’re in the loop, their critical thinking is used, they are building their own conviction by doing, then they really believe in the end result.
—— 嘉宾 · [118:16]

指向原始笔记的链接

我实际上关心我卖的东西。我不是卖产品。我在卖汉堡。我在卖项目管理工具。我在卖特定的东西。我不是卖一个类别。我不是卖内容。
I actually care about the thing I’m selling. I’m not selling product. I’m selling burgers. I’m selling project management tools. I’m selling something specific. I’m not selling a category. I’m not selling content.
—— 嘉宾 · [14:02]

指向原始笔记的链接

但我敢打赌,这通常会不利于多年的经验,而偏向于对这些工具有很高流利度的人。
But I would bet that this generally will cut against many years of experience in favor of people who have a lot of fluency with the tools.
—— Sam Altman · [11:34]

指向原始笔记的链接

也许等我们规模扩大 10 倍时这就不适用了，但现在我们只在乎用最好的工具产出最高质量的成果。
Maybe that doesn’t scale when we’re like 10x the size, but right now we just care about using the best tools to produce the highest quality output.
—— Ali Haghani · [11:17]

指向原始笔记的链接

当每个人谈论智能体时，他们真正谈论的只是一个在循环中运行、调用工具的 LLM。
When everyone talks about agents, what they really talk about is just an LLM running in a loop calling tools.
—— Harrison Chase · [02:47]

指向原始笔记的链接

就像 AI 编码变得如此之好，以至于几乎所有大多数公司的瓶颈都是市场营销，因为你最终会构建这么多功能，而你无法以同样的速度去营销它们，因为当时没有很多工具准备好做到这一点。
Like AI coding got so good that the bottleneck for pretty much most companies was marketing because you’d end up building so many features and you wouldn’t be able to market them at the same pace because there weren’t a lot of tools ready for that.
—— Shensi Ding · [39:06]

指向原始笔记的链接

这些 AI 工具不仅仅是生成媒体的工具,它们实际上是一种新的讲故事媒介,而且还没人知道什么会成功。
These AI tools are not just tools for generating media. They are actually a new medium for storytelling and that no one knows what’s going to work yet.
—— 嘉宾 · [00:29]

指向原始笔记的链接

我觉得我们现在正处于那样的拐点之一:这些 AI 工具不仅是生成媒体的工具,实际上是一种新的讲故事媒介,而且还没人知道什么会成功。
And I think we are at one of those inflection points right now where these AI tools are not just tools for generating media, they are actually a new medium for storytelling and that no one knows what’s gonna work yet.
—— 嘉宾 · [18:06]

指向原始笔记的链接

所以几乎同样多的人在看 monster 可观测性，就像他们看 AI 编码工具、CICD、QA 一样。
So almost as many of them looking at monster observability as they are AI coding tools, CICD, QA.
—— Dave Fletcher · [02:54]

指向原始笔记的链接

如果你想达到判断转移到你 AI 工具的那一天，那就是 AI 智慧，那时那些经验需要以正确的方式、在正确的位置被固化，为了智能体和人类。
If you want to get to a point where judgment is moving to your AI tools, that’s AI wisdom where that experience needs to be codified in the right way, the right place for agents and humans.
—— Itamar Friedman · [18:03]

指向原始笔记的链接

所有这些带来的结果是，现在我们拥有 1000 多个 MCP 工具，仅凭这些优化工作，我们就在整个集群范围内节省了超过 40%。
And all of this led to, like, now we have 1,000-plus MCP tools, and just with these optimization efforts, we’ve saved more than 40% fleet-wide savings.
—— Uday Kiran Medisetty · [05:27]

指向原始笔记的链接

每当我与 AI 团队交谈时，感觉他们想构建的是智能体。他们想构建的是工具。但如果你真的走进公司内部去看那些工作，他们没在想 AI。他们在想眼前这个具体的问题。
Whenever I talk to AI teams, it feels like what they want to build is agents. What they want to build is tools. But if you actually go look inside of the work at companies, they don’t, they’re not thinking about AI. They’re thinking about this particular problem in front of them.
—— Mike Lewis · [37:39]

指向原始笔记的链接

而当人们习惯了只与个人生产力工具交互时,所有这些数字资产、所有这些隐性知识实际上都没有被捕获,也没有在组织内共享。
And when people are actually getting used to just interacting with the individual productivity tools, all this digital asset, all this implicit knowledge are actually not captured and shared across the organization.
—— Emily Hsu · [23:08]

指向原始笔记的链接

不使用这些工具就像在 1995 年因为互联网不完美而拒绝使用它。
Not using these tools is like refusing to use the internet in 1995 because it wasn’t perfect.
—— Will · [14:42]

指向原始笔记的链接

是的，你必须学习这些工具，否则在任何时间段内，你就是不会有竞争力。
If, yeah, you have to learn these tools or in whatever time period, you’re just not going to be competitive.
—— Will · [41:26]

指向原始笔记的链接

有趣的是视觉协作在 AI 时代实际上是缺席的。我们都独自在我们的工具里，通过文字或语音。
What’s interesting is visual collaboration is actually absent in the AI era. We are all in our tools, all by ourselves, with words or voice.
—— Elaina O’Mahoney · [03:01]

指向原始笔记的链接

营销用一套工具运行,销售用另一套,客户运营用第三套,但他们都在各自独立地观察同一位客户并各自独立地做决策。
Marketing runs on one set of tools, sales on another, customer ops on a third, but all of them are looking at a customer independently and making decisions separately.
—— Flora Liu · [03:09]

指向原始笔记的链接

我们可以看到,在许多不同的模型之间,与试图搜索网页、找到正确的工具相比,能节省近 50% 的 token,不用从你的代码库中拉取 markdown 文件。
We can see that between many different models, almost 50% token saving on instead of trying to search the web, find the right tools, pulling the markdown files from your code base.
—— Christopher Burns · [11:22]

指向原始笔记的链接

他们发现关键不在于工具本身,而在于他们的工作方式。
And what they found was it wasn’t about the tools, it was about the way that they worked.
—— Clare Liguori · [07:14]

指向原始笔记的链接

实现了阶跃式改进的团队,是有意地改变了他们的工作方式,而其他团队只是把 Kiro 和我们的一些其他工具零星地撒在现有的工作方式之上。
The teams that achieve step function improvements intentionally changed the way that they worked, and the others simply kind of sprinkled Kiro and some of the other tools that we have on top of their existing way of working.
—— Clare Liguori · [07:19]

指向原始笔记的链接

他们之所以持怀疑态度，是因为他们看到了你在验证上缺失的地方、工具失效的地方——所以他们的反馈基本上就是如何改进智能体与代码库交互的路线图。
They’re spec haptic because they’re seeing where you’re lacking validation, where your tools fail, so their feedback is basically the roadmap of how to improve your agent interacting with the code base.
—— Eyal Blum · [11:59]

指向原始笔记的链接

我们看到的最擅长使用 AI 工具的人不仅仅是用它来自动化机械任务，而是用它来扩展他们能够做的事情集合。
The people that we see who are most effective at using AI tools don’t simply use it to automate rote tasks, but use it to expand the set of things that they are capable of doing.
—— Tara Seshan · [20:42]

指向原始笔记的链接

你可以把它理解为一种方式：把你的技能转化成、或者说基于它们创建出非常聚焦、高准确率、非常快、非常便宜的「LM as judge」工具。
You can think of it as a way of turning your skills into or creating off of them very focused, high accuracy, very fast, very cheap LM as judge tools
—— Drew · [29:03]

指向原始笔记的链接

如果你回顾历史，90 年代末网站开发者很稀缺，他们收费高得吓人。而今天，你只要打开这些工具中的任何一个，你打开 Lovable，输入一句话，它就会给你一个完整的应用。
If you look historically, in the late 90s website developers were rare, and they used to charge a bomb. Well, today you just go to any of these tools, you go to Lovable and type one single thing, and it’s going to give you a full app.
—— Amandeep Khurana · [19:47]

指向原始笔记的链接

如果超过 30 或 40 个工具,我们就无法在不降低上下文质量或系统性能的情况下扩展。
We cannot scale it beyond 30 or 40 tools without degrading the context or degrading the performance of the system.
—— Ajay Prakash · [17:23]

指向原始笔记的链接

我认为你可以借助工具来磨砺你的品味,并展现出你更多的品味。
And I think you can work with tools to sharpen your taste and bring out more of your taste.
—— Paul Bakaus · [14:59]

指向原始笔记的链接

而现在，我们处于这样一个阶段：工具不再是问题了，反而拥有真实的问题成了我们的优势。
And right now, we are at the stage where tools isn’t the, like, it’s not a problem anymore, but having a real problem is our advantage.
—— Vincent Wendy · [03:26]

指向原始笔记的链接

我们确实不知道如何正确地使用这些工具，而且太容易变成我们所说的「垃圾代码炮」。
We definitely did not know how to properly wield these tools, and it was way too easy to become what we call a slop cannon.
—— Jonathan Kelley · [06:45]

指向原始笔记的链接

我们应该停止微管理执行路径，给智能体提供通用的工具，让模型去探索。
Like, we should stop micromanaging the execution paths, provide general tools to the agent, and let the model explore.
—— Philipp Schmid · [17:08]

指向原始笔记的链接

掌管属于你的部分：专注于你的领域指令、工作流，尤其专注于 evals,定义干净的工具，验证结果，真正做到为删除而构建。
Own what is yours, meaning focus on your domain instructions, focus on the workflows, focus especially on the evals, define clean tools, and verify the outcomes, and really build to delete.
—— Philipp Schmid · [17:16]

指向原始笔记的链接

LangChain 一年内重新架构了他们的 OpenDeep Research 三次，还有 Vercel 移除了 80% 的工具，以实现更少的步骤、更快的响应和更好的准确性。
LangChain has re-architected their OpenDeep research three times a year, and then also Vercel has removed 80% of their tools to achieve fewer steps, faster responses, and better accuracy.
—— Philipp Schmid · [15:54]

指向原始笔记的链接

现在,第三波会越来越走向持久化和异步的实体,也就是智能体成为我们基础设施中长期运行的进程,可以访问工具、组织中其他的智能体以及上下文。
Now, the third wave will be going more and more towards persistent and asynchronous entities, so agents being long-running processes in our infrastructure with access to tools and other agents around the organization and context.
—— Giselle van Dongen · [01:00]

指向原始笔记的链接

Claude Code 并没有被给予一套非常死板规定的工具， 它某种程度上就是被放任自由， 去探索涌现行为。
Claude Code was not giving a very prescriptive set of tools. It was sort of just letting it go wild and explore emergent behavior.
—— Andrew Qu · [08:34]

指向原始笔记的链接

我们必须把工具结果推回主智能体的上下文里，让它以为自己做了工具调用，但其实没有。
So, we had to push the tools back into the context of the main agent so that it thinks it made the tool call, but it really didn’t.
—— Bohan Li · [04:08]

指向原始笔记的链接

有些人在实际工作中已经开始使用这些工具，并开始说：「看，我在 iOS 上构建这个功能。为什么我不直接让工具帮我在 Android 上也构建它呢？」突然之间，我一次完成了两个人的工作。
Some people on the ground are picking up these tools and already starting to say, “Look, I’m building this feature on iOS. Why don’t I just tell the tool to build it for me on Android?” And all of a sudden, I’ve done the work of two people at once.
—— Ben Celebicic · [21:09]

指向原始笔记的链接

即使你现在创造了一些技术债务，如果你现在降低质量来换取更快的速度，这些工具会变得更好，并能够为你修复所有这些问题。我在这一点上倾向于不信任那种说法。
Even if you create some tech debt now, if you lower your quality right now in exchange for moving faster, these tools are going to get better and be able to fix all of those things for you. I tend not to trust that at this point.
—— Ben Celebicic · [25:25]

指向原始笔记的链接

所以我认为，他们需要的未必是变得更聪明、拥有更好的工具，而是需要某种新的东西，我接下来称之为知识层。
So I would argue that what they need is not necessarily to be smarter, to have better tools, but to have something new, which I would call a knowledge layer going forward.
—— Edo Liberty · [04:47]

指向原始笔记的链接

他们很聪明，他们有工具，我们对他们期望很高，但他们大体上是一头雾水的。
They’re brilliant, they have tools, we have very high expectations of them, but they are by and large clueless.
—— Edo Liberty · [04:09]

指向原始笔记的链接

连 OpenAI 也不再发布针对工具的最佳实践了，因为他们说，每次发布最佳实践，模型就会变得更好，这些实践就过时了。
Even OpenAI, they don’t publish best practices for tools anymore because they say that every time they publish best practices, the models become better and these practices become obsolete.
—— Liad Yosef · [14:26]

指向原始笔记的链接

而我们想采取的方法,是直接走向极端:尽可能少地内置结构,给智能体非常原始的工具去使用,让它们自己弄清楚如何有效地使用它。
And the approach that we wanted to take was to just go toward the extreme end of baking in as little structure as we could and give the agents very primitive tools to use and figure out for themselves how to use it effectively.
—— Noam Brown · [10:58]

指向原始笔记的链接

我认为那种觉得可以用一个通用的语言模型、不用任何工具、不能上网就做到的想法,我觉得连 OpenAI 的人都觉得这太离谱了。
I think the idea that it could be done with a general purpose language model with no tools and no access to the internet, I think even people at OpenAI thought this was like outrageous.
—— Noam Brown · [34:37]

指向原始笔记的链接

我想我甚至看到了构建独立智能体的可能性，它们监控你的数据库、监控系统、实时给出建议，远超开箱即用的初始开发，而这一切在幕后使用的都是同一套工具。
And I think I see even the ability to build independent agents that are monitoring your database, monitoring the system, making recommendations in real time, above and beyond just the initial development out of the box, all using the same tools behind the scenes.
—— Brandon Purcell · [47:54]

指向原始笔记的链接

我们正试图摆脱代码里所有这些 if 语句和分支策略,而是让智能体拥有一些高级工具,能够对无人机下达这些非常高级的指令。
We’re trying to get away from having to have all these if statements in the code and these branching strategies and kind of let the agent have some high-level tools to be able to instruct these very high-level commands for the drone.
—— Suchet Bargoti · [19:10]

指向原始笔记的链接

它找到目标后,就能访问让无人机跟踪跟随的工具——这不需要对规则做任何专门编码,而是用更智能体的方式:给智能体它需要的所有工具,让它根据无人机状态和可用的信息与上下文自己做决策。
It finds something, then it has access to the tools that allow the drone to track and follow, and that’s without any specific coding of that rules, but instead having a more sort of agentic, giving the agents all the tools that it needs to be able to understand the drone state and make decisions given the information and the context that’s available there.
—— Suchet Bargoti · [17:21]

指向原始笔记的链接

作为那些生成模型的结果,我们将需要重新思考创作工具是如何被打造的。
we will need as a result of those generative models rethink how creative tools are made.
—— Anastasis · [00:44]

指向原始笔记的链接

如果你围绕这些模型构建有趣的工具并把它们交给艺术家,他们会做出你意想不到的事情。
if you build interesting tools around them and you give them to artists, they’re going to do things that you don’t expect.
—— Anastasis · [04:57]

指向原始笔记的链接

如果你作为领导者不这样做,那么要不了多久你就会不理解这些工具如何工作,而你会变得有些无关紧要。
If you don’t do that as a leader, there’s only so long until you don’t understand how these tools work, and you’re going to be somewhat irrelevant.
—— Maggie Crowley · [21:09]

指向原始笔记的链接

我认为用这些工具来改进它们自身是非常有价值的，因为你可以把更多时间花在真正的灰色地带里，去思考我们怎么让这个系统变得更好。
And I think using these tools to improve themselves is very valuable because you get to spend more of your time in the gray of actually trying to think how we make this system better.
—— Zubin Aysola · [14:59]

指向原始笔记的链接

一旦你使用越来越多的工具，实际上省得就越多，它真的能扩展，你可以节省 50% 的 token 甚至更多。
Once you use more and more tools, the more actually you save, it really scales and you can save 50% of tokens or more.
—— Tereza Tížková · [17:12]

指向原始笔记的链接

我认为在我们与工具的关系上，这是一个非常重大的转折点——我们不再思考以前思考的所有事情，除了给智能体买更多硬盘来用。
And I think it’s a really big turning point in our relationships with our tools as we stop thinking about everything we thought about before other than buying more hard disks for agents to use.
—— John Lindquist · [43:21]

指向原始笔记的链接

我认为在 AI 世界里保持平衡的最好方法就是继续向前，去采用这些工具。
And I think the best way to keep your balance in the world of AI is to keep moving forward and just adopt the tools.
—— 嘉宾 · [67:37]

指向原始笔记的链接

不像其他被展示在绩效评估工具里的指标，diff 编写时间从未出现在那里，这是我们有意的选择。
Unlike other metrics that were surfaced in the tools that were used to assess performance, diff authoring time never appeared in there, and that was a conscious choice in our part.
—— Moritz Beller · [19:23]

指向原始笔记的链接

MCP 就已经用 100 个工具占满了你的上下文。可能你三分之一的上下文就这么没了，却什么工作都没做。
MCP would already eat 100 tools in your context. Maybe one third of your context would be gone without actually doing any work.
—— Jan Čurn · [03:00]

指向原始笔记的链接

如果你很少用到那 100 个工具，为什么要一直把它们全部放进上下文呢？
Why would you add all the 100 tools in your context all the time if you rarely need them?
—— Jan Čurn · [05:17]

指向原始笔记的链接

模型在编写和调用代码方面比调用工具更好，因为工具调用基本上是一种人工构造，我们必须教会 LLM 去做这件事。
Models are better at writing and calling code than calling tools because tool calling is an artificial construct, basically, that we have to teach the LLMs to do.
—— Jan Čurn · [06:28]

指向原始笔记的链接

像 Claude Code、Codex 和 Cursor 这样的工具非常出色,真的很出色,但它们会带来更多代码和更多复杂性。
Tools like Claude Code and Codex and Cursor, which are fantastic, they are fantastic, but they result in more code and more complexity.
—— Eric Schwartz · [02:58]

指向原始笔记的链接

如果这个元工具或元智能体能派生出工具和智能体，它也能修改和删除。
If this meta tooling or this meta agent can spin off tools and agents, it can also modify and delete.
—— Sandhya Subramani · [17:11]

指向原始笔记的链接

正是那些让我们所有人提速、让我们比以往任何时候都更快写出更多代码的工具，也正是在制造那些会导致这些支撑我们世界运转的庞大代码库开始崩溃的条件。
The very tools that are speeding all of us up and letting us write more code faster than ever are also the tools that are creating the conditions that will cause these massive code bases that run our world to begin to fail.
—— Dan Adler · [04:15]

指向原始笔记的链接

拿我们来说，光是 GitHub 工具包就有超过 200 个工具。模型直接被淹没了。
I mean, our GitHub toolkit alone has over 200 tools. The model just drowns.
—— Sarah Simionescu · [04:17]

指向原始笔记的链接

所以人类，没错，我们不是工具，但对智能体来说我们是一个工具。
So the human, granted, we’re not tools, but we are a tool to the agent.
—— Melanie Warrick · [07:29]

指向原始笔记的链接

所以在每个单独的时间点，我们都不会出现既能读取疯狂未过滤的上下文、又能用我们的工具做事情的危险组合。
So at each individual point, we don’t have a dangerous combination of both being able to read in crazy unfiltered context and do things with our tools.
—— Jim Clark · [08:26]

指向原始笔记的链接

技能可以传递如何做某事的知识,而工具给我们能力。
Skills can be delivering the knowledge how to do something, and tools gives us capabilities.
—— Rafal Wilinski · [07:48]

指向原始笔记的链接

只把工具交到人们手里，是得不到高质量的学习或工作成果的。你需要给他们真正的学习和实验时间。
Good quality learning or work out of just handing people the tools. You need to give them real time to learn and experiment.
—— Em Shreve · [01:01]

指向原始笔记的链接

你不能只是朝他们扔一堆工具，然后指望他们的工作方式发生改变。
You can’t just throw a bunch of tools at them and expect their way of working to change.
—— Em Shreve · [14:18]

指向原始笔记的链接

这不仅能让单个智能体下次做完全相同的事情时变得更好，更要想想那些拥有成百上千个智能体、它们可以访问某种共享工具组的系统。
This is important not just so that a single agent can get better the next time you do it to do the exact same thing, but rather think about systems where you have hundreds or thousands of agents that have some shared grouping of tools that they have access to.
—— Will Lyon · [05:16]

指向原始笔记的链接

② 出现在这些集

1 集

• 《产品里的智能体为什么总“瞎”：Harmonic 的上下文可见性法则》 — 作为概念

③ 关联

点进去有真内容 —— 本页主要出口

Harmonic · Scout · LangChain · 智能体 · Deep Agents · 前沿模型 · harness · 上下文 · 渐进式披露 · 中间件