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

32 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

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

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

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

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

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