Anthropic's Boris Cherny: Why Coding Is Solved, and What Comes Next
发布时间 来源
Episode 设置
摘要
Boris Cherny, creator of Claude Code at Anthropic, joins Sequoia partner Lauren Reeder at AI Ascent 2026 to talk about where coding goes from here. He explains why he hasn't written a line of code in 2026, why he now ships dozens of PRs a day from his phone, and why he believes coding is effectively solved — at least for the code he writes. Also: why loops are the future, why he thinks Claude Code itself may be 100 lines of code a year from now, and why the invention of the printing press is the right analogy for what's about to happen to software.
00:00 Introduction
00:55 Claude Code Crowd Check
02:39 Origin Story of Claude Code
03:35 From Typeahead to Agents
05:07 Is Coding Solved
06:50 Boris Personal Workflow
08:51 Future Teams and Generalists
10:26 SaaS Apocalypse Predictions
12:57 Audience Q&A Deep Dive
23:35 Closing and Whats Next
GPT-4正在为你翻译摘要中......
中英文字稿 
好的，我很高兴介绍我们的下一个演讲者。请举手，有谁在用Claude Code？好的，请举手，有谁有Claude Code综合症？来吧，朋友们，这没关系，没关系。我的团队开玩笑地说我有Claude Code综合症，这可能是事实，也可能不是。我们今天很高兴请到了Boris Cherney。Boris是Claude Code的创始人和设计者，在此过程中，他见证了现代软件开发方式的重塑。Boris，感谢您今天抽出时间与我们交流。我们知道整个软件开发领域在某种程度上依赖于您的贡献，感谢您今天花一个小时与我们在一起，采访Boris的是我们团队的Lauren Reeder。
▶ 英文原文 ⏱
Okay, I'm excited to introduce our next speaker. Show of hands, who here uses Claude Code? Okay, show of hands, who here has Claude Code psychosis? Come on, guys, it's okay, it's okay. My team lovingly says I have Claude Code psychosis, which may or may not be true. We're delighted to have Boris Cherney with us today. Boris is the creator, the father of Claude Code, and in the process of doing that, has just had a front row seat to reinventing the modern way of software development. And we're really grateful to you, Boris, for taking the time to speak with us today. We know that the entirety of software development kind of rests on your shoulders, so thank you for taking an hour of your time to be with us today, and interviewing Boris is Lauren Reeder from our team.
谢谢。这句开场白你已经说了。我通常会问这里有谁使用Claude Code。看到这么多举手，真是太棒了。感谢你加入我们，Boris。能有你在这里真是非常特别。对于一个满是构建者的房间，我认为你正在彻底改变构建的方式，因此我非常好奇你是如何看待软件的未来、编码以及我们应该把空闲时间花在哪里的。不过，我会先简单介绍一下你，这样大家能有更多的背景了解。除了创造云代码，Boris还是一个典型的工程师。从你的职业生涯来看，你写了大量代码，还编写了关于编程和TypeScript的教材。我记得我们上次聊天时，你在过去一年里，甚至到2026年为止还没写过一行代码，这真是个不小的改变。
▶ 英文原文 ⏱
Thank you. You took my opening line. I usually ask who here uses Claude Code. Those are a lot of hands. That's awesome. Thank you for joining us, Boris. It's very special to have you here. As a room full of builders, I think you are changing building entirely, and so I'm very curious to explore how you think about the future of software, coding, and what we should spend all of our free time on. But I'll give you a tiny bit more background on you so that everyone has a little bit more context. So beyond creating cloud code, Boris is very much an engineer's engineer. You were writing a lot of code through your whole career, writing textbooks about code, including programming and TypeScript. And I think last time we chatted, you hadn't written a single line of code in the last year, or at least so far in 2026, which is quite the change.
还有一件很少人知道的事情。在中学时，我曾写过一篇关于如何在TI-83 Plus计算器上进行Basic编程的指南。我刚刚查了一下，竟然还在网上，实在是非常尴尬，所以请不要去搜。不过它确实存在。我们绝对会去找找看这个东西。那么我将从几个问题开始，也许我们可以聊聊云代码的历史、你是如何开始的。之后会有大量的观众问答环节，所以大家可以开始在心里琢磨一下问题，期待很快能把时间交给你们。
▶ 英文原文 ⏱
There's also a little known thing. Back in middle school, I wrote a guide about writing basic for TI-83 plus calculators. And I just, I searched it. It's actually still on the internet. It's extremely embarrassing, so please don't search it. But it exists. We will definitely be finding that. So we're going to do, I'm going to start with a few questions here. Maybe we'll start with a little bit of the history of cloud code, how you started it. And then we're going to have a lot of audience Q&A for this one. And so start thinking about your questions in the back of your head, and would love to turn it over to you all soon.
好的，还有，很快的说一下，对于使用云代码的人来说，大多数人主要使用 CLI 吗？好的，大多数是 CLI？哦，那真是很多。大多数是桌面应用？好的，大多数是 VS Code 或 JetBrains IDE？哦，实际上不是很多。其他呢？我这段时间主要使用 iOS。嗯，好的。酷。所以我算是无意间开始做云代码的。我是在 2024 年底加入了这个团队，当时这个团队是 Anthropic Labs 内部的一个孵化项目。这个团队实现了自己的目标，我们创建了云代码、MCP 和桌面应用程序。这个团队当时只有几个人，就像是一个创新团队。我们构建了我们想要构建的东西，然后团队就解散了。现在，这个团队又重新组建迎来了第二轮。Mike Krieger 现在正在领导这个项目，他是 Anthropic 的首席产品官，也是 Instagram 的创始人之一。
▶ 英文原文 ⏱
Yeah. And also, real quick, so for people that use cloud code, do people use the CLI mostly? Like, okay, majority CLI? Okay, that's a lot. Majority desktop? Okay, majority VS code, or Jeprains IDE? Okay, that's actually not a lot. Okay, other? I'm like iOS mostly these days. Yeah. Okay, cool. Yeah, so I started cloud code kind of accidentally, in a lot of ways. I joined this team back in late 2024. It was sort of this incubator within Anthropical, Anthropic Labs. And the team kind of served its purpose. We created cloud code, MCP, and the desktop app. It was a team. It was just a few of us. So very much like innovation team. We built the thing that we wanted to build. We disbanded the team. Now the team's actually back together for round two. Mike Krieger, who's the, you know, like the chief product officer at Anthropic, and used to be one of the founders at Instagram. So he's leading that right now.
我开始研究编程的原因是我们觉得存在一种产品瓶颈。我猜这里的人可能经常用这个词，但我们在实验室里确实常常这样说。这个概念是，模型具备很多功能，但还没有产品能充分利用这些功能。在2024年末，当我们研究编程时，当时的技术前沿是代码补全。因为当你打开IDE并按下Tab键时，可以逐行补全代码。这是Sonnet 3.5首次实现的功能。但是，我们觉得可以做得更多，模型几乎已经准备好迈向下一个重大进展。所以我们不再需要逐行补全，可以让智能体自动编写所有代码。因此，我着手去实现这个功能，但在最初的六个月里并没有取得成功。
▶ 英文原文 ⏱
So kind of the reason that I started to work on coding is we felt like there was this product overhang. And I'm guessing people here use that word a lot. But we definitely use this word a lot in kind of within the lab. There's this idea that the model can do all this stuff that no product has yet captured. And in late 2024, when we were looking at coding, the way that we did coding, the state of the art at the time was type ahead. Because you open your ID and you press tab, and you can like complete like one line at a time. And that was the thing that Sonnet 3.5 enabled for the first time. But the feeling was we could actually go a lot further than that. And the model was almost ready for the next big step. So we don't have to do type ahead anymore. We can just have the agent write all of the code. And so I built it. And it just really didn't work for the first six months.
这段文字翻译成中文如下：
这东西开始的时候不太好用，几乎不能用。我写的时候，只用在大约10%的代码上。即便是在我们最初发布四元代码之后，也没有大受欢迎。虽然有很多人在用，但它并没有像现在这样呈现出爆发式增长。这种增长是从五月的Opus 4开始的，我记得非常清楚。那时是爆发式增长的起点，随后每次新模型的发布都会引发一个增长拐点。从Opus 4，到4.5，再到4.6，现在是4.7，每次更新都带来新的增长拐点。但实际上，我们当时在尝试构建的是一个产品市场契合度前的产品（pre-PMF）。我们知道在六个月内都不会有市场契合度，因为我们是在为下一个模型做准备。这基本上就是我们当时的整个思路。
▶ 英文原文 ⏱
It was like not very good. It was barely usable. I wrote it from, I used it for maybe 10% of my code or something like that. And even after we released quad code initially, it was not a hit. There's a lot of people that used it, but it did not have this exponential growth that it has today. That started with Opus 4 in May. And I remember that very clearly. That's like when the exponential growth started, and then it kind of inflected with every model release. Like it started with Opus 4, then 4.5, then 4.6, now 4.7. It just kind of keeps inflecting. But essentially, we were trying to build this thing that was like pre-PMF. And we knew that it wouldn't have PMF for six months because we were building for the next model. And that was the idea pretty much the whole time.
对于Anthropic来说，我们一直以来都非常专注。我们一直关注商业、企业、安全性和编程。这就是我们一直以来想要构建的方式。因此在某个时刻，我们有些清楚地知道自己想要开发一款产品，但具体的时间并不确定。因此最终这成为了我们的产品赌注。这是一个不可思议的故事，尤其是因为它是个意外。您曾公开表示您认为编程的问题已经解决。如果这是Anthropic的三个赌注之一，您能否详细说明一下您的意思，以及什么问题可能尚未解决，或者可能会出现哪些次要问题？
▶ 英文原文 ⏱
And for Anthropic in general, we've always just been very focused. We’ve always cared about business and enterprise and safety and coding. That's just always been kind of the way that we wanted to build. And so at some point, we kind of knew that we wanted to build a product. We didn't know exactly when. So this kind of ended up being the product bet. It's an incredible story, especially that it was an accident. So you've said on the record that you think coding is solved. If this is one of the three bets for Anthropic, can you tell us more about what you mean by that and what might still not be solved or what secondary problems might come?
好的，我可以为大家提个问题：谁是100%手写代码的？谁是使用代理工具（例如 quad code）全程编写代码的？好，那么，有没有人是介于两者之间的，比如只用工具完成50%？对我来说，我是100%手写的，毕竟 quad code 的代码库已经泄露了，所以大家都知道。其实这很简单，就用 TypeScript 和 React，没有什么大秘密，也不复杂。我们选择 TypeScript 和 React 的原因是，它们非常适合模型的分布。当我们刚开始构建代码库时，模型还没有现在这么智能，所以编程语言和框架的选择非常重要。如今，模型能写任何东西，能适应新语言和新框架，但在当时，要做到这一点，再适应分布是一条可行的道路。
▶ 英文原文 ⏱
All right. I can ask another question for the room. Who writes 100% of their code by hand? Who writes 100% of their code using an agent, like quad code? Okay. Who's like somewhere in between? Okay. So like 50% solved. I mean, for me, it's like, for me, it's 100%. Like the quad code code base, you know, it leaked. So, you know, people know. It's pretty simple. It's just like TypeScript and it's React. Like there's no big secret. There's nothing really complicated. The reason we picked TypeScript and React is it's very on distribution for the model. So when we started, you know, building the code base, the model was not as intelligent as it is today. So the language and the framework mattered a lot. Nowadays, you know, it can write whatever and it can pick up new languages, new frameworks it hasn't seen. But back then you wanted to do something pretty on distribution.
因此，我觉得相当早的时候，我们就达到了一个阶段，模型能够编写100%的代码。对于我们来说，这大概是在去年的十月、十一月发生的。而现在对我来说，你知道，模型已经能写我全部的代码了。我每天通常会写几个几十个PR。上周有一天我写了大约150个PR，那是个记录。我只是试着看看自己能做到什么程度。不过对我来说，这个问题已经解决了。但在其他地方并不是这样的。有一些非常庞大、复杂的代码库，还有一些模型还不太擅长的奇怪语言。正如这里的每个人都知道的，它正在不断进步。通常的解决方案就是等待下一代模型。
▶ 英文原文 ⏱
Because of that, I think fairly early, we got to the point where the model just wrote 100% of the code. And for us, this happened sometime in October, November last year. And so for me today, you know, like the model writes 100% of my code. I write somewhere, you know, usually a few dozen PRs every day. There was a day last week I did like 150 PRs in a day. That was like, that was a record. I was just trying to kind of push to see how far I can get it. But yeah, it's like for me, for me it's just solved. But this is not the case everywhere. There's very big, complicated code bases. There's kind of weird languages the model's not good at yet. And, you know, as everyone here knows, it's getting there. Usually the answer is just wait for the next model.
当然。我能分享一下我的个人设置吗？前几天我给你们介绍过一次，确实挺疯狂的。大概六个月前，我在推特上分享过我的个人设置，当时我没想到会让大家感到惊讶，那只是我平时编程的方式。不过自那之后，我的设置已经改变了。现在，大部分工作我都是用手机来完成的。你们可能看不到，但我用一个叫Cloud的应用。在这个应用里，界面左侧有一个代码选项卡，我同时会运行很多个会话，你们大概看不到到底有多少。通常我会有五到十个会话，然后每个会话中还会有大量代理。目前来说，大概有几百个代理在同时运行。通宵的时候，我通常会有几千个代理在处理更深入的工作。
▶ 英文原文 ⏱
Can you actually tell us about your personal setup? You walked us through it the other day. It is pretty wild. Yeah, so I shared my personal setup like six months ago or something on Twitter. And it's funny, I actually, I shared it, I didn't realize that it would be surprising for anyone. That was just like the way that I coded. And it's changed since then. It's changed. And so now, actually, most of my work I do for my phone. And so, I don't know if like, you guys won't be able to see this, but I have like the Cloud app. And if you open the Cloud app, on the left-hand side, there's this little code tab. And I just have a bunch of sessions going. You probably can't see it. How many sessions? Usually I have like, maybe like five to 10 sessions. And then the sessions usually have a bunch of agents. So, I think currently, probably like a few hundred agents going. Usually every night, I have like a few thousand that are doing kind of deeper work.
有几种方法可以管理这个。一个办法是让云端使用一堆子代理来完成工作。其实，我越来越常用的方法是一个循环。这是一个斜杠循环，它真是个很酷的东西，也非常简单，就是一个管用的方法。你只需要让云端使用cron来安排一个未来的作业计划。这个作业是可以重复的，你可以根据需要安排它每分钟、每五分钟、每天运行一次。现在，我大概有几十个这样的循环在运行。我有一个循环负责监控我的PR，比如修复CI、自动重新基线，还有一个循环保持CI的健康状态，比如处理不稳定的测试等。还有一个循环每30分钟从Twitter收集反馈，并进行分类。
▶ 英文原文 ⏱
There's a few ways to manage it. One is that you ask Cloud to use a bunch of sub-agents to do work. Actually, the thing that I've been finding myself using more and more is a loop. So, this is a slash loop. And it's just like the coolest thing. It's like the simplest thing that works. All it is, is you have Cloud use cron to schedule a job for some point in the future. And it's a repeat job. And it can run every minute, every five minutes, every day, kind of however often you want to schedule it. And at this point, I have like dozens of loops that are running for stuff. So, I have one that's babysitting my PRs, like fixing CI, auto-rebasing. I have another one that keeps CI healthy. So, like if there's like a flaky test or whatever, it'll go and fix it. I have another one that grabs feedback from Twitter and kind of clusters it for me every 30 minutes.
所以，我一直有很多这样的循环在运行。我有点觉得，循环是未来。如果你还没试过，强烈推荐。而我们最近还推出了“例程”，这其实是类似的东西，但是在服务器上运行。这样，即使你关掉笔记本电脑，它也会继续运行。这是你个人的设置。能不能谈谈你觉得未来的团队会是什么样子的？你如何从你正在做的工作中推断出如何让团队中的每个人都保持前进并理解背景？或者你认为我们需要更多地放手给智能代理才能让事情顺利运作？
▶ 英文原文 ⏱
So, I just have a bunch of these loops running at any time. I sort of feel like loops are the future at this point. If you haven't experimented with it, highly, highly recommend it. And we also just launched routines, which is the same thing, but kind of on the server. So, even if you close your laptop, it keeps going. So, that's your personal setup. Tell us about what you think teams will look like in the future. How do you extrapolate from all the work you're doing to keep everyone on the team moving forward, understanding the context? Or do you think we need to let go of a lot more to agents to make it work?
我认为，你知道，做预测真的很难，但既然我在这里要做预测，那我就试着做一些。 我感觉事情的发展趋势是未来会有更多的全才。现在，当我们谈论全才时，我想我们通常指的还是那些工程师。他们仍然在编写代码，但可能是属于产品工程师，比如，他们同时能够做iOS、网页和服务器开发，这就是工程领域的全才。不过，我认为我们将会看到越来越多的是跨学科的全才。
▶ 英文原文 ⏱
I think, you know, it's so hard to make predictions, but I'm here to make predictions, so I'll try to make some. I feel like the way that things are going is generally there's going to be a lot more generalists than there are today. And today when we talk about generalists, I think largely we're talking about people that are still engineers. So, they're still writing code, but maybe they're kind of product engineers. So, maybe when we say generalists, it's like, you know, they do iOS and web and server, for example. That's like a generalist in engineering. But I think the thing that we're going to start to see a lot more of is generalists that are cross-disciplinary.
这是一群不仅擅长产品工程，还在设计方面也很出色的工程师。我们在产品、数据科学和工程领域都非常有优势。我不太确定，但我们团队开始出现这样的趋势。我们云代码团队的许多人都是跨学科的通才。我们团队的每个人都会写代码，比如我们的工程经理、产品经理、设计师、数据科学家、财务人员和用户研究员，所有人都在编写代码。他们在某一方面是专家，但现在每个人都在编程。我看到一些人点头，但我猜在座的各位其实并不感到惊讶，因为你们可能也看到了同样的情况。
▶ 英文原文 ⏱
So, this is engineers that are really good at product engineering, but also really great at design. We're really great at product and data science and engineering. I don't know. It's something that we're starting to see on our team. So, actually, like a lot of people on the cloud code team are generalists across disciplines. Everyone on our team code. So, like, our engineering manager, our product manager, our designers, our data scientist, our finance guy, our user researcher, every single person on our team writes code. And so, you know, like, they're specialists in something, but now also everyone's just coding. And, you know, I'm seeing some nods, but I bet also it's actually not that surprising to people in this room because I bet you're seeing the same things.
我还有一组问题要问，然后会开放给观众提问。我们刚刚谈了一些编码领域的变化。我很好奇，你认为软件或软件产品的世界正在发生什么变化。当我们看到人工智能使编写代码的成本降低了10倍甚至100倍时，用软件生产的产品的价值会有什么变化？我们是否面临着一个SaaS（软件即服务）灾难？你认为这个局面会怎样发展？另外，你将需要再做一个预测。关于SaaS灾难的问题是我最喜欢的问题。
▶ 英文原文 ⏱
I'll have one more thread of questions and we'll open up to the audience. So, we talked a bit about what's changing with coding. I'm curious about what you see changing in the world of software or software products. I think as we see AI making writing code 10 or 100x cheaper, what happens to the value of the products that are produced with software? Do we have a Saspocalypse on our hands? How do you think this plays out? And again, you're going to have to make another prediction. The Saspocalypse question is my favorite question then.
我认为将会发生两件事，而我觉得这两件事都不是大家一直在讨论的内容。其中一件是，你们当中有没有人听过“Acquired”播客？这个播客非常棒。我那天跟他们做了一次节目，感觉就像见到了偶像一样，因为他们的主持人真的很出色。他们有一个关于“七种力量”的观点，这是Hamilton写的一本书中的概念，描述了商业中的七种护城河。我认为随着人工智能的发展，其中一些“护城河”会变得更重要，而另一些则会变得不那么重要。比如，转移成本就会变得不那么重要，因为你可以使用模型，把某项业务从一个平台转移到另一个平台上。
▶ 英文原文 ⏱
I think there's two things that are going to happen and I don't think either of them is the thing that people have been talking about. I think one is, is anyone here an acquired listener? Like the acquired podcast? Yeah, it's like the best podcast. I actually, I got to do an Unplugged with them the other week and I just, I felt like I got to like meet my heroes because they're just like the hosts are the best. So, they have this idea of seven powers and this is like Hamilton, he kind of wrote, he wrote a book about this and this is kind of the seven moats in business and I think what's going to happen is because of AI some of these moats are going to get more important and some are going to get less important and so like for example one that gets less important is switching costs because you can just use the model and you can kind of port from one thing to a different thing.
另一项变得不那么重要的是流程能力。对于那些护城河在于工作流程和处理方式的公司来说，云计算在处理流程方面变得越来越强大了。尤其是在4.7版本中，它能够快速爬升任何目标，所以如果你给它一个目标，并要求它不断迭代直到完成，它就能做到。我认为这是第一个这样的模型。因此，我认为这些流程能力将变得不那么重要，但之前的护城河依然重要，比如网络效应、规模经济、垄断资源等等，这些都不会因为人工智能的变化而改变。
▶ 英文原文 ⏱
Another one that gets less important is process power because for companies whose moat is like workflows and process and things like this Cloud is getting really good at figuring out process and especially with 4.7 it can just hill climb anything so if you give it a target and you tell it to iterate until it's done it'll just do it. I think this is the first model like that. So, I think these are going to get less important but I think the previous moats actually still matter so this is like network effects scale economies cornered resources things like that these are not really changing with AI.
我认为第二点是，如果你看看今天或者过去十年的创业公司数量，我认为在未来的十年里，那些将彻底改变一切的创业公司数量将会增加十倍。因为现在，即便你是一家微小的创业公司，也可以创造出和大公司同等价值的东西，甚至在竞争中不落下风。大公司必须更新他们的商业流程，改变他们的工作方式，还需要对所有员工进行科技培训，这会遇到很多内部的阻力。但是，如果你是从零开始，就可以从一开始就将AI融入并构建你的业务。
▶ 英文原文 ⏱
I think the second thing is if you look at the number of startups today or like maybe in the next you know the past 10 years I think the number of startups in the next 10 years that are just going to like disrupt everything is going to increase like 10x because right now you can be a tiny startup you could build a thing that's as valuable as a large company and you can actually compete head to head because the large company has to evolve their business process they have to evolve the way they work they have to retrain everyone to use technology. They're going to face a lot of internal resistance to that but you know no one here has that problem if you're starting fresh then you can kind of build with AI natively from the ground up.
所以我不知道，我觉得现在是创业的最佳时机，有这么多的市场变革即将到来，所以我们终究还是有希望的。谢谢你，Boris。我很乐意向观众开放提问时间，如果有人想问Dan任何问题的话。你好，我很好奇，你说在产品市场契合度出现之前你们花了六个月进行构建，但现在模型已经足够好了，那么你认为云代码的成功有多少是归功于模型的，而不是产品决策和产品体验？
▶ 英文原文 ⏱
So I don't know I think it's the best time to build it's the best time to be a startup there's so much disruption coming so there is hope for us after all. Thank you Boris I would love to open up to audience questions if anyone has anything they would like to ask Dan. Hi yeah I'm curious you said that you built six months before there was product market fit but now given that the models are good enough how much do you attribute the success of cloud code to the model versus like product decisions and the like feel the product?
我觉得这可能是个混合，是的，我认为这是个混合情况。如果你在大约一年前问我，我会说比例可能是50-50。我不确定如果你六个月前问我的话，这个比例也许还是50-50。那么两年后呢？哦，两年后我就不知道了，兄弟。我们通常只计划最近一周，或者六个月后的事情。顺便说一下，我认为比例是50-50的原因是，我以前参加过YC加速器，我是那里的第一批员工之一，创办了很多初创公司。在初创公司，尤其是在YC，他们总是反复强调要打造人们喜爱的产品，所以产品本身是什么并不重要，商业模式也不重要，最后你必须打造一个人们喜爱的东西。我认为这就是为什么产品重要，因为我们非常关注细节，这样用户在整天使用的时候就能有很好的体验。
▶ 英文原文 ⏱
I think it's probably a mix yeah I think it's a mix I think if you asked maybe a year ago the ratio was maybe something like 50-50 maybe I don't know if you asked me six months ago the mix would be 50-50 what about in two years oh two I don't know dude we plan on like we plan one week out six months sometime in the future and by the way I think the reason it was 50-50 is you know I like I did YC back in the day I was like the first hire at a YC company and like I did a bunch of startups and in startups like the thing that they drill into and especially in YC over and over is build something people love and so it doesn't matter what the product is it's it doesn't matter like the model and all this stuff you still in the end have to build a thing that people love and I think that's that's why the product matters is we we pay so much attention to the little details so that as you use it all day it's a really great experience.
我认为随着模型的不断优化，控制机制的重要性会逐渐降低。目前我们在考虑的是如何升级这个控制机制，比如如何更好地支持循环操作，如何更轻松地运行多个代理。一个想法是引入子代理，还有其他一些我们正在研究的新功能。我预测到明年，模型会更加智能化，因此目前围绕提示注入、命令静态验证、权限模式和人工监控等的安全机制将变得不那么重要，因为模型本身会做出正确的决策。这就是我的预测。
▶ 英文原文 ⏱
I think as the model's gotten better the harness kind of gets less important and I think like a thing that we're thinking about right now is like how do we evolve the harness so like how do we make loops more of a first-class thing how do we make it easier to run a lot of agents you know beside you know like subagents is one idea there's a bunch more stuff that we're cooking but I think in a year the model will be much better aligned and so all the safety mechanisms that we have today around prompt injection and kind of static verification of commands and permission modes human in the loop all this kind of stuff is just gonna be less important because the model will just do the right thing so yeah that's that's my prediction.
你想要扔掉盒子，丹，非常好，我们从软件稍微拉远一点来看。我认为云代码在几个月前引发了一次文化变革，它使得构建软件变得更加大众化。现在你可以看到店主们自己为自己开发软件，甚至编写微控制器的程序来控制当有人开门时灯光的开启。你认为在未来，构建软件会不会像掌握微软办公软件那样，成为一种人人都能具备的技能，而不仅仅是科技行业的人才会的事情？
▶ 英文原文 ⏱
You want to toss the box Dan great to zoom out a little bit from software I think cloud code did a cultural change a few months ago where it democratized like building software you can see shop owners building their own software for themselves or even programming microcontrollers to control the light when someone opens the door do you see in the future building software becoming a skill like I know a Microsoft office so it's a thing that everybody can do not just people in the tech industry?
哦天哪，是的是的，我觉得这不仅仅是这样，我觉得它会变得更像一种技能，就像我知道如何发送短信一样。我经常阅读科幻和科技历史这两种类型的书籍，在科技历史中，我认为有一个与当前状况最相似的事件发生在15世纪，那就是欧洲的印刷术。在印刷术出现之前，大约只有10%的欧洲人口识字，他们知道如何阅读和书写，通常受雇于那些不识字的国王和领主，他们的工作就是帮助读写，这并不是每个人都掌握的技能。
▶ 英文原文 ⏱
Oh my god yes yes yes I think it's gonna be even more than that I think it's gonna be I don't know it's gonna be a skill like yeah like I know how to send a text message. I think um you know like I read my two genres are essentially sci-fi and tech history this is what I read a lot of and I think in tech history there's one thing which I think to me is the clearest parallel for what's happening right now and this is in the 1400s the printing press in Europe and what what happened was before the printing press essentially 10% of the European population was literate they knew how to read and write they were often employed by like kings and lords that were not literate and their job was to you know their job was to read and write and this is not something that everyone knew how to do.
印刷机被发明后，很快又有了两台印刷机。在发明后的50年里，欧洲出版的文学作品比之前的一千年还要多。在这段时间里，书的价格降低了差不多100倍。但是，由于识字需要教育系统，政府的支持，还有大家不能都忙于农活等原因，真正提高识字率花了好几百年的时间。不过，在接下来的几百年里，全球的识字率达到了70%左右。现在，我们大多数人都能读书写字，不需要特别的学位来达到这个水平，但仍然有专业的作家，这是一个可以追求的职业。我认为即将发生的事情是，软件会像识字一样迅速普及，任何人都能涉及，并且这个过程会比50年更快。这其中有很多相似之处。
▶ 英文原文 ⏱
The printing press was invented then there were two more presses and in the 50 years after the first printing press there was more literature published in Europe than in the thousand years before and over the same period the cost of literature the cost of a book went down like 100x and then you know it took a couple hundred years because you know learning to read and write is hard you need education systems and government and everyone can't be working on farms and so on but over the next few hundred years literacy globally went up to like 70% and so you know now we can all read and write and you don't need a degree in reading and writing to know how to read and write although still there are professional writers and that is the thing that you can do so I think the thing that's about to happen and it's going to be much faster than 50 years is software will be a thing that is fully democratized that anyone can do and you know there's a lot of corollaries to this.
所以，比如说，如果你在编写会计软件，我觉得即使是现在，最好的人选可能不是工程师，而是一个非常优秀的会计师，因为他们对这个领域非常了解。编程其实是容易的一部分，了解领域才是最难的。我认为这显然就是未来的趋势。Greg 说过的一件事是，你们现在就有点像是在生活在未来，因为你们能够访问这些模型和代理代码。这些代码在发布之前是内部工具。那么，你们在工程方面和世界其他地方的差距是一个月吗？三个月？六个月？并且这个差距是变大还是变小呢？是的，内部来说，我们和其他人用的模型是一样的。对我们来说，自用测试非常重要，所以我们使用大家都在用的工具。我们尝试使用了一点 mythos（某个内测工具），然后大量使用 opus 4.7 来进行自用测试，并且编写我们的大部分代码。
▶ 英文原文 ⏱
So for example let's say you're writing accounting software the best person to write accounting software I think maybe even today is not an engineer it's a really good accountant because they know the domain really well and coding is the easy part it's knowing the domain that's the hard part and I think this is just obviously the future so one of the things Greg said was that you guys are living in the future a little bit because you get to have access to the models and the agents code code is an internal tool before you released it is the gap between where you guys are in engineering and the rest of the world is that a month is it three months there's six months and is that is that gap getting bigger or smaller over time yeah so so internally we use the same models everyone else does for us the dog fooding is really really important so we use the thing that everyone else here does you know we use like a little bit of mythos to try it and then we use a lot of opus 4.7 to dog food it and to write most of our code.
我认为在模型方面其实并没有太大的差距，可以说已经是一个神话了，最终某种程度上的传承会普及给所有人。不过在产品方面，可能存在更大的差距，这主要是因为我们正在改变所有的流程。比如，在Anthropic，我们几乎所有事情都使用云服务，云服务之间整天都在交流。当我编程时，我的云服务也在编程，并通过Slack与其他同样在运行的云服务进行沟通，以解决未知问题。我们公司里没有手动编写的代码，所有的SQL都是由模型生成的，一切都是由模型构建的。
▶ 英文原文 ⏱
I think on the model side there isn't really a gap you know it's like it's pretty much mythos and you know that will become some version of some descendant of that will become available at some point to everyone I think on the product side there's probably a far larger gap and that's just related to us changing all of our processes like if you talk to people at Anthropic we use cloud for literally everything and our clouds are talking all day like as I'm coding as my clouds are coding in a loop they will communicate over slack to talk to other people's clouds that are also running in a loop to kind of figure out unknowns we have no more manually written code anywhere at the company all of the sequel is written by models everything is just built by the models.
所以，我认为我们领先的地方其实不在于技术，因为我们使用的技术对大家都是一样的，因为从根本上讲，我们是在构建一个平台，对我们来说，让开发者能使用和我们相同的东西是非常重要的，我们自己也使用我们推出的所有产品。然而，我觉得在组织结构和流程方面，我们确实有很大的领先优势。希望我们能在这样的场合谈论这些，让大家都能从中学习和进步。这也是创业公司一个很大的优势——在这方面起步要容易得多。
▶ 英文原文 ⏱
So I think actually the place that we're ahead is not the technology because the same technology available to us is available to everyone here because fundamentally we are building a platform and so for us it's really important that developers can use the same thing that we're using and that we dog food everything that we put out there but I think there's actually a far bigger lead in kind of the organizational structure and organizational process and this is a place where you know hopefully we can talk about it in places like this and everyone can kind of learn from it and also evolve yeah and I think that's one of the advantages startups have it's so much easier to start there.
好的，Jaron，上次我们谈话时，我记得你提到了一些关于多代理的内容。当时在一个红杉资本的活动上，我们讨论了一些代码方面的问题，你提到有一些事情正在进行中。现在你正在思考的事情显然涉及到slash batch、slash loop、子团队和团队的概念。你能否谈谈在模型层面或在控制层面上，你是如何在控制层面注入先验知识的，以及在模型层面目标函数是如何变化的，以便于更好地处理工作分配和启动代理，因为很多工作都是可以并行化的。如此一来，你可以更快地完成许多任务。我觉得我必须用自己的直觉来判断何时并行化，而不是依赖模型自动理解是否可以为某项任务启动10个子代理。
▶ 英文原文 ⏱
Jaron yeah last time we talked I think I think you'd mentioned we talked a little bit about multi-agent and it was very in code at the time at a prior sequoia event and you mentioned that there were some things going down the pipeline and there's a thing you're talking you're thinking about now obviously there's slash batch there's slash loop there's sub teams there's teams can you speak some to either at the model level and at the harness level how you're injecting priors in the harness level how the objective function is changing at the model level to kind of make this experience around delegating work spinning up agents better because so much of the work is paralyzable you can do so many things so much faster and I feel like I have to overlay my own intuition for when to paralyze things rather than the model kind of understanding that you can spin up 10 sub agents for something.
在产品方面，这其实归结于如何设定提示词，这就是全部。所以，我们会调整提示词，让模型在一定程度上能更好地并行处理任务。不过，随着模型自身的改进，它就能自然而然地做到这些事情。比如像循环操作，我发现版本4.7就开始会自动执行这些任务，这真的很酷。比如，我会告诉它去进行某个数据查询，然后它察觉到数据随时间变化，就会开始一个循环，每30分钟给我生成一个报告。然后我说太好了，你能把它发到我的Slack上吗？它就会用Slack的接口去完成这个任务。所以，我认为随着时间推移，不该是用户去琢磨怎么更好地使用工具。如果确实如此，那就是一个产品设计问题，说明我没做好工作。其实应该是让模型自己能更好地完成这些任务，我们则需要给它合理的提示，让它自然而然地做到这一点。
▶ 英文原文 ⏱
Yeah I mean on the product side it really just comes down to prompting that's that's all it is and so you know we tweak prompts to kind of help the model do stuff in parallel more but also honestly as the model gets better it just naturally does this and so something like loop I found actually 4.7 it just starts doing which is really cool it's like it does something like a you know I'll tell it go pull this data query and it's like hey I noticed that the data is changing over time I'll start a loop and I'll give you a report every 30 minutes and I'm like great can you send it to me over Slack and then it uses the Slack MCP to do that so so I think actually over time it's not on users to figure out how to hold the tools better and if that's the case it's actually a product design problem and like I'm not doing a good job it's really on the model to do this stuff better and on us kind of prompting it so it naturally does this.
当前，许多人使用云端服务、Codex或其他云工具来进行大量计算。然而，也有一些非常热心的倡导者推崇将人工智能本地化。我可以想象，随着开源模型等技术的发展，这将使得人们能够在本地获得更高质量的编程辅助。 我很好奇您对于未来几年的看法：您认为大家仍然会依赖云端集中计算，还是会转向使用本地化的人工智能代理，从而避免被限速等问题，并享受其他好处？
▶ 英文原文 ⏱
So right now it seems like a lot of us use like cloud or codex or these tools in the cloud to do a lot of our computing but then there are some very vocal advocates of have your AI be local and I could imagine over time as open way models and other things catch up that this could be more of a possibility for people to get really high quality coding assistance so I'm curious your vision of say over the next like years or something like that do you see the trajectory of everyone still really relying on the like cloud centralized compute or is there a pivot to oh we all just have our local agents that we can rely on and they don't get throttled and other benefits.
嗯，我觉得可能有几种方式来回答这个问题。我认为最根本的回答方式是，现在这已经不那么重要了。因为我们正处在这样一个阶段，模型几乎能够自行解决一切。我想也许在几年之内，模型将能够完成所有编程工作：启动代理、构建环境等等。所以，如果它决定使用本地模型来执行这些任务，那就是它会去做的事情。我认为这些已经不再是我们作为工程师需要做的决定了。
▶ 英文原文 ⏱
Yeah I think it I don't know there's maybe a few ways to answer that I think maybe like kind of the most fundamental way to answer that is it doesn't matter because I think now we're getting to the point where the model is just able to figure it out so I think like by a couple years from now the model is just going to be doing all the code it's going to be starting the agents it's going to be building the environments and so like if it decides like actually I'll use like local models to do this you know that's what it'll do I don't think these will be decisions that we are making as engineers anymore.
我们还有时间回答几个问题，所以我可以提出来。Jamie，门做得不错，谢谢。感觉云代码的一个重大决策是利用了许多开发工具和工作流程是本地的这一事实，但对于一般的知识工作来说，这并不总是适用。我很好奇你是如何考虑这一点的，尤其是在与协作工作相关的情况下，如何让协作工作能够有效利用我们使用的工具，就像云代码对开发人员一样强大。
▶ 英文原文 ⏱
We have time for a couple more questions so I can toss this out Jamie nice door thank you it feels like one of the great decisions with cloud code was making use of the fact that a lot of developers tools and workflows are local but that isn't necessarily always the case for sort of general knowledge work with you know cloud tools I'm curious how you're thinking about this with co-work of how do you give co-work enough access to the tools that we use to be powerful the same way that cloud code is for developers.
是的，这是个非常好的问题。我记得在我还在大公司的时候，我们花了大约五年的时间将所有环境迁移到远程办公。这是很多工作，特别是在大规模环境下。但是对于知识型工作来说，这方面的条件基本都已经具备了，比如使用Salesforce、Google文档等工具。对我们来说，最简单的解决方案就是使用MCP。你可以用Quad AI中的同一个MCP连接器，连接Salesforce、Google文档和Google日历，然后Co-Work、Quad CLI 以及Quad Code Everywhere都可以使用它。对于那些没有MCP的系统，你认为计算机使用在这方面将会有很大的机会吗？
▶ 英文原文 ⏱
Yeah it's that's a really great question I know I know when I was when I was at a big company we took like five years moving all the environments to remote it's just like so much work especially at a big scale but for knowledge work largely it's there already with like salesforce and docs and things like that for us it's always just the simplest answer it's just mcp so the same mcp connector that you have in quad ai you hook up like you know salesforce you hook up google docs google calendar and then co-work can use that quad cli can use it quad code everywhere can use it for the systems that don't have mcps like do you think that's where computer use is going to be a big opportunity.
是的，我认为“电脑使用”是一个比较笼统的说法。目前据我所知，Anthropic 在电脑方面的表现相当领先。因此，如果你通过合作使用它，它非常不错，可以使用你电脑上的几乎任何软件。虽然速度很慢，但现在特别是版本 4.7，运行效果相当好。不过，除此之外，MCP 可能是一个答案，因为这些东西其实并没有那么重要。无论是 MCP、CLI、API，还是某种编程接口，对模型来说都不重要，因为模型只关心的是“tokens”（令牌/文本片段）。
▶ 英文原文 ⏱
Yeah I think computer use is kind of a catch-all so I think currently for as far as I know I think anthropic is like pretty far ahead on computers and so like if you use it through co-work it's quite good so it's able to use pretty much any piece of software that you have on your computer it's very slow but it does it quite well now especially with 4.7 yeah but I think otherwise like mcp is kind of the answer it's and you know all this stuff just doesn't matter that much it could be mcp clis apis just some sort of programmatic access because the model doesn't care is to the model is just tokens.
好的，我们还有时间来回答最后一个问题。Ryan，Sean，你们想要提出问题吗？谢谢。你们之前好像暗示过这个问题，但如果你在不久前发现产品的滞后性，并打算开发一个随着模型改进会变得更有趣的产品，你能否简要谈谈你今天开发的这个产品的形态，以及为什么你认为在六个月到一年后，随着模型的进步，它会变得更加有趣？
▶ 英文原文 ⏱
All right we have time for one more question Ryan Sean do you want to toss the. thank you you've kind of alluded to this but if like some time ago you saw the probability the product overhang and thought to build a product that would then become more interesting once models got better could you just talk even in vague terms about the shape of a product you built today that you think becomes a much more interesting as models get better in six months to a year.
云设计是一个很好的例子，目前已经相当不错，并且未来会变得更好。我们还在为云代码开发一些新功能，这些功能将在未来几周内推出，你会看到它们的。我认为loop和batch这些用于大量并行化代理的技术会有所提升，计算机的使用也是一个值得关注的方面。
▶ 英文原文 ⏱
Yeah cloud design I think is a really good example it's it's pretty good today it's going to get a lot better there's also a few things that we're cooking up for cloud code that are going to be landing over the coming weeks so you'll see those and then I think I think loop and batch and things like this around like massively paralyzing agents that's going to get better I think computer use is another good one.
好的，鲍里斯，非常感谢你加入我们。我想我们会再待一会儿，以回答大家的问题。谢谢各位。
▶ 英文原文 ⏱
All right Boris thank you so much for joining us I think we'll be here for a little longer if anyone's questions thanks guys.