25 min 2026-05
Anthropic's Boris Cherny: Why Coding Is Solved, and What Comes Next
概要
Claude Code 创造者 Boris Cherny 在 Sequoia 活动上分享 Claude Code 意外诞生的故事、编码已被解决的判断、/loop 范式、跨学科通才团队、SaaS 七大护城河重排以及软件民主化的'印刷术时刻'。
核心洞察
- Claude Code 诞生于 Anthropic Labs 内部孵化团队，最初 6 个月几乎不可用——Boris 只用它写约 10% 的代码；真正的指数增长从 2025 年 5 月 Opus 4 发布开始，此后每次模型迭代（4.5 → 4.6 → 4.7）都带来新的增长拐点。
- Boris 现在 100% 由模型写代码，日常产出数十个 PR，最高纪录一天 150 个 PR；大部分工作在手机上完成，同时运行 5-10 个 session、数百个 agent，夜间放出数千个 agent 做深度工作。
/loop是他认为最重要的范式——用 cron 定时循环调度 Claude 做持续性任务（看护 PR、修 CI、每 30 分钟从 Twitter 聚合反馈），Routines 是同一概念的服务端版本。- AI 让七大商业护城河（Seven Powers）重新洗牌——切换成本和流程壁垒被削弱，但网络效应、规模经济、稀缺资源等仍然成立；未来 10 年创业公司数量将增长 10 倍。
- 软件开发正在经历"印刷术时刻"——类比 1400 年代欧洲印刷术让识字率从 10% 最终升至 70%，编程将从专业技能变成人人可用的基础能力，最好的会计软件将由会计师而非工程师来构建。
Claude Code 的意外诞生：6 个月的 pre-PMF 赌注
核心要点：Claude Code 源于 Anthropic Labs 孵化团队的一个"产品溢出"（product overhang）判断——模型能力远超当时产品形态，团队选择为"下一代模型"预先构建产品，忍受 6 个月的不好用期。
- Anthropic Labs 是一个小型创新团队，创造了 Claude Code、MCP 和桌面应用，完成后解散，现在由 Instagram 联合创始人 Mike Krieger 带领重组进入"第二轮"
- 2024 年底编码的最先进水平还是"按 Tab 补全一行代码"（Sonnet 3.5 开启的能力），但团队判断可以跳到"让 agent 写全部代码"
- 前 6 个月 Claude Code 几乎不好用，Boris 只用它写约 10% 的代码
- 初始发布后并未爆发——指数增长从 Opus 4（2025 年 5 月）开始，每次模型升级（4.5 → 4.6 → 4.7）带来新拐点
- 选择 TypeScript + React 是因为它们在模型训练分布中占比高，早期模型不够聪明，语言和框架的选择至关重要
"We were building for the next model. And that was the idea pretty much the whole time." —— Boris Cherny
Boris 的个人工作流：手机为主，数百个 agent 并行
核心要点：Boris 现在 100% 由模型写代码，大部分工作在手机的 Claude App 上完成——同时维护 5-10 个 session、数百个 agent，夜间放出数千个做深度任务。
- 日常产出数十个 PR，最高纪录一天 150 个 PR（"试试能推多远"）
- 手机上通过 Claude App 的 code tab 管理多个 session
- 每个 session 内有大量 sub-agent 并行工作
- 夜间放出数千个 agent 做"更深层的工作"
- Claude Code 代码库本身"很简单"——TypeScript + React，没有大秘密（代码已泄露，公众可见）
- 从 2025 年 10-11 月起模型开始写 100% 的代码
`/loop` 是未来：持续运行的自主 agent 循环
核心要点：Boris 认为 /loop 是目前最酷也最简单有效的功能——用 cron 调度 Claude 定时执行重复任务，他自己有数十个 loop 同时运行；Routines 是 loop 的服务端版本，关闭笔记本也能继续运行。
- Loop 本质：让 Claude 用 cron 定时执行任务——每分钟、每 5 分钟、每天
- Boris 的 loop 清单：看护 PR（修 CI、自动 rebase）、保持 CI 健康（修 flaky test）、每 30 分钟从 Twitter 聚合用户反馈
- Routines = loop 的服务端版本，笔记本关闭后仍然运行
- 4.7 模型开始自发使用 loop——比如被要求拉取数据时会主动说"我注意到数据在变化，我会每 30 分钟给你报告一次"，并通过 Slack MCP 发送
- Boris 的观点：不应该由用户来学习如何更好地使用工具，而应该由模型自然地做到这些
"I sort of feel like loops are the future at this point." —— Boris Cherny
团队的未来：跨学科通才取代单一专家
核心要点：未来的团队成员将是跨学科的通才——不仅是全栈工程师，而是同时精通产品、设计、数据科学和工程的人；Claude Code 团队已经是这样运作：每个人都在写代码，包括工程经理、产品经理、设计师、财务。
- 当前"通才"还是指工程师（做 iOS + Web + Server），未来的通才将跨越学科边界
- Claude Code 团队的每一个人都写代码——工程经理、产品经理、设计师、数据科学家、财务、用户研究员
- Anthropic 全公司层面：所有 SQL 由模型编写，没有手写代码；Claude 之间通过 Slack 互相沟通协调
- Anthropic 领先外部的不是技术（相同模型对所有人开放），而是组织结构和流程变革
SaaS 格局重塑：七大护城河的重新排序
核心要点：AI 让 Hamilton Helmer 的"七大商业护城河"重新洗牌——切换成本和流程壁垒被削弱（Claude 4.7 可以"爬山"任何流程），但网络效应、规模经济、稀缺资源等仍然成立。
- 切换成本下降：模型可以帮你从一个产品迁移到另一个产品
- 流程壁垒下降：Claude 越来越擅长理解和执行流程，4.7 是第一个可以"给定目标就能迭代到完成"的模型
- 网络效应、规模经济、稀缺资源——这些护城河不受 AI 影响
- 未来 10 年创业公司数量将增长 10 倍——小团队可以构建与大公司同等价值的产品
- 大公司面临内部阻力（业务流程变革、全员再培训），而从零开始的创业者可以 AI 原生构建
"I think it's the best time to build. It's the best time to be a startup." —— Boris Cherny
软件民主化：编程正在经历"印刷术时刻"
核心要点：Boris 将当前类比 1400 年代欧洲印刷术——印刷术发明后 50 年出版的文献超过之前一千年的总和，书籍成本下降 100 倍，识字率从 10% 最终升至 70%；编程将以更快的速度经历同样的转变。
- 印刷术前欧洲只有约 10% 的人识字，他们受雇于不识字的国王和领主
- 编写会计软件的最佳人选不是工程师而是会计师——因为领域知识是难的部分，编码是简单的部分
- 编程将成为像发短信一样基础的技能——每个人都会，但专业程序员仍然存在（就像专业作家仍然存在）
产品 vs 模型：YC 的核心教训仍然成立
核心要点：Claude Code 的成功约 50/50 归功于模型能力和产品设计——即使模型变得更强，"构建人们热爱的东西"这个 YC 核心教条仍然是关键，但 harness（产品外壳）的重要性会随模型改善而降低。
- Boris 做过 YC，是 YC 公司的第一个员工——"build something people love"被反复灌输
- 团队对产品细节极度关注，确保全天使用体验出色
- 随着模型改善，安全机制（prompt injection 防护、静态命令验证、权限模式、human in the loop）将变得不那么重要——"模型会自己做对的事"
- 未来关注方向：让 loop 成为一等功能、更容易运行大量 agent、Claude Design
本地 vs 云端：模型会自己做决定
核心要点：Boris 认为本地与云端的争论最终"不重要"——几年后模型将自己决定使用本地模型还是云端计算，这不再是工程师做的决定。
- 有人倡导本地 AI，开源模型在追赶中
- Boris 的回答：再过几年，模型会自己启动 agent、构建环境、选择执行方式
- 对于知识工作（非编程），MCP 是通用答案——连接 Salesforce、Google Docs、Google Calendar
- 没有 MCP 的系统通过 computer use 覆盖——Anthropic 在 computer use 方面"遥遥领先"，4.7 版本表现相当好但速度慢
中文翻译 English Original
**Moderator (Asia)：** 好的，我很高兴介绍我们的下一位嘉宾。举手看看，在座谁用过 Claude Code？好的，再举手看看，谁有"Claude Code 上瘾症"？没关系，承认吧。我的团队亲切地说我有 Claude Code 上瘾症，这可能是事实也可能不是。我们今天非常荣幸邀请到 Boris Cherny。Boris 是 Claude Code 的创造者、缔造者。在这个过程中，他亲眼见证了现代软件开发方式的重塑。Boris，非常感谢你抽出时间来跟我们聊。我们知道整个软件开发的未来某种程度上都扛在你的肩上。感谢你百忙之中前来。采访 Boris 的是我们团队的 Lauren Reader。谢谢。
[掌声]
[掌声]
**Moderator (Asia):** 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, [clears throat] it's okay. It's okay. Um my my my team lovingly says I have Claude code psychosis, which may or may not be true. Um we are delighted to have Boris Cherny with us today. Uh Boris is the creator, the father of Claude code. Um and uh in the process of doing that has just had a front row seat to to reinventing uh the modern way of of software development. Um and we're we're really grateful to you, Boris, for taking the time to speak with us today. We know that um the entirety of software development kind of rests on your shoulders. So, thank you for taking it out of your time to be with us today. And interviewing Boris is Lauren Reader from our team. Thank you.
[applause]
[applause]
**Lauren Reader：** 搬椅子坐好。Asia 你把我的开场白抢了。我们问了谁在用 Claude Code，很多人举手，太棒了。Boris，感谢你来到这里，能请到你非常特别。作为一屋子的创造者，我觉得你正在从根本上改变"构建"这件事。所以我很想探讨你对软件的未来、编程的未来的看法，以及我们应该用多出来的空闲时间做什么。先给大家补充一点你的背景。除了创建 Claude Code 之外，Boris 是一位非常纯粹的工程师。整个职业生涯你都在写大量代码，还写了编程教材，包括那本《Programming TypeScript》。上次我们聊的时候，你说 2026 年到目前为止你一行代码都没写过，这变化真的很大。
**Lauren Reader:** Giving our chairs. Um you took my you took my opening line, Asia. We asked who here uses Claude code. There's a lot of hands. That's awesome. Thank you for joining us, Boris. It's very special to have you here. Um as a roomful 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. Um but I'll give you a me a tiny bit more background on you so that everyone has a little bit more context. So, beyond creating Claude 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 in TypeScript. Um 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.
**Boris Cherny：** 还有一个不太为人知的事——中学时候我写过一本在 TI-83 Plus 计算器上用 BASIC 编程的指南。我搜了一下，它居然还在互联网上。非常尴尬，所以请大家不要去搜。但它确实存在。
[笑声]
[笑声]
**Boris Cherny:** Um There's also a a little known thing back in middle school, I wrote a guide about uh writing BASIC for TI-83 Plus calculators. And I I just I I searched for it, it's actually still on the internet. It's extremely embarrassing, so please don't search it. But it exists.
[laughter]
[laughter]
**Lauren Reader：** 我们一定会去找的。好，接下来我会先问几个问题，可能从 Claude Code 的诞生史开始，然后我们会留大量时间给观众问答。所以大家可以开始在脑子里酝酿问题，我很快就会把话筒交给你们。对了，快速调查一下，用 Claude Code 的人里，主要用命令行界面（CLI）的？好的，大多数是 CLI。主要用桌面端的？好。主要用 VS Code 或 JetBrains IDE 的？好，人数其实不多。还有别的方式？
**Lauren Reader:** We will definitely be finding that. Um 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 Claude 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, uh and would love to turn it over to you all soon. Yeah. Um and also real quick, so for people that use Claude code, do people use the CLI mostly? Like okay, majority CLI? Okay. That's a lot. Majority desktop? Okay. Majority VS code or JetBrains IDE? Okay. That's actually not a lot. Okay. Other?
**Boris Cherny：** 我最近主要用 iOS。是的。
[笑声]
好的。我创建 Claude Code 在很多方面其实是个意外。2024 年底我加入了 Anthropic 内部一个叫 Anthropic Labs 的孵化团队。这个团队完成了它的使命——我们创造了 Claude Code、MCP 和桌面应用。团队只有几个人，是一个创新小组。我们做完想做的东西后就解散了。现在这个团队又重新组建起来了，进入第二阶段。Mike Krieger 在领导这个团队，他是 Anthropic 的首席产品官，也是 Instagram 的联合创始人之一。
我开始做编程工具的原因，是我们感觉到了产品悬崖（product overhang）。在座的可能经常用这个词。在实验室内部我们也经常说这个词。它的意思是：模型已经能做很多事情了，但还没有任何产品把这些能力释放出来。2024 年底，我们审视编程领域时，当时的最先进水平是自动补全——你打开 IDE，按 Tab 键，一次补全一行。这是 Sonnet 3.5 首次实现的能力。但我们的感觉是可以走得更远。模型几乎已经准备好迈出下一大步了。我们不需要再做逐行补全，可以直接让 agent 写所有代码。
于是我把它做了出来，但前 6 个月它真的不好用。勉强能用的程度。我自己大概只有 10% 的代码用它来写。即使在最初发布 Claude Code 之后，它也不算成功。有不少人在用，但还没有今天这种指数级增长。真正的增长是从去年 5 月 Opus 4 开始的。我记得很清楚，那是指数级增长的起点，然后每次模型更新都再次加速——从 Opus 4 到 4.5，再到 4.6，现在是 4.7，每次都在拐点上再拐一次。
本质上，我们在做一个还没有产品市场契合（PMF）的东西，而且我们知道它还需要 6 个月才能达到 PMF，因为我们是在为下一代模型而构建。整个过程就是这个思路。Anthropic 一直非常专注——我们一直关心商业化、企业客户、安全和编程。这就是我们想要的构建方式。某个时刻我们知道要做一个产品，但不知道具体做什么，最终 Claude Code 成了这个产品赌注。
[笑声]
好的。我创建 Claude Code 在很多方面其实是个意外。2024 年底我加入了 Anthropic 内部一个叫 Anthropic Labs 的孵化团队。这个团队完成了它的使命——我们创造了 Claude Code、MCP 和桌面应用。团队只有几个人，是一个创新小组。我们做完想做的东西后就解散了。现在这个团队又重新组建起来了，进入第二阶段。Mike Krieger 在领导这个团队，他是 Anthropic 的首席产品官，也是 Instagram 的联合创始人之一。
我开始做编程工具的原因，是我们感觉到了产品悬崖（product overhang）。在座的可能经常用这个词。在实验室内部我们也经常说这个词。它的意思是：模型已经能做很多事情了，但还没有任何产品把这些能力释放出来。2024 年底，我们审视编程领域时，当时的最先进水平是自动补全——你打开 IDE，按 Tab 键，一次补全一行。这是 Sonnet 3.5 首次实现的能力。但我们的感觉是可以走得更远。模型几乎已经准备好迈出下一大步了。我们不需要再做逐行补全，可以直接让 agent 写所有代码。
于是我把它做了出来，但前 6 个月它真的不好用。勉强能用的程度。我自己大概只有 10% 的代码用它来写。即使在最初发布 Claude Code 之后，它也不算成功。有不少人在用，但还没有今天这种指数级增长。真正的增长是从去年 5 月 Opus 4 开始的。我记得很清楚，那是指数级增长的起点，然后每次模型更新都再次加速——从 Opus 4 到 4.5，再到 4.6，现在是 4.7，每次都在拐点上再拐一次。
本质上，我们在做一个还没有产品市场契合（PMF）的东西，而且我们知道它还需要 6 个月才能达到 PMF，因为我们是在为下一代模型而构建。整个过程就是这个思路。Anthropic 一直非常专注——我们一直关心商业化、企业客户、安全和编程。这就是我们想要的构建方式。某个时刻我们知道要做一个产品，但不知道具体做什么，最终 Claude Code 成了这个产品赌注。
**Boris Cherny:** I'm like iOS mostly these days. Yeah.
[laughter]
Okay. Cool. Um yeah, so I started Claude code kind of accidentally in a in a lot of ways. Um I joined this team back in late 2024. It was a sort of this incubator within Anthropic called Anthropic Labs. And uh the team kind of served its purpose. Um we created Claude code, uh 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. Uh now the team's actually back together for round two. Mike Krieger, who's the you know, like the chief product officer at at Anthropic and used to be one of the founders at Instagram, so he's leading that right now.
Um so the kind of the the the the reason that I started to work on coding is we felt like there was this product overhang. And I I'm guessing people here use that word a lot. Uh but we definitely use this word a lot in kind of within the lab. Uh there's this idea that the model can do all the 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. It was you open your IDE 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 6 months. 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 Claude 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. Um that started with Opus 4 in May. And I I remember that very clearly. That's like when the exponential growth started, and then it kind of inflected with every model release. Uh 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 6 months because we were building for the next model. And that was the idea the pretty much the whole time. And you know, 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 what we wanted. So, this kind of ended up being the the product bet.
[laughter]
Okay. Cool. Um yeah, so I started Claude code kind of accidentally in a in a lot of ways. Um I joined this team back in late 2024. It was a sort of this incubator within Anthropic called Anthropic Labs. And uh the team kind of served its purpose. Um we created Claude code, uh 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. Uh now the team's actually back together for round two. Mike Krieger, who's the you know, like the chief product officer at at Anthropic and used to be one of the founders at Instagram, so he's leading that right now.
Um so the kind of the the the the reason that I started to work on coding is we felt like there was this product overhang. And I I'm guessing people here use that word a lot. Uh but we definitely use this word a lot in kind of within the lab. Uh there's this idea that the model can do all the 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. It was you open your IDE 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 6 months. 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 Claude 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. Um that started with Opus 4 in May. And I I remember that very clearly. That's like when the exponential growth started, and then it kind of inflected with every model release. Uh 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 6 months because we were building for the next model. And that was the idea the pretty much the whole time. And you know, 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 what we wanted. So, this kind of ended up being the the product bet.
**Lauren Reader：** 这是一个了不起的故事，尤其它居然是个意外。你公开说过你认为编程已经被"解决"了。如果这是 Anthropic 最重要的三件事之一，能否详细讲讲你说的"解决"是什么意思，还有哪些部分可能还没解决，或者会出现什么二阶效应？
**Lauren Reader:** It's an incredible story, especially that it was an accident. Um so, you've said on the record that you think coding is solved. Uh if this is one of the three best from Anthropic, can you tell us more about what you mean by that, and what might still not be solved, or what second-order problems might come?
**Boris Cherny：** 好，我再做一个现场调查。谁 100% 手写代码？谁 100% 用 Claude Code 这样的 agent 写代码？好。谁是介于两者之间？好。所以大概解决了 50%。
[笑声]
对我来说，是 100%。Claude Code 的代码库——大家知道它泄露了——其实挺简单的。就是 TypeScript 加 React。没什么大秘密，也没什么特别复杂的。我们选择 TypeScript 和 React 是因为这些技术在模型的训练分布上很主流。刚开始搭建代码库的时候，模型没有今天这么智能，所以编程语言和框架的选择很重要。现在模型什么都能写，能学会它没见过的新语言和新框架。但在当时，你需要选一个模型非常熟悉的技术栈。
因此，我们比较早就达到了模型写 100% 代码的状态。对我们来说，这大约发生在去年 10 月、11 月。所以对我来说，今天模型写 100% 的代码。我通常每天提交几十个 PR。上周有一天我提了大概 150 个 PR，那是一个纪录。我当时就是想试试能推到什么程度。对我而言，编程就是已经解决了。
但这并不是所有地方都如此。有非常大型复杂的代码库，有一些模型还不擅长的小众语言。大家也知道，它正在接近全面解决。通常答案就是等下一个模型。
[笑声]
对我来说，是 100%。Claude Code 的代码库——大家知道它泄露了——其实挺简单的。就是 TypeScript 加 React。没什么大秘密，也没什么特别复杂的。我们选择 TypeScript 和 React 是因为这些技术在模型的训练分布上很主流。刚开始搭建代码库的时候，模型没有今天这么智能，所以编程语言和框架的选择很重要。现在模型什么都能写，能学会它没见过的新语言和新框架。但在当时，你需要选一个模型非常熟悉的技术栈。
因此，我们比较早就达到了模型写 100% 代码的状态。对我们来说，这大约发生在去年 10 月、11 月。所以对我来说，今天模型写 100% 的代码。我通常每天提交几十个 PR。上周有一天我提了大概 150 个 PR，那是一个纪录。我当时就是想试试能推到什么程度。对我而言，编程就是已经解决了。
但这并不是所有地方都如此。有非常大型复杂的代码库，有一些模型还不擅长的小众语言。大家也知道，它正在接近全面解决。通常答案就是等下一个模型。
**Boris Cherny:** 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 a agent like Claude code? Okay. Who's like somewhere in between? Okay. So, like 50% solved.
[laughter]
I mean, for me it's for me it's like for me it's 100%. Like the the Claude code code base, um you know, it leaked, so you know, people know. Uh it's pretty simple. It's just like TypeScript and it's React. Like there's no big secret. There's there's nothing really complicated. The 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 use something pretty on distribution.
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. Uh 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. Um but yeah, it's like for me for me it's just solved.
Um 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. Um and you know, as everyone here knows, it's it's getting there. Usually the answer is just wait for the next model.
[laughter]
I mean, for me it's for me it's like for me it's 100%. Like the the Claude code code base, um you know, it leaked, so you know, people know. Uh it's pretty simple. It's just like TypeScript and it's React. Like there's no big secret. There's there's nothing really complicated. The 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 use something pretty on distribution.
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. Uh 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. Um but yeah, it's like for me for me it's just solved.
Um 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. Um and you know, as everyone here knows, it's it's getting there. Usually the answer is just wait for the next model.
**Lauren Reader：** 能不能聊聊你个人的工作环境？前几天你给我们演示过，确实很疯狂。
**Lauren Reader:** Can you actually tell us about your personal setup? You walked us through it the other day. It is pretty wild.
**Boris Cherny：** 好。大概 6 个月前我在 Twitter 上分享了我的个人设置。有意思的是，我当时并没意识到这对别人来说会很惊讶。我以为那就是正常的编码方式。
[笑声]
而且现在已经变了。现在我大部分工作是在手机上完成的。大家可能看不清楚，但我打开 Claude app，左边有一个 Code 标签页，里面有一堆会话在运行。你们可能看不太清。
[笑声]
而且现在已经变了。现在我大部分工作是在手机上完成的。大家可能看不清楚，但我打开 Claude app，左边有一个 Code 标签页，里面有一堆会话在运行。你们可能看不太清。
**Boris Cherny:** Yeah. Um so, I shared my personal setup like 6 months ago or something on on Twitter. And it 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.
[laughter]
And it's changed since then. It's changed. Um and so, now actually most of my work I do from my phone. Um and so, I don't know if like you guys won't be able to see this, but I have um so, I have like the Claude app, and if you open the Claude app, on the left-hand side, there's this little code tab, and I just have a bunch of sessions going. Um you you probably can't see it.
[laughter]
And it's changed since then. It's changed. Um and so, now actually most of my work I do from my phone. Um and so, I don't know if like you guys won't be able to see this, but I have um so, I have like the Claude app, and if you open the Claude app, on the left-hand side, there's this little code tab, and I just have a bunch of sessions going. Um you you probably can't see it.
**Lauren Reader：** 有多少个会话？
**Lauren Reader:** How many sessions?
**Boris Cherny：** 通常大概五到十个会话。每个会话里又有一堆 agent，我目前大概有几百个 agent 在跑。每天晚上通常会有几千个在做更深度的工作。
管理它们有几种方式。一种是让 Claude 派遣一堆子 agent 来干活。但我最近越来越多用的是 loop。就是 /loop 这个功能，它是最酷的东西，也是最简单的有效方案。它的原理就是让 Claude 用 cron 在未来某个时间点调度一个重复任务。可以每分钟、每 5 分钟、每天跑，随你设定。
现在我有几十个 loop 在跑各种事情。有一个在照看我的 PR——修 CI、自动 rebase。另一个保持 CI 健康——如果有不稳定的测试，它就会去修。还有一个每 30 分钟从 Twitter 抓取用户反馈并帮我做聚类。我随时都有一堆 loop 在运行。我感觉 loop 就是未来。如果你还没试过，强烈推荐。
我们还刚上线了 routines，它跟 loop 是一回事，但是在服务器端运行。即使你合上笔记本电脑，它还是会继续跑。
管理它们有几种方式。一种是让 Claude 派遣一堆子 agent 来干活。但我最近越来越多用的是 loop。就是 /loop 这个功能，它是最酷的东西，也是最简单的有效方案。它的原理就是让 Claude 用 cron 在未来某个时间点调度一个重复任务。可以每分钟、每 5 分钟、每天跑，随你设定。
现在我有几十个 loop 在跑各种事情。有一个在照看我的 PR——修 CI、自动 rebase。另一个保持 CI 健康——如果有不稳定的测试，它就会去修。还有一个每 30 分钟从 Twitter 抓取用户反馈并帮我做聚类。我随时都有一堆 loop 在运行。我感觉 loop 就是未来。如果你还没试过，强烈推荐。
我们还刚上线了 routines，它跟 loop 是一回事，但是在服务器端运行。即使你合上笔记本电脑，它还是会继续跑。
**Boris Cherny:** Uh usually have like maybe like five to 10 sessions. Uh and then the sessions usually have a bunch of agents, so I think currently probably like a few hundred agents going. Um usually every night I have like a few thousand that are doing kind of deeper work.
There's a few ways to manage it. One is that you ask Claude to use a bunch of sub-agents to do work. Actually, the the thing that I've been finding myself using more and more is the loop. So, this is /loop, and it's just like the coolest thing. It's like the simplest thing that works. All it is is you have Claude use cron to schedule a job for some point in the future, and it's a repeat job. And it can run every every minute, every 5 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 it'll go and fix it. Um I have another one that grabs uh feedback from Twitter and kind of clusters it for me every 30 minutes. 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 it keeps going.
There's a few ways to manage it. One is that you ask Claude to use a bunch of sub-agents to do work. Actually, the the thing that I've been finding myself using more and more is the loop. So, this is /loop, and it's just like the coolest thing. It's like the simplest thing that works. All it is is you have Claude use cron to schedule a job for some point in the future, and it's a repeat job. And it can run every every minute, every 5 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 it'll go and fix it. Um I have another one that grabs uh feedback from Twitter and kind of clusters it for me every 30 minutes. 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 it keeps going.
**Lauren Reader：** 这是你个人的设置。跟我们聊聊你认为未来的团队会是什么样子？从你所做的一切来看，怎么让团队所有人保持同步、理解上下文？还是说你觉得我们需要把更多东西交给 agent？
**Lauren Reader:** 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?
**Boris Cherny：** 做预测真的很难，但既然来了就试试。我感觉事情的走向是：未来会出现比今天多得多的通才。今天我们说的"通才"，主要还是指工程师。他们仍然在写代码，可能是产品工程师。所谓通才可能是指既做 iOS、又做 Web、又做后端，这是工程领域里的通才。
但我认为接下来会大量出现的是跨学科通才。比如既擅长产品工程又很懂设计的人，或者同时精通产品、数据科学和工程的人。
这是我们团队已经在发生的事。Claude Code 团队里很多人是跨学科通才。我们团队所有人都在写代码——工程经理、产品经理、设计师、数据科学家、财务人员、用户研究员，每一个人都在写代码。他们各有专长，但现在所有人都在编程。我看到有人在点头，我猜这对在座的各位也不算太意外，因为你们可能也在看到同样的变化。
但我认为接下来会大量出现的是跨学科通才。比如既擅长产品工程又很懂设计的人，或者同时精通产品、数据科学和工程的人。
这是我们团队已经在发生的事。Claude Code 团队里很多人是跨学科通才。我们团队所有人都在写代码——工程经理、产品经理、设计师、数据科学家、财务人员、用户研究员，每一个人都在写代码。他们各有专长，但现在所有人都在编程。我看到有人在点头，我猜这对在座的各位也不算太意外，因为你们可能也在看到同样的变化。
**Boris Cherny:** Um I think so I you know, it's like it's so hard to make predictions, but um I'm here to make predictions, so I'll try to make some. I I 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 generalist, it's like a 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. So, this is engineers that are really good at product engineering, but also really great at design. Or really great at product and data science and engineering.
Um I don't know. It's it's something that we're starting to see on our team. So, actually like a lot of people on the Claude code team are generalists across disciplines. Everyone on our team codes. 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 specialist 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 cuz I bet you're seeing the same things.
But I think the thing that we're going to start to see a lot more of is generalists that are cross-disciplinary. So, this is engineers that are really good at product engineering, but also really great at design. Or really great at product and data science and engineering.
Um I don't know. It's it's something that we're starting to see on our team. So, actually like a lot of people on the Claude code team are generalists across disciplines. Everyone on our team codes. 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 specialist 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 cuz I bet you're seeing the same things.
**Lauren Reader：** 好，我再问最后一个我最喜欢的问题，然后就开放给观众。我们聊了编程在怎么变化，我好奇的是你看到软件产品世界在怎么变化。当 AI 把写代码的成本降低 10 倍或 100 倍时，用软件生产出来的产品价值会怎样？我们面临一场 SaaS 末日吗？你怎么看？这又得做一个预测了。
**Lauren Reader:** Um [clears throat] I'll have one more favorite questions then 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. Um 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 SAS apocalypse on our hands? How do you think this plays out? And again, you're going to have to make another prediction.
**Boris Cherny：** SaaS 末日这个问题是我最喜欢的问题。我认为会发生两件事，而且这两件都不是大家一直在讨论的那些东西。
第一件事——在座有谁听 Acquired 播客？那是最好的播客。前几周我有机会上了一期他们的 unplugged，感觉就像见到了偶像，因为两位主持人真的太棒了。他们讲过一个叫"七种力量"（Seven Powers）的框架，这是 Hamilton Helmer 在书里写的，讲的是商业中的七种护城河。我认为因为 AI 的出现，其中一些护城河会变得更重要，另一些会变得不那么重要。
比如，转换成本（switching costs）会变得不那么重要，因为你可以用模型把东西从一个平台迁移到另一个平台。流程壁垒（process power）也会变得不那么重要，因为那些靠工作流和流程建立护城河的公司，Claude 正在变得非常擅长搞定流程。尤其是 4.7，它能对任何东西做爬山优化（hill climb）。你只要给它一个目标，告诉它迭代到完成，它就会一直做下去。我认为这是第一个具备这种能力的模型。所以这些护城河会变弱，但其他护城河依然重要——网络效应、规模经济、稀缺资源等等。这些并不会因为 AI 而改变。
第二件事——如果你看今天的创业公司数量，或者过去 10 年的情况，我认为未来 10 年能够颠覆一切的创业公司数量会增加 10 倍。因为现在你可以是一个很小的创业公司，却能做出跟大公司一样有价值的东西，还能正面竞争。大公司必须改变他们的业务流程，必须改变工作方式，必须给所有人重新培训技术使用，内部会面临大量阻力。但在座各位没有这个问题。如果你从零开始，就能从底层原生地用 AI 来构建。
所以，我觉得现在是创业最好的时代。有太多颠覆性机会正在到来。
第一件事——在座有谁听 Acquired 播客？那是最好的播客。前几周我有机会上了一期他们的 unplugged，感觉就像见到了偶像，因为两位主持人真的太棒了。他们讲过一个叫"七种力量"（Seven Powers）的框架，这是 Hamilton Helmer 在书里写的，讲的是商业中的七种护城河。我认为因为 AI 的出现，其中一些护城河会变得更重要，另一些会变得不那么重要。
比如，转换成本（switching costs）会变得不那么重要，因为你可以用模型把东西从一个平台迁移到另一个平台。流程壁垒（process power）也会变得不那么重要，因为那些靠工作流和流程建立护城河的公司，Claude 正在变得非常擅长搞定流程。尤其是 4.7，它能对任何东西做爬山优化（hill climb）。你只要给它一个目标，告诉它迭代到完成，它就会一直做下去。我认为这是第一个具备这种能力的模型。所以这些护城河会变弱，但其他护城河依然重要——网络效应、规模经济、稀缺资源等等。这些并不会因为 AI 而改变。
第二件事——如果你看今天的创业公司数量，或者过去 10 年的情况，我认为未来 10 年能够颠覆一切的创业公司数量会增加 10 倍。因为现在你可以是一个很小的创业公司，却能做出跟大公司一样有价值的东西，还能正面竞争。大公司必须改变他们的业务流程，必须改变工作方式，必须给所有人重新培训技术使用，内部会面临大量阻力。但在座各位没有这个问题。如果你从零开始，就能从底层原生地用 AI 来构建。
所以，我觉得现在是创业最好的时代。有太多颠覆性机会正在到来。
**Boris Cherny:** The SAS apocalypse question is my favorite question then. Um I think there's two things that are going to happen and I 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. Uh I actually I I got to do a unplugged with them the other week and I I just I I felt like I got to like meet my heroes cuz they're they're just like the hosts are the best. So, they have this idea of uh seven powers and and this is a this is like Hamilton. He kind of wrote he wrote a book about this and this is kind of the seven modes in business. And I think what's going to happen is because of AI, some of these modes 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 uh switching costs because you can just use the model and you can kind of port from one thing to a different thing. Another one that gets less important is process power because for companies whose mode is like workflows and process and things like this, Claude 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 will 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 modes actually still matter. So, this is like network effects, uh scale economies, cornered resources, things like that. These are not really changing with AI.
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.
So, I don't know. I I think it's the best time to build. It's the best time to be a startup. It's there's so much disruption coming.
I think one is Is anyone here an acquired listener? Like the acquired podcast? Yeah, it's like the best podcast. Uh I actually I I got to do a unplugged with them the other week and I I just I I felt like I got to like meet my heroes cuz they're they're just like the hosts are the best. So, they have this idea of uh seven powers and and this is a this is like Hamilton. He kind of wrote he wrote a book about this and this is kind of the seven modes in business. And I think what's going to happen is because of AI, some of these modes 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 uh switching costs because you can just use the model and you can kind of port from one thing to a different thing. Another one that gets less important is process power because for companies whose mode is like workflows and process and things like this, Claude 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 will 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 modes actually still matter. So, this is like network effects, uh scale economies, cornered resources, things like that. These are not really changing with AI.
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.
So, I don't know. I I think it's the best time to build. It's the best time to be a startup. It's there's so much disruption coming.
**Lauren Reader：** 看来我们还是有希望的。谢谢 Boris。我想开放给观众提问，有没有人想问什么？Dan？
**Lauren Reader:** So, there is hope for us after all. Thank you, Boris. Um I would love to open up to audience questions if anyone has anything they would like to ask. Dan?
**Audience (Dan)：** 我很好奇。你说你在产品市场契合之前 6 个月就开始做了，但现在模型已经足够好了。你觉得 Claude Code 的成功有多少归功于模型本身，有多少归功于产品层面的决策？
**Audience (Dan):** I Yeah, I'm curious. Um you said that you built uh 6 months before there was product market fit, but now given that the models are good enough, how much do you attribute the success of Claude code to the model versus like product decisions in the the like field of product?
**Boris Cherny：** 我觉得可能是两者的混合。是的，是混合的。如果你大概 6 个月前问我，比例大概是 50/50。
**Boris Cherny:** Uh I think it's probably a mix. Yeah, I think it's a mix. I think I think if you asked me maybe a year ago, the ratio was maybe something like 50/50. Um maybe I don't know. If you asked me 6 months ago, the mix would be 50/50.
**Audience (Dan)：** 那两年后呢？
**Audience (Dan):** What about in 2 years?
**Boris Cherny：** 两年后？兄弟，我们的计划周期是一周。
**Boris Cherny:** Oh, 2 year I don't know, dude. We plan in like we plan in 1 week out.
**Audience：** 那就说某个未来时间点吧。
[笑声]
[笑声]
**Audience:** Months. Sometime in the future.
[laughter]
[laughter]
**Boris Cherny：** 我解释一下为什么是 50/50。我以前做过 YC，是一家 YC 公司的第一号员工，做过好几个创业公司。在创业圈里，尤其是 YC，他们反复灌输给你的一件事就是：做一个人们热爱的产品。不管产品是什么，不管模型什么的，最终你还是得做一个让人们喜欢的东西。我觉得这就是为什么产品很重要——我们非常在意每一个小细节，让你全天使用时都能有很好的体验。
我认为随着模型变得更好，"外壳"（harness）会变得没那么重要。我们现在在思考的是怎么让外壳进化——怎么让 loop 成为更核心的功能？怎么让跑大量 agent 更容易？子 agent 是一个方向，还有更多我们在酝酿的东西。但我认为再过一年，模型的对齐度会好很多。所以我们今天围绕提示注入、命令静态验证、权限模式、人在回路（human in the loop）等安全机制，都会变得不那么重要，因为模型自己就会做正确的事。这是我的预测。
我认为随着模型变得更好，"外壳"（harness）会变得没那么重要。我们现在在思考的是怎么让外壳进化——怎么让 loop 成为更核心的功能？怎么让跑大量 agent 更容易？子 agent 是一个方向，还有更多我们在酝酿的东西。但我认为再过一年，模型的对齐度会好很多。所以我们今天围绕提示注入、命令静态验证、权限模式、人在回路（human in the loop）等安全机制，都会变得不那么重要，因为模型自己就会做正确的事。这是我的预测。
**Boris Cherny:** And by the way, I think the reason it was 50/50 is um you know, I I I like I 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 you and then especially in YC over and over is build something people love. And so, it it doesn't matter what the product is, 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.
I think as the model's gotten better, the harness kind of gets less important. And I I think like I think 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? Uh you know, beside you know, like sub agents 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 uh prompt injection and kind of static verification of commands and uh permission modes, human in the loop, all this kind of stuff is just going to be less important cuz the model will just do the right thing. Um So, yeah, that's that's my prediction.
I think as the model's gotten better, the harness kind of gets less important. And I I think like I think 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? Uh you know, beside you know, like sub agents 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 uh prompt injection and kind of static verification of commands and uh permission modes, human in the loop, all this kind of stuff is just going to be less important cuz the model will just do the right thing. Um So, yeah, that's that's my prediction.
**Lauren Reader：** 谢谢。Dan，把话筒传一下？
**Lauren Reader:** Thank you. You want to toss the box, Dan?
**Audience：** 从软件领域稍微放大一些来看——我觉得 Claude Code 几个月前实现了一次文化变革，它让软件开发民主化了。你能看到店主在给自己写软件，甚至有人在给微控制器编程，实现开门时自动控灯。你觉得未来编程会变成一种像掌握 Microsoft Office 一样的技能吗？就是每个人都能做到，而不仅仅是科技行业的人？
**Audience:** Great. Um To zoom to zoom out a little bit from software, I think Claude code did a cultural change a few months ago where it democratized like building software. You can see uh shop owners building their own um software for themselves or even uh programming microcontrollers to control the light when someone opens the door. Um do you see in the future um building software becoming a skill like uh I know uh Microsoft Office? Um so, it's a thing that ev- everybody can do, not just people in the tech industry?
**Boris Cherny：** 天哪，是的。完全是的。我觉得它甚至会比那更普及。它会变成一种像"我会发短信"一样自然的技能。
我读的书主要是两个类别：科幻和科技史。在科技史里，有一个事件我认为是当下正在发生的事情的最佳类比——1400 年代欧洲的印刷术。在印刷术发明之前，欧洲大约只有 10% 的人识字。他们通常受雇于那些自己不识字的国王和领主，专门负责读写。这不是人人都会的技能。
印刷术发明之后，又出现了几种改进的印刷机。在第一台印刷机问世后的 50 年里，欧洲出版的文献比之前一千年加起来还多。同一时期，书的价格下降了大约 100 倍。然后花了几百年时间——因为学习读写很难，需要教育体系、政府投入，人们不能都在农田里干活——但几百年后，全球识字率升到了 70% 左右。
现在我们所有人都能读写了，你不需要一个读写学位才能识字。但仍然有专业作家，这仍然是一种职业。所以我认为即将发生的事情——而且会比 50 年快得多——是软件开发会完全民主化，任何人都能做到。
还有很多推论。比如说你要写会计软件。我觉得最适合写会计软件的人，可能今天就已经不是工程师了，而是一个非常优秀的会计师。因为他们对领域了如指掌，而编码是容易的部分，懂领域才是难的部分。我认为这显然就是未来的方向。
我读的书主要是两个类别：科幻和科技史。在科技史里，有一个事件我认为是当下正在发生的事情的最佳类比——1400 年代欧洲的印刷术。在印刷术发明之前，欧洲大约只有 10% 的人识字。他们通常受雇于那些自己不识字的国王和领主，专门负责读写。这不是人人都会的技能。
印刷术发明之后，又出现了几种改进的印刷机。在第一台印刷机问世后的 50 年里，欧洲出版的文献比之前一千年加起来还多。同一时期，书的价格下降了大约 100 倍。然后花了几百年时间——因为学习读写很难，需要教育体系、政府投入，人们不能都在农田里干活——但几百年后，全球识字率升到了 70% 左右。
现在我们所有人都能读写了，你不需要一个读写学位才能识字。但仍然有专业作家，这仍然是一种职业。所以我认为即将发生的事情——而且会比 50 年快得多——是软件开发会完全民主化，任何人都能做到。
还有很多推论。比如说你要写会计软件。我觉得最适合写会计软件的人，可能今天就已经不是工程师了，而是一个非常优秀的会计师。因为他们对领域了如指掌，而编码是容易的部分，懂领域才是难的部分。我认为这显然就是未来的方向。
**Boris Cherny:** Oh my god, yes. Yes. Yes. I I I think it's going to be even more than that. I think it's going to be I don't know. It's going to be a skill like yeah, like I know how to send a text message.
I I I think um you know, like I I read a my my two genres are essentially sci-fi and tech history. This is what I read a lot of. I 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 their job was to read and write and this is not something that everyone knew how to do.
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 a 100x. And then, you know, it took a couple hundred years cuz 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 a degree in reading and writing to know how to read and write. Although still there are professional writers and that is a thing that you can do. So, I 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. 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 I think this is just obviously the the future.
I I I think um you know, like I I read a my my two genres are essentially sci-fi and tech history. This is what I read a lot of. I 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 their job was to read and write and this is not something that everyone knew how to do.
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 a 100x. And then, you know, it took a couple hundred years cuz 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 a degree in reading and writing to know how to read and write. Although still there are professional writers and that is a thing that you can do. So, I 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. 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 I think this is just obviously the the future.
**Audience：** Greg 说过你们有点活在未来，因为你们能提前用到模型和 agent。Claude Code 在发布前就是一个内部工具。你们在工程方面领先外界多少？是一个月、三个月还是六个月？这个差距是在扩大还是缩小？
**Audience:** So, uh one of the things Greg said was that you guys are living in the future a little bit cuz you get to have access to the models and the agents. Claude code was an internal tool before you released it. Um is the gap between where you guys are in engineering and the rest of the world, is that a month? Is it 3 months? Is it 6 months? And is that is that gap getting bigger or smaller over time?
**Boris Cherny：** 在内部，我们用的模型跟大家一样。对我们来说，吃自己的狗粮（dogfooding）非常重要。我们用的跟在座各位用的是同一个东西。我们会用一点 Mythos 来测试，然后大量使用 Opus 4.7 来吃狗粮、写大部分代码。在模型方面，其实没有什么差距。Mythos 某个后续版本迟早会向所有人开放。
我认为在产品层面，差距可能更大。这跟我们改变了所有流程有关。如果你跟 Anthropic 的人聊，我们用 Claude 做所有事情。我们的 Claude 整天在互相沟通——当我在写代码、当我的 Claude 在 loop 里写代码时，它们会通过 Slack 跟其他人正在 loop 里运行的 Claude 沟通，协调解决未知问题。公司里再也没有手写代码了。所有 SQL 都是模型写的。一切都由模型构建。
所以我认为我们真正领先的地方不是技术——因为我们能用的技术大家都能用，本质上我们在做平台。对我们来说，让开发者能用跟我们一样的东西非常重要，我们会对发布的一切进行 dogfooding。但我认为真正的领先优势在于组织结构和组织流程。这是一个我们希望能在像今天这样的场合分享的话题，让大家都能从中学习、共同进化。
我认为在产品层面，差距可能更大。这跟我们改变了所有流程有关。如果你跟 Anthropic 的人聊，我们用 Claude 做所有事情。我们的 Claude 整天在互相沟通——当我在写代码、当我的 Claude 在 loop 里写代码时，它们会通过 Slack 跟其他人正在 loop 里运行的 Claude 沟通，协调解决未知问题。公司里再也没有手写代码了。所有 SQL 都是模型写的。一切都由模型构建。
所以我认为我们真正领先的地方不是技术——因为我们能用的技术大家都能用，本质上我们在做平台。对我们来说，让开发者能用跟我们一样的东西非常重要，我们会对发布的一切进行 dogfooding。但我认为真正的领先优势在于组织结构和组织流程。这是一个我们希望能在像今天这样的场合分享的话题，让大家都能从中学习、共同进化。
**Boris Cherny:** Yeah, so so internally, we use the same models everyone else does. Um for us, the dog fooding is really really important. So, we use the thing that everyone else here does. Um you know, we use like a little bit of mythos to try it and then we use a lot of Opus 4.7 to to dog food it and to write most of our code. Um I think on the model side, there isn't really a gap. Um 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 Claude for literally everything. And our Claudes are talking all day like as as I'm coding, as my Claudes are coding in a loop, they will communicate over Slack to talk to other people's Claudes 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 SQL is written by uh by models. Everything is just built by the models.
So, I I I think actually the place that we're ahead is not the technology cuz 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 we dog food everything that we put out there. But I think there's actually a far bigger weed 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 uh everyone can kind of learn from it and and also evolve.
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 Claude for literally everything. And our Claudes are talking all day like as as I'm coding, as my Claudes are coding in a loop, they will communicate over Slack to talk to other people's Claudes 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 SQL is written by uh by models. Everything is just built by the models.
So, I I I think actually the place that we're ahead is not the technology cuz 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 we dog food everything that we put out there. But I think there's actually a far bigger weed 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 uh everyone can kind of learn from it and and also evolve.
**Lauren Reader：** 是的，我觉得这也是创业公司的优势之一。从零开始要容易得多。Jared？
**Lauren Reader:** Yeah, and I think that's one of the advantages startups have. It's so much easier to start there. Jared?
**Audience (Jared)：** 上次我们聊的时候，你提到了多 agent 的方向，当时还处于非常早期的代码阶段。现在有了 /batch、/loop、sub teams、teams。你能讲讲在模型层面和外壳层面，你们是怎么注入先验知识的？模型层面的目标函数是怎么变化的，从而让委派任务、启动 agent 这些体验变得更好？因为很多工作是可以并行的，能做得快很多，但我感觉我必须用自己的直觉来判断什么时候该并行，而不是模型自己理解"你可以为这件事启动 10 个子 agent"。
**Audience (Jared):** Yeah, um 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 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 the model level to kind of make this experience around delegating work, spinning up agents better? Cuz so much of the work is parallelizable. You can do so many things so much faster and I feel like I have to overlay my own intuition for when to parallelize things rather than the model kind of understanding that you can spin up 10 sub agents for something.
**Boris Cherny：** 在产品层面，说到底就是提示工程（prompting）。我们调整提示词来帮助模型更多地并行处理。但说实话，随着模型变得更好，它自然就会这么做了。像 loop 这个功能，我发现 4.7 会自己主动做。很酷的一个例子——我会跟它说"去拉这个数据查询"，它会说"嘿，我注意到数据在随时间变化。我会启动一个 loop，每 30 分钟给你一份报告。"我说"好，能通过 Slack 发给我吗？"然后它就用 Slack MCP 来做这件事。
所以我觉得随着时间推移，不应该是用户去琢磨怎么更好地使用工具。如果用户需要这么做，那其实是产品设计的问题，说明我没做好。应该是模型自己变得更好，加上我们的提示让它自然而然地做到这些。
所以我觉得随着时间推移，不应该是用户去琢磨怎么更好地使用工具。如果用户需要这么做，那其实是产品设计的问题，说明我没做好。应该是模型自己变得更好，加上我们的提示让它自然而然地做到这些。
**Boris Cherny:** Yeah, I mean on on the product side, it really just comes down to prompting. That's That's how it is. And so, you know, we 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. Uh which is really cool. It's like it does something like uh you know, I'll I'll I'll tell it, "Go uh 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.
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.
**Audience：** 现在似乎很多人用 Claude 或 Codex 这些云端工具来做大量计算。但也有一些非常积极的倡导者支持 AI 本地化。随着时间推移，开源模型追上来之后，人们可能获得非常高质量的本地编程辅助。你对未来几年的愿景是什么？你觉得大家会继续依赖集中式云端计算，还是会转向本地 agent——不会被限流，还有其他好处？
**Audience:** Um so, right now it seems like a lot of us use um like Claude or Codex or these uh tools in the cloud to do a lot of our computing. But then, there are some very vocal advocates of uh having your AI be local. And I could imagine over time as um open way models and other things catch up that this could be more of a possibility for people 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 uh 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?
**Boris Cherny：** 我觉得这个问题有几种回答方式。可能最根本的答案是：这不重要。因为我们正在到达一个模型自己能搞定一切的阶段。我觉得再过几年，模型会自己写所有代码、自己启动 agent、自己搭建环境。如果它决定用本地模型来做某件事，那它就会那么做。这些我不认为还会是工程师需要做的决策了。
**Boris Cherny:** Yeah, I think it um I don't know. There's maybe a few ways to answer that. I think maybe like kind of the the most fundamental way to answer that is it doesn't matter. Cuz Cuz 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, then you know, that's what it'll do. These I I don't think these will be decisions that we are making as engineers anymore.
**Lauren Reader：** 还有时间再问几个问题，话筒传一下。Jamie。
**Lauren Reader:** We have time for a couple more questions, so I can toss this out. Jamie.
**Audience (Jamie)：** 谢谢。Claude Code 的一个伟大决策是利用了开发者的工具和工作流大多是本地的这个事实。但对于一般的知识工作来说，情况不一定是这样——很多工具是云端的。你怎么思考 Co-work 的设计？如何给 Co-work 足够的工具访问权限，让它像 Claude Code 对开发者那样强大？
**Audience (Jamie):** Nester. Thank you. It feels like one of the great uh decisions with Claude Code was making use of the fact that a lot of developers' tools and workflows are local. But um 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 Claude Code is for developers?
**Boris Cherny：** 这是一个很好的问题。我以前在大公司的时候，把所有环境迁移到远端花了大约 5 年时间，规模大了就是很多工作。但对于知识工作来说，基本上已经在云端了——Salesforce、Docs 之类的。对我们来说，答案永远是最简单的方案——就是 MCP。你在 Claude AI 里用的那个 MCP 连接器，你接上 Salesforce、Google Docs、Google Calendar，然后 Co-work 就能用，Claude CLI 能用，Claude Code Everywhere 也能用。
**Boris Cherny:** Yeah, it's That's a really great question. Um I know I know when I was uh when I was at a big company, we took like 5 years moving all the environments to remote. It's just like so much work, especially at a big scale. Um but for knowledge work, largely, it's there already with like Salesforce and Docs and things like that. Um for us, it's always just the simplest answer. It's just MCP. So, the same MCP connector that you have in Claude AI, you hook up like, you know, Salesforce, you hook up Google Docs, Google Calendar. Uh and then Co-work can use that. Claude CLI can use it. Claude Code everywhere can use it.
**Lauren Reader：** 对于那些还没有 MCP 的系统呢？你觉得这是计算机使用（computer use）发挥作用的大机会吗？
**Lauren Reader:** And for the for the systems that don't have MCPs, like do you think that's where computer use is going to be a big opportunity?
**Boris Cherny：** 是的，我觉得 computer use 是一个兜底方案。据我所知，Anthropic 在计算机使用方面相当领先。如果你通过 Co-work 来用，效果已经很不错了。它能操作你电脑上几乎任何软件。速度很慢，但做得很好，尤其是 4.7。不过总的来说，MCP 就是答案。这些东西其实都不太重要——MCP、API、某种程序化的访问方式，模型不在乎是哪种。对模型来说，一切都只是 token。
**Boris Cherny:** Yeah, I think computer use is kind of a catchall. Um 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. Um 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. Um Yeah, but I think I think otherwise like MCP is is kind of the answer. It's And you know, all this stuff just doesn't matter that much. It could be MCPs, APIs, just some sort of programmatic access cuz the the model doesn't care. It's to mo- To the model, it's just tokens.
**Lauren Reader：** 好，最后一个问题了。Ryan。Sean，话筒传一下。
**Lauren Reader:** All right, we have time for one more question. Um Ryan. Sean, do you want to toss the
**Audience (Ryan)：** 谢谢。你之前提到你看到了产品悬崖，于是去做了一个产品，它随着模型变好而变得更有趣。那如果今天你要做一个新产品，你会做什么形状的东西？一个你认为随着模型在未来 6 个月到一年变得更好而会变得更有趣的产品？哪怕说得模糊一点也行。
**Audience (Ryan):** Thank you. Um you've kind of alluded to this, but if like sometime ago you saw the probabil- 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'd build today that you think could becomes a much more interesting as models get better in 6 months to a year?
**Boris Cherny：** Claude Design 我觉得是一个很好的例子。它今天已经不错了，未来会好很多。还有一些我们正在为 Claude Code 酝酿的东西，未来几周会陆续上线。然后我觉得 loop、batch 这些围绕大规模并行 agent 的功能也会变得更好。Computer use 也是一个好例子。
**Boris Cherny:** Yeah, Claude design I I think is a really good example. It's uh it's pretty good today. It's going to get a lot better. Um there's also a few things that we're cooking up for Claude Code uh that are going to be landing over the coming weeks. So, you'll see those. Um and then I think uh I think loop and batch and things like this around like massively parallelizing agents, that's going to get better. And computer use is another good one.
**Lauren Reader：** 好的，Boris，非常感谢你来。我们还会在这里待一会儿，如果有人还有问题的话。
[掌声]
[掌声]
**Lauren Reader:** All right, Boris. Thank you so much for joining us. I think we'll be here for a little longer if anyone has questions.
[applause]
[applause]
**Boris Cherny：** 谢谢大家。
**Boris Cherny:** Thanks, guys.
