章节 1：开场与产品背景 (Introduction & Product Context)

📝 本节摘要：

本节作为访谈的开篇，主持人 Greg 介绍了 Claude Co-work 的核心定位——它是一个将技术性极强的 Claude Code 封装进简洁 UI 的产品，旨在让包括非技术人员在内的所有人（甚至父母）都能使用。Claude Code/Co-work 的创造者 Boris 指出，最初 Claude Code 并非作为产品构建，但用户的使用方式（甚至“滥用”）给团队带来了巨大惊喜。双方用早期 App Store 的发展历程类比，认为目前正处于探索 Co-work 潜力的早期阶段，没有人拥有全部答案。

[原文] [Greg]: claude Cowwork is here and if you understand how to use it you're going to be able to outperform 99% of people on this planet it is an easy way for you to use Claude Code you might have heard of Claude Code it's gone viral but the problem is it feels technical you have to go into the terminal and it's not fun for a lot of beginners

[译文] [Greg]: Claude Co-work 来了，如果你懂得如何使用它，你将能够超越这个星球上 99% 的人。这是一种使用 Claude Code 的简便方法，你可能听说过 Claude Code，它已经疯传了，但问题是它让人感觉技术性太强，你必须进入终端（terminal），这对许多初学者来说并不好玩。

[原文] [Greg]: so Claude has come up with co-work and it's a brand new product that harnesses the power of Claude code in a UI that is simple that anyone could use that your dad can use your mom could use hey even you can use

[译文] [Greg]: 所以 Claude 推出了 Co-work，这是一个全新的产品，它利用了 Claude Code 的强大功能，但采用了一个简单的用户界面（UI），任何人都可以使用，你爸爸可以用，你妈妈可以用，嘿，甚至你也可以用。

[原文] [Greg]: so in this episode I brought on Boris the maker of this product i'm so excited that he shows you the best practices for how to use Claude Co-work and at the end how he sets up his Claude code to get the most out of it you're going to love this episode

[译文] [Greg]: 所以在这一集中，我请来了这个产品的制造者 Boris，我非常兴奋他能向大家展示使用 Claude Co-work 的最佳实践，以及在最后展示他如何设置自己的 Claude Code 以充分利用它，你会喜欢这一集的。

[原文] [Greg]: we are lucky we've got Boris he's the creator of Claude code and I would say the co-creator of Claude co-work today and today what I want to get accomplished is everyone's talking about co-work and I want to best understand what are the use cases how can we get started what are some nonobvious ways I can use it,

[译文] [Greg]: 我们很幸运请到了 Boris，他是 Claude Code 的创造者，我想说也是如今 Claude Co-work 的联合创造者。今天我想达成的是，大家都在谈论 Co-work，我想最好地了解它的用例是什么，我们如何开始，以及有哪些不明显的（nonobvious）使用方法。

[原文] [Greg]: so Boris thank you so much for coming on the show and I have one question for you by the end of this episode what are people going to get out of it

[译文] [Greg]: 所以 Boris，非常感谢你来到节目中，我有一个问题问你，到这一集结束时，人们会从中得到什么？

[原文] [Boris]: oo I think people are going to start to get some more ideas for how to use co-work and hopefully they're going to tweet about it and maybe they'll even reach out to me so I can learn how they want to use co-work

[译文] [Boris]: 噢，我认为人们将开始获得更多关于如何使用 Co-work 的想法，希望他们会在推特上讨论它，甚至可能会联系我，这样我就能了解他们想如何使用 Co-work。

[原文] [Boris]: it's funny I feel like um quad code from the beginning it was sort of built to be it wasn't actually built to be a product at all but when we first started thinking about it as a product we thought that the thing people would use it for is coding but we learned very quickly that people didn't just use it for coding they used it for like all sorts of stuff

[译文] [Boris]: 这很有趣，我觉得 Claude Code 从一开始某种程度上……它实际上根本不是为了成为一个产品而构建的，但当我们第一次开始将其视为一个产品时，我们认为人们会用它来写代码，但我们很快了解到人们不仅仅用它来写代码，他们用它来做各种各样的事情。

[原文] [Boris]: so I I kind of feel the journey of quad code has been very surprising and I have been learning so much just watching how people use the product and how they abuse it and kind of like what what they actually want to use it for and even if it's not designed for that,

[译文] [Boris]: 所以我感觉 Claude Code 的旅程非常令人惊讶，我仅仅通过观察人们如何使用这个产品、如何“滥用”它、以及他们实际上想用它做什么（即使它不是为此设计的），就学到了很多东西。

[原文] [Boris]: so I kind of feel the same way about Coorwork you know I have some ideas about what people are going to use it for i kind of view these as hypothesis and so you know happy to talk about it happy to maybe I'll do a quick demo to to show you kind of some of the some of the things that we use it for but I think that it's going to be pretty surprising uh and I hope that I will be surprised um when we see how people actually use it in the wild

[译文] [Boris]: 所以我对 Co-work 也有同样的感觉，你知道我对人们会用它做什么有一些想法，我把这些看作是假设。所以我很高兴谈论它，也很高兴也许做一个快速演示来向你展示我们用它做的一些事情，但我认为这将会非常令人惊讶，而且我希望当我们在现实世界（in the wild）中看到人们实际如何使用它时，我会感到惊讶。

[原文] [Greg]: yeah I think uh that's always the case with with platforms especially if you think about it like when when the makers of the app store created the app store you know the the initial apps was like you know a beer drinking app and like a bunch of random apps like that did they know that you know Uber was going to come out of that Door Dash was going to come out of that Tik Tok was going to come out of that probably not

[译文] [Greg]: 是的，我认为平台总是这样的，特别是如果你回想一下，当 App Store 的制造者创建 App Store 时，最初的 App 就像是一个喝啤酒的 App 以及一堆像那样的随机 App。他们知道 Uber 会从中诞生吗？DoorDash 会从中诞生吗？TikTok 会从中诞生吗？可能不知道。

[原文] [Greg]: so I think that what's really cool about the phase that we are in right now with Claude Code and also Claude Co-work is we're all figuring it out at the same time and none of us including the creator have all the answers,

[译文] [Greg]: 所以我认为我们现在处于 Claude Code 和 Claude Co-work 的这个阶段非常酷的一点是，我们都在同时探索它，我们中没有人（包括创造者）拥有所有答案。

[原文] [Greg]: but I agree with you like what's it's it's a good time to be sharing some you know sharing what's working not working and you know if you're open to it let's let's screen share and get our hands dirty

[译文] [Greg]: 但我同意你的看法，这是一个分享的好时机，分享什么有效、什么无效。如果你愿意的话，让我们进行屏幕共享，亲自动手试一试（get our hands dirty）。

章节 2：核心概念解构：什么是 Agentic AI (Core Concepts: What is Agentic AI)

📝 本节摘要：

在本节中，Boris 展示了 Claude 桌面应用的界面，包括 Chat、Co-work 和 Code 三个主要标签页。他深入剖析了“Agentic（代理）”这一术语，认为该词因被滥用而失去了原意。Boris 定义了真正的 Agentic AI：区别于仅能生成文本或搜索网络的传统 AI，它能够“采取行动（take action）”，使用电脑工具并与现实世界交互。这正是 Anthropic 从早期就确立的发展路径：从编程能力，到工具使用，最终实现计算机操控能力。

[原文] [Greg]: so what are we looking at right now Boris yeah so this is the this is the cloud desktop app um so you just download it um it co-work is only available for Mac OS um you know Windows coming soon uh there's a few different tabs in the desktop app so there's the chat that's the default there's co-work that's the new one and there's code and that's just quad code

[译文] [Greg]: 那么我们现在看的是什么，Boris？是的，这就是 Claude 桌面应用程序，你只需要下载它。Co-work 目前仅支持 Mac OS，Windows 版本即将推出。桌面应用程序中有几个不同的标签页：默认的是 Chat（聊天），新的是 Co-work，还有 Code，也就是 Claude Code。

[原文] [Boris]: um co-work under the hood it's actually just quad code and so you know the agent that makes quad code awesome we call it the quad agent it's also available as the quad agent SDK so you can use it programmatically you can you know all sorts of companies build all sorts of cool things on top of it we actually use that same exact SDK directly in co-work

[译文] [Boris]: Co-work 的底层实际上就是 Claude Code。让 Claude Code 如此出色的代理（agent），我们称之为 Claude Agent，它也以 Claude Agent SDK 的形式提供。所以你可以通过编程方式使用它，各种公司都在通过它构建各种很酷的东西。我们在 Co-work 中直接使用了完全相同的 SDK。

[原文] [Boris]: um so it's like you know it's pretty cool just kind of one layer across everything we have the best agent have the best agentic model might as well use it and so what I'll do is just to kind of show how how to use this thing and you know like when I think about agentic AI this word agentic has sort of lost all meaning cuz it it's just like used so much

[译文] [Boris]: 这很酷，就像是横跨所有事物的一层。既然我们拥有最好的代理和最好的代理模型（agentic model），那就不妨加以利用。所以我将演示如何使用这个东西。你知道，当我想到“Agentic AI”（代理 AI）时，我觉得“Agentic”这个词已经某种程度上失去了所有意义，因为它被使用得太滥了。

[原文] [Boris]: so I feel like probably a lot of listeners have heard the word agent but they don't actually know what it means or you know they think it's like some like cool AI or or something but it it actually has like a very specific meaning in the AI world which I think has kind of been lost because a lot of the products that people have released in cold agentic in the past are not actually agentic

[译文] [Boris]: 我觉得很多听众可能都听过“Agent”（代理）这个词，但他们并不真正知道它是什么意思，或者以为它就是某种酷炫的 AI 之类的。但在 AI 领域，它实际上有着非常具体的含义，我认为这个含义已经有点丢失了，因为过去人们发布的许多被称为“Agentic”的产品实际上并不具备代理能力。

[原文] [Boris]: and so like when you think about the AI products that everyone's used you know like obviously quad code uh chat based apps where you know you just chat with the app kind of back and forth send some messages the biggest difference with agents is uh it can take action and you know it's not just text and it's not just like web searching but it can actually use tools on your computer it can it can interact with the world

[译文] [Boris]: 当你想到大家都在使用的 AI 产品时，比如显而易见的 Claude Code，或者是基于聊天的应用程序，你只是和应用程序来回聊天、发送一些信息。代理最大的区别在于它可以采取行动（take action），不仅仅是文本，也不仅仅是网络搜索，而是它实际上可以使用你电脑上的工具，它可以与世界互动。

[原文] [Boris]: and so for anthropic from the very beginning since before our models were good like before like you know like cloud 3 or whatever this is a thing that we wanted to get really good at because we felt that it's very important um and so from the start we wanted our models to be really great at coding and then really great at tool use and then really great at computer use

[译文] [Boris]: 对于 Anthropic 来说，从一开始，甚至在我们的模型变得优秀之前——比如在 Claude 3 或其他版本之前——这就是我们想要真正擅长的事情，因为我们觉得这非常重要。所以从一开始，我们就希望我们的模型非常擅长编程，然后非常擅长工具使用，接着非常擅长计算机使用。

[原文] [Boris]: so it's it's kind of cool like you know the last year seeing how people have been hacking quad code it's pretty obvious this is kind of the place that we should go um and so for people that have used quad code you know none of this will be you know like too surprising these are actually things that you can do so really what we're trying to do is make this something that everyone can use in a way that's safe

[译文] [Boris]: 所以这有点酷，过去一年看着人们如何破解（hacking）Claude Code，很明显这就是我们要去的方向。对于使用过 Claude Code 的人来说，这都不会太令人惊讶，这些实际上都是你可以做的事情。所以我们真正想做的是让每个人都能以安全的方式使用它。

章节 3：实操演示一：文件管理与安全机制 (Demo I: File Management & Safety Layers)

📝 本节摘要：

在本节中，Boris 演示了 Co-work 的基础功能：管理本地文件。他向 Co-work 授予了“收据”文件夹的访问权限，并要求其根据日期重命名文件。演示中展示了 AI 的“反向启发（Reverse Elicitation）”能力——当遇到日期缺失的文件时，模型会主动询问用户如何处理，而非盲目猜测。此外，Boris 详细阐述了产品的多层安全机制，包括底层的“对齐（Alignment）”研究、隔离的虚拟环境（Virtual Machine）、以及针对误删文件的保护提示，确保 AI 在接管电脑时的安全性。

[原文] [Boris]: and so what I'm going to do is um you know here on my desktop I have a I have this like receipts folder i have a few receipts in it um so I'm just going to give uh co-work access to my desktop and you you have to pick like which specific folders it can see by default it can't see anything so you have to kind of opt in to see to let it uh access specific folders

[译文] [Boris]: 那么我要做的是，在我的桌面上有一个“收据”文件夹，里面有一些收据。我要给 Co-work 访问我桌面的权限，你必须选择它能看到哪些特定的文件夹，默认情况下它什么也看不到，所以你必须选择性地让它访问特定的文件夹。

[原文] [Boris]: and so I'm going to say um you know I can say uh I have a receipts folder can you rename the files to match the dates on the receipts

[译文] [Boris]: 然后我会说，我有一个收据文件夹，你能把文件名重命名为与收据上的日期相匹配吗？

[原文] [Greg]: so so I think one interesting thing is when you're using co-work it's really like it's operating with your files like that's a that's a big sort of mindset shift that people should have it's almost like your operating system is that right

[译文] [Greg]: 所以我认为有一件有趣的事情是，当你使用 Co-work 时，它真的就像在操作你的文件一样，这是人们应该有的一个巨大的思维转变，它几乎就像你的操作系统，是这样吗？

[原文] [Boris]: yeah exactly it's like it it has your files so the ones that you give it access to um but actually the even cooler thing is it can use all sorts of tools um and so like files actually is like you know that's like that's useful but it's not it's not like that cool what's actually much more interesting is it can generate files for you so you know it can make like presentations and things like this

[译文] [Boris]: 是的，没错，就像它拥有你的文件一样（指那些你授权给它的）。但实际上更酷的是它可以使用各种各样的工具。像文件操作实际上……你知道这很有用，但这并不是那么酷，实际上更有趣的是它可以为你生成文件，所以它可以制作演示文稿之类的东西。

[原文] [Boris]: um it can interact with any tool over MCP and it has built-in support for Chromebased browsers um so it can actually control your browser to do to do stuff and so I'll I'll kind of show that a little bit

[译文] [Boris]: 它可以通 MCP（Model Context Protocol）与任何工具交互，并且内置了对基于 Chrome 的浏览器的支持，所以它实际上可以控制你的浏览器去做事情，稍后我会演示一下。

[原文] [Boris]: so this is kind of the first step um when you're first getting started with co-work the thing I recommend is you know do exactly what I just did you know just mount a folder give co-work access to it um and just like play around with it it's it's super useful for cleaning up files organizing things like that

[译文] [Boris]: 这算是第一步。当你刚开始使用 Co-work 时，我推荐的做法就是做我刚才做的事，挂载一个文件夹，给 Co-work 访问权限，然后试着玩一下。它对于清理文件、组织此类事物非常有用。

[原文] [Boris]: um and so here it found these four receipts that I have um it's asking me if uh one of the receipts I guess is missing a date so should it just rename the others so I'll just say um you know for one it's we'll say it's like up to you and then for two I'll say uh don't rename it

[译文] [Boris]: 在这里它找到了我有这四张收据，它在问我……我猜其中一张收据缺少日期，所以是否应该只重命名其他的？我会说，对于第一张，就由你决定；对于第二张，我说不要重命名它。

[原文] [Boris]: and we actually call this uh like reverse elicitation in the AI world so so what this means is when the model is unsure about something it's going to ask you for clarification um and we've sort of taught the model to be pretty good at this so instead of assuming if it's unsure about something it's just going to ask you

[译文] [Boris]: 在 AI 领域我们实际上称之为“反向启发（reverse elicitation）”。这意味着当模型对某事不确定时，它会要求你进行澄清。我们已经教导模型在这方面做得相当好，所以当它对某事不确定时，它不会擅自假设，而是会直接问你。

[原文] [Boris]: And so yeah in this case so it renamed the receipts so I'm just going to open this up to double check yeah cool and so the receipts are renamed a little bit better organized and so maybe what I can try next is um let's like put this in a spreadsheet

[译文] [Boris]: 是的，在这个案例中它重命名了收据，我打开检查一下，是的，很酷。收据被重命名了，组织得更好了一些。所以也许我接下来可以尝试的是，让我们把这些放入一个电子表格中。

[原文] [Greg]: so it takes control of your computer basically in that sense right if you allow it to take control

[译文] [Greg]: 所以从这个意义上说，它基本上接管了你的电脑控制权，对吧？如果你允许它接管的话。

[原文] [Boris]: yeah yeah that's right and so we put like so much work into kind of safety and making sure that as this happens you don't you don't like accidentally shoot yourself in the foot and like delete files or whatever um so there's just like a huge amount of work that went into this

[译文] [Boris]: 是的，没错。所以我们在安全性上投入了大量工作，确保在发生这种情况时，你不会意外地“搬起石头砸自己的脚”，比如删除了文件之类的。所以在这方面投入了巨大的工作量。

[原文] [Boris]: and it kind of starts at the model side where you know for anthropic from the very beginning we were the AI safety lab and that's the reason that we exist um and so there's a lot of work into like alignment and mechanistic interpretability and kind of all these ideas to to make sure that the model does what you want in a way that's safe kind of at the model layer

[译文] [Boris]: 这某种程度上始于模型端。你知道对于 Anthropic 来说，从一开始我们就是 AI 安全实验室，这是我们存在的理由。所以在“对齐（alignment）”和“机械可解释性（mechanistic interpretability）”以及所有这些理念上有很多工作，以确保模型在模型层面上以安全的方式做你想要它做的事。

[原文] [Boris]: and this literally means like studying the neurons kind of the same way that you would study uh neurons in you know like in in the human um and so we you know you can like identify structures and you can kind of study in a very scientific way as a black box also um to make sure that it's safe so this is called alignment

[译文] [Boris]: 这字面上的意思就是研究神经元，就像你研究人类神经元一样。你可以识别结构，你可以用非常科学的方式研究它（即使作为一个黑盒），以确保它是安全的，这被称为对齐。

[原文] [Boris]: um and then we do a whole bunch of other stuff so there's actually a whole virtual machine running under the hood and this is just to make sure that any actions taken are safe and don't affect your broader system

[译文] [Boris]: 然后我们还做了一堆其他的事情，实际上底层运行着一个完整的虚拟机，这只是为了确保所采取的任何操作都是安全的，并且不会影响你更广泛的系统。

[原文] [Boris]: um and then as of last week there's also deletion protection so if you accidentally delete something then um you're going to get prompted first um so the model can kind of make sure that that's actually a thing that you want to do

[译文] [Boris]: 就在上周，我们还加入了删除保护功能，所以如果你意外删除了什么东西，你会先收到提示，这样模型可以某种程度上确保这确实是你想要做的事情。

[原文] [Boris]: obviously also as we start interacting with the internet something like prompt injection is quite scary and so we built in a lot of protections against that um obviously you know is it's not perfect and it's something we're iterating on um but this is also part of the reason that we released this pretty early is we want to see how people use it and a big part of making models safe isn't just studying them on a lab but studying them in the wild um to see how it's useful

[译文] [Boris]: 显然，当我们开始与互联网交互时，像“提示注入（prompt injection）”这样的事情相当可怕，所以我们要对此内置了很多保护措施。显然，它并不完美，这也是我们正在迭代的事情。但这也就是我们要尽早发布它的部分原因，我们想看看人们如何使用它。让模型变安全的很大一部分不仅仅是在实验室里研究它们，而是在现实世界（in the wild）中研究它们，看看它是如何被使用的。

章节 4：实操演示二：接管浏览器与电子表格 (Demo II: Browser Control & Spreadsheets)

📝 本节摘要：

演示进入深水区，Boris 展示了 Co-work 如何突破本地环境，直接接管浏览器创建 Google Sheet。期间，他回忆了早期模型（Sonnet 3.5时期）操作电脑的趣事——当时为了演示“点比萨”这一简单动作，AI 竟耗时一小时。面对现在的进化速度，Greg 用 iPhone App Store 早期的“喝啤酒应用”做类比，认为我们目前正处于 AI Agent 应用爆发的前夜，正如当年人们无法预见 Uber 的诞生一样，现在也无法完全预知 Agent 的未来形态。

[原文] [Boris]: um and so this was like pretty cool right so we we have this folder um first it kind of renamed all all my receipts i asked it to make a sheet it just made this spreadsheet so it's already here um maybe I don't want a spreadsheet maybe I want like a Google sheet

[译文] [Boris]: 这看起来挺酷的对吧？我们有了这个文件夹，首先它重命名了我所有的收据，我让它制作一个表格，它就做好了这个电子表格，它已经在这里了。但也可能我不想要（本地）电子表格，也许我想要一个 Google Sheet。

[原文] [Boris]: so actually that's so interesting right cuz like I think uh where people stumble with tools like co-working and cloud code is because you can do anything making it of course that makes sense making it a Google sheet but like that's where it's so interesting that you can you really can treat it like a teammate in that sense right like go and do this thing the world is your oyster

[译文] [Boris]: 实际上这非常有意思，因为我认为人们在使用 Co-work 和 Claude Code 这类工具时会遇到障碍，是因为你可以做“任何事”。制作一个 Google Sheet 当然合乎逻辑，但这正是它的有趣之处——你真的可以把它当作一个队友，就像在说“去把这件事做了”，世界尽在你的掌握之中（the world is your oyster）。

[原文] [Greg]: whoa what is happening right now yeah so it's like it's opening the browser

[译文] [Greg]: 哇，现在发生了什么？是的，它好像正在打开浏览器。

[原文] [Boris]: um and so here it's going to ask me from for permission just for this demo I'm going to say always allow for the site um but you can just say like allow once or deny and so Quad's taking the wheel um it's making a spreadsheet for me

[译文] [Boris]: 在这里它会请求我的许可。仅仅为了这次演示，我会选择“总是允许该网站”，但你也可以选择“仅允许一次”或“拒绝”。现在 Claude（Quad）正在接管控制权（taking the wheel），它正在为我制作电子表格。

[原文] [Boris]: um this is going to sort of take a while and so this is one of the things that we're iterating on is like making this kind of computer use a lot faster i I remember like man this is like when I first joined Enthropic and this was maybe um this like sonnet 3.6 6 days or I forgot what what we called it like Sonic 3.5 new um and that was the first model that I think we really started to crack computers

[译文] [Boris]: 这可能会花一点时间，这也是我们正在迭代的事情之一，即让这种计算机操作变得更快。我记得，天哪，就像我刚加入 Anthropic 时，那可能是 Sonnet 3.6 时代，或者我忘了我们叫它什么了，好像是 Sonnet 3.5 New？那是第一个我认为我们真正开始攻克计算机操作的模型。

[原文] [Boris]: and I remember I was like sitting with my team and there was literally a researcher that ran into the room like in the movies and was like oh my god quad knows how to use computers and um we just had it like order a pizza and it uh it picked a pineapple pizza and then ordered it and it asked us for a credit card and then we we got that delivered to the office but it was tedious it took like an hour or something for it to click around and since then we've been improving the model's ability to use a computer

[译文] [Boris]: 我记得当时我和团队坐在一起，真的有一个研究员像电影里那样跑进房间，说：“天哪，Claude 知道怎么用电脑了！”我们让它订个比萨，它选了一个菠萝比萨然后下单了，它还向我们要了信用卡，最后确实送到了办公室。但那过程很繁琐，它到处点击花了大概一个小时。从那时起，我们一直在提高模型使用计算机的能力。

[原文] [Boris]: um and so you can kind of see that here so here the you know quad is typing and it's interacting with the spreadsheet and it can see what's on the screen it can interact with it anything that's in your browser it it can just use

[译文] [Boris]: 所以你可以在这里看到，Claude 正在打字，正在与电子表格交互。它能看到屏幕上的内容，并与之交互。任何在你浏览器里的东西，它都可以直接使用。

[原文] [Boris]: okay so let's like let's make this like kind of a nice spreadsheet because we don't want to send like a badly formatted spreadsheet to our coworker um but let's make it nice and then uh we can ask Quad to send it

[译文] [Boris]: 好的，让我们把它做成一个漂亮的电子表格，因为我们要发给同事，不想发一个格式糟糕的表格。让我们把它弄漂亮点，然后我们可以让 Claude 发送它。

[原文] [Boris]: and so here it's kind of cool it's like you know it's it's still early days and so there's some like formatting mistakes it didn't paste it exactly correctly but it noticed it so notice that you know it's not actually split correctly and so now it's trying to format it

[译文] [Boris]: 这里很酷的一点是，你知道现在还处于早期阶段，所以会有一些格式错误，它粘贴得不完全正确，但它注意到了。它注意到数据并没有被正确分割，所以现在它正在尝试重新格式化它。

[原文] [Greg]: um kind of notice this and yeah Greg like to your point it's funny these like these use cases and the way that people are going to use these tools like I said at the start it's going to be so surprising um I'm just so excited to see how people use it and sort of the crazy thing about them is they're so general purpose it's like it's sort of like a computer itself or like the internet or something

[译文] [Greg]: 注意到了这点。是的，就像你说的，这很有趣，这些用例以及人们使用这些工具的方式，正如我一开始所说，将会非常令人惊讶。我很兴奋看到人们如何使用它。这东西疯狂的地方在于它们是如此通用，就像计算机本身，或者像互联网一样。

[原文] [Greg]: like like you said like when when you first like had an iPhone like you would never have predicted that you know there would be an Uber app at some point but you know that's that's what happened um and I sort of feel like we're at the beginning of that but for for agents

[译文] [Greg]: 就像你说的，当你第一次拥有 iPhone 时，你绝不会预测到某个时候会出现 Uber 应用，但你知道那就是发生了。我觉得我们现在正处于那个阶段的开端，只不过这次是针对“代理（Agents）”的。

章节 5：工作流变革：并行处理与自动化 (Workflow Shift: Parallelism & Automation)

📝 本节摘要：

本节的核心在于工作流的彻底转变。Greg 思考如何通过“审计”公司内部的繁琐任务来寻找自动化机会。Boris 提出了“并行处理（Parallelism）”的概念——与其盯着 AI 完成单一任务，不如同时运行多个任务（Multi-Clauding）。他形象地将这种新角色比作从“执行者”转变为“管理者”：你只需启动任务、去喝杯咖啡，然后回来“照看（tending）”这些正在工作的 AI。他还分享了一个具体案例：利用 Co-work 自动检查团队进度表，并在 Slack 上催促未填写的工程师，从而省去了恼人的微管工作。

[原文] [Greg]: like I'm watching this and I'm like this is really cool but I'm thinking about like okay you know how do I audit like my entire company like what are all the tasks that the company is doing how are they interacting with files and how are they using the internet and how are they sending things and then what are opportunities I can use to like make my team and also my life more productive that's what's going through my head right now

[译文] [Greg]: 就像我看着这个，我觉得这真的很酷，但我正在思考，好吧，我该如何审计我的整个公司？比如公司正在做的所有任务是什么？他们如何与文件交互？他们如何使用互联网？他们如何发送东西？然后有哪些机会是我可以利用来让我的团队以及我的生活更高效的？这就是我现在脑子里在想的事情。

[原文] [Boris]: yeah yeah totally that's a great way to think about it um and by the way something that's kind of cool is you know as this is running I'm just going to make a new task and do something else um so you know what are some cool episodes uh start up Cool and so while while this one's running we can like we can let this one go too and I often have a bunch of tasks running in parallel too

[译文] [Boris]: 是的，完全正确，这是一个很好的思考方式。顺便说一下，有一件很酷的事情是，当这个任务正在运行时，我打算创建一个新任务去做点别的事情。比如“有哪些很酷的剧集？”……启动。酷，所以当这一个正在运行时，我们可以让那一个也继续运行，我经常也有很多任务并行运行。

[原文] [Boris]: but yeah that's exactly it it's like you should just think about like what what's all like the tedious stuff that you do every day and you can just throw all the stuff to cowork um and I I feel like this happened for coding over the last year because of course engineers and you know programmers are the earliest adopters so when the tooling first be became able to do that kind of work engineers adopted it first but you know now now this is coming uh uh now this is possible for everyone else to use too so that's like that's super exciting

[译文] [Boris]: 是的，正是如此。你应该思考一下你每天做的所有那些乏味琐碎的事情，你可以把所有这些东西都扔给 Co-work。我觉得这在过去一年的编程领域已经发生了，因为工程师和程序员当然是最早的采用者，所以当工具最初能够做那种工作时，工程师们首先采用了它。但你知道，现在这也来了，现在这对于其他人来说也成为可能了，所以这超级令人兴奋。

[原文] [Boris]: and when we talk to engineers about the way they like to use quad code you know they run a bunch of quads in parallel they use it to automate the tedious stuff and I don't know man like for me this is just the most fun I've ever had as an engineer cuz I get to do the stuff that I enjoy and I just feel so productive because Quad does all the you know the stuff that I didn't want to do

[译文] [Boris]: 当我们和工程师谈论他们喜欢如何使用 Claude Code（原文作 quad code）时，你知道他们会并行运行一堆 Claude，他们用它来自动化那些乏味的事情。我不知道怎么形容，老兄，对我来说，这是我作为工程师以来最开心的时候，因为我可以做我喜欢的事情，而且我感觉效率极高，因为 Claude 做了所有那些我不通过想做的事情。

[原文] [Boris]: um okay so now we have this like we have the spreadsheet this looks all right it's not too bad um the data looks correct um you know one thing that's missing though is uh uh well we we can add maybe like the totals but I think for the sake of the demo what I'm going to do is um I'm going to see if it can email it so just reading for our audio listeners can you open Gmail and send the sheet to Amy and Wow yeah so I'm going to say always continue

[译文] [Boris]: 嗯，好的，现在我们有了这个电子表格，看起来还行，不算太差，数据看起来是正确的。虽然缺了一样东西，比如我们可以加上总计，但我认为为了演示起见，我要做的是看看它能不能把它通过邮件发出去。为了我们的音频听众读一下指令：“你能打开 Gmail 并把这个表格发给 Amy 吗？”哇，是的，所以我选择“始终继续”。

[原文] [Greg]: so how is it going to know it's Amy right it's going to pull up the contacts within Gmail yeah yeah exactly um yeah that that's exactly it it's going to interact with it the same way that uh you know anyone else would interact with a computer and it's the same thing it can it can like click stuff it can read the screen okay so compose window open let me type Amy

[译文] [Greg]: 所以它怎么知道是哪个 Amy 呢？对吧，它会在 Gmail 里调取联系人吗？是的，没错。完全就是这样，它会像任何其他人与电脑交互一样与它交互。这是一样的，它可以点击东西，它可以读取屏幕。好的，“撰写窗口打开，让我输入 Amy”。

[原文] [Greg]: so you have like multiple when you're when you're like locked in so to speak you're kind of you have multiple of these windows open at or multiple multiple virtual machines open at at the same time

[译文] [Greg]: 所以当你处于“全神贯注（locked in）”状态时，可以这么说，你会同时打开多个这样的窗口，或者同时打开多个虚拟机吗？

[原文] [Boris]: yeah yeah i usually have a bunch of these um you know like five or five or 10 or whatever um and so we can see the models you know trying to interact with this and so it filled out Amy and you know by the way just so because this is you know going on YouTube you know you're going to have some haters in the comments so we're just going to address them right now someone in the comments is going to be like "But that's so slow i can do it faster myself or something." What is your reaction

[译文] [Boris]: 是的，是的，我通常有一堆这样的窗口，你知道，大概 5 个或 10 个之类的。我们可以看到模型正在尝试与之交互，它填好了 Amy。顺便说一下，因为这是要发到 YouTube 上的，你知道评论区会有一些喷子（haters），所以我们现在就来回应他们。评论区肯定会有人说：“但这太慢了，我自己做会更快之类的。”你对此有什么反应？

[原文] [Boris]: yeah of course you can yeah um I could definitely do this much faster and it's actually the same thing for a lot of quad code right like especially at the beginning I I could do it much faster um but but I think sort of two things happen one is that uh the model just gets better at doing it quickly and this is just something you would I I would expect over time

[译文] [Boris]: 是的，你当然可以。我绝对可以做得比这快得多，这实际上对于很多 Claude Code 的操作也是一样的，对吧，特别是在开始的时候，我可以做得快得多。但我认为会发生两件事：一是模型会越来越擅长快速完成任务，这是我预计随着时间推移会发生的。

[原文] [Boris]: but then the second thing is because you can do multiple things in parallel it's actually a big time saver and so usually my workflow is I'll kick off you know like a few different tasks in parallel and I'll just kind of like go back and forth between them and kind of tend to my quads make sure they're in a good place see if they have any questions or anything like that

[译文] [Boris]: 但第二件事是，因为你可以并行做多件事，这实际上是一个巨大的时间节省器。所以通常我的工作流程是，我会并行启动几个不同的任务，然后我就在它们之间来回切换，有点像“照看我的 Claude 们（tend to my quads/Claudes）”，确保它们处于良好状态，看看它们是否有什么问题之类的。

[原文] [Boris]: so it's really a different kind of workflow like I feel like now is the age of like kind of multi- multi- clotting of of paroism of like not going super deep on stuff but kind of being more of a generalist and more tending tending to your clouds and so like this was this other chat that we kicked off earlier um and in this case it sort of did some research so that's pretty cool

[译文] [Boris]: 所以这真的是一种不同的工作流程。我觉得现在是某种“多重 Claude 并行（multi-Clauding）”的时代，是并行主义的时代，不再是深入钻研某件事，而是更多地成为一个通才，更多地去“照看你的云端智能体（tending to your clouds）”。看，这是我们刚才启动的另一个聊天，在这个案例中它做了一些研究，这很酷。

[原文] [Boris]: and I also use this for like Slack too like a pretty common use case I've been doing maybe a couple times a week is I have a spreadsheet where we track all the team's work for for the month or for the week or whatever and instead of having to bug everyone on the team to fill out the status what I do is I ask co-work to look at the spreadsheet any column that's not filled out just message the engineer on Slack um and it does that really well so you know I I just ask it to do that and then I go get a coffee and I I don't have to do that anymore

[译文] [Boris]: 我也把这个用于 Slack，比如我大概每周做几次的一个非常常见的用例是：我有一个电子表格，用来跟踪团队这一个月或这一周的所有工作。与其还要去烦团队里的每个人让他们填写状态，我做的是让 Co-work 查看电子表格，任何没有填写的栏目，就直接在 Slack 上给那个工程师发消息。它做得非常好，所以我只需要让它去做，然后我去喝杯咖啡，我再也不用亲自做那件事了。

章节 6：用户分层与技能扩展 (User Segmentation & Skills Expansion)

📝 本节摘要：

Greg 询问 Co-work 是否会成为通往 Claude Code 的“入门药”，因为后者对初学者来说略显硬核。Boris 分享了一个令人惊讶的数据：在 Anthropic 内部，许多非技术人员（如销售、设计师）早已开始使用基于终端的 Claude Code。他解释道，Co-work 旨在为这部分人群提供更友好的 UI。随后，两人探讨了“Skills（技能）”的概念——这是一种让 AI 掌握特定工具（如 Excel 或 AutoCAD）的封装能力。Boris 建议 Co-work 用户初期保持简单，不要像工程师那样过度定制，除非遇到特定软件无法处理的情况再考虑编写 Skill。

[原文] [Greg]: do you think that co-work is going to be the gateway drug to cloud code because for a lot of beginners nontechnical people cloud code feels a bit overwhelming but when I'm when I'm watching you do this this feels you know approachable

[译文] [Greg]: 你认为 Co-work 会成为通向 Claude Code 的“入门药（gateway drug）”吗？因为对于许多初学者和非技术人员来说，Claude Code 感觉有点让人不知所措，但当我看着你做这些时，感觉这很平易近人。

[原文] [Boris]: yeah i I mean I think it's like probably two kinds of users um Well and it's also it's funny cloud code is built originally in a terminal and you know now nowadays it's available in the Quad mobile app it's available on the website uh in the IDE on Slack on GitHub so you know nowadays it's available everywhere but originally it was built in a terminal and I never thought that most engineers would want to use a terminal cuz you know it's scary it's like this thing that's sort of hidden away on the computer like you know only the most hardcore engineers want to actually work in a terminal day in and day out and so it's surprising to me that most engineers wanted to use it

[译文] [Boris]: 是的，我想这可能涉及两类用户。这也很有趣，Claude Code 最初是构建在终端（terminal）里的，虽然现在它可以在 Claude 移动应用、网站、IDE、Slack 和 GitHub 上使用，所以现在它无处不在，但最初它是建立在终端里的。我从未想过大多数工程师会想要使用终端，因为你知道那很可怕，就像是藏在电脑深处的某种东西，只有最硬核的工程师才想整天在终端里工作。所以大多数工程师想用它这点让我很惊讶。

[原文] [Boris]: what's even more surprising is a lot of non-engineers started to use it and that was the craziest thing and you know looking at like the sales team at Enthropic like the GTM team half of them use quad code every week um and looking at other non-technical people at Enthropic like designers product managers data scientists pretty much all of them use quad code every day

[译文] [Boris]: 更令人惊讶的是，许多非工程师也开始使用它，这是最疯狂的事情。看看 Anthropic 的销售团队，比如 GTM（Go-To-Market）团队，他们中有一半人每周都在使用 Claude Code。再看看 Anthropic 的其他非技术人员，如设计师、产品经理、数据科学家，几乎所有人每天都在使用 Claude Code。

[原文] [Boris]: so that that's been like pretty surprising but my hypothesis is what they would prefer is actually something a little bit more like this where you don't have to deal with a terminal and all that kind of thing you have a you have a nice UI um because you don't need access to bash and all that kind of stuff cuz the the model will just do it for you

[译文] [Boris]: 这确实相当令人惊讶，但我的假设是，他们实际上更喜欢像 Co-work 这样一点的东西，你不需要处理终端和所有那一类事情，你有一个漂亮的 UI。因为你不需要访问 Bash（命令行）那一类东西，模型会为你完成它。

[原文] [Greg]: yeah i think what I would love with something like this is you know automating some of these processes it's like instead of doing oneoffs it's like anytime this happens I want you to do this that's my dream

[译文] [Greg]: 是的，我想我最希望这类工具能做到的就是自动化其中一些流程。不再是一次性地做某事，而是像“每当发生这种情况时，我都要你做这个”，那是我的梦想。

[原文] [Boris]: yeah it's a cool idea i'm excited to see like how it's tied into skills also i think it's something we're we're thinking about we haven't quite figured out yet um yeah cuz like a skill what what is it it's essentially kind of a repeatable way to do something and so you saw that a little bit earlier up in this conversation where um when Quad was generating the spreadsheet um I don't know if you saw but it actually loaded the skill and so we prepackaged the skill for Excel and that's the way that Quad knows how to do it

[译文] [Boris]: 是的，这是一个很酷的想法。我很期待看到它如何与“技能（Skills）”结合起来，这也是我们在思考但还没完全弄清楚的事情。因为像“技能”是什么？它本质上是一种可重复的做事方式。你在刚才的对话中也看到了一点，当 Claude 生成电子表格时，不知道你是否注意到，它实际上加载了一个技能。我们为 Excel 预打包了一个技能，这就是 Claude 知道如何操作它的方式。

[原文] [Boris]: um and so if you have some like weird file format I don't know if you work with like AutoCAD or if you work with you know like Salesforce kind of what whatever it is the tool the tool that you use you just make a skill and then quad can can do it for you

[译文] [Boris]: 所以如果你有一些奇怪的文件格式，我不道你是否使用 AutoCAD，或者你是否使用 Salesforce，无论是什么工具，你使用的那个工具，你只需要制作一个技能，然后 Claude 就可以为你操作它。

[原文] [Greg]: that's interesting so if you have more skills co-working it you know to do things related to those skills co-workers is more likely to use those skills so you might be able to get a better outcome out of co-work if you you know do some upfront work to actually create some skills

[译文] [Greg]: 这很有趣。所以如果你在 Co-work 中拥有更多技能去做相关的事情，Co-work 就更有可能使用这些技能。如果你做一些前期工作去实际创建一些技能，你可能会从 Co-work 中获得更好的结果。

[原文] [Boris]: i think so yeah wow yeah I think I think that's exactly right yeah okay well that's good to know and and you know what else do we need to know about co-work cuz I know there's you know there's you know extensions there's there's skills like walk us through some of is there anything else that you know we need to know in order to get the most out of of the product

[译文] [Boris]: 我认为是这样的，是的。哇，我想这完全正确。好的，这很高兴知道。除此之外我们还需要了解关于 Co-work 的什么？因为我知道有扩展（extensions），有技能，能不能带我们要过一遍？还有什么我们需要知道的以便充分利用这个产品吗？

[原文] [Boris]: you know we we tried to build cowork just to be pretty simple um when we think about the different audiences we serve for an audience like engineers they don't actually like simple like simple is is good by default but engineers love to hack their tools they love to customize their tools um so that's actually really important so Quad Code is just like the most customizable coding agent it has just like so many extension points there's like there's skills there's custom agents uh there there's hooks there's a an insane amount of configuration and settings that you can set

[译文] [Boris]: 你知道，我们试图把 Co-work 构建得非常简单。当我们考虑我们服务的不同受众时，像工程师这样的受众，他们实际上不喜欢“简单”。默认情况下简单是好的，但工程师喜欢破解（hack）他们的工具，他们喜欢定制他们的工具，所以这实际上非常重要。Claude Code 就像是可定制性最强的编程代理，它有太多的扩展点，有技能，有自定义代理，有钩子（hooks），有疯狂数量的配置和设置供你设定。

[原文] [Boris]: for some of my co-work I think we're kind of starting in the opposite direction um and just keep it really simple at the start um and so if you use co-work I would probably not customize too much like if you have co-work installed and you install the Chrome extension that's pretty much all you need and it'll do everything else for you i think over time as you find yourself using maybe software that co-work is not great at like that's the point to think about writing skills but that wouldn't be my starting point just start simple

[译文] [Boris]: 对于 Co-work，我认为我们的起点方向有点相反，我们在开始时保持它非常简单。所以如果你使用 Co-work，我可能会建议不要过度定制。如果你安装了 Co-work 并且安装了 Chrome 扩展，那基本上就是你所需要的一切，它会为你做其他所有事情。我认为随着时间的推移，当你发现自己使用的某些软件 Co-work 并不擅长时，那才是考虑编写技能的时候，但我不会以此为起点，刚开始就保持简单。

章节 7：未来展望：2027年的AI协作 (Future Outlook: AI Collaboration in 2027)

📝 本节摘要：

在本节中，Greg 邀请 Boris 预测一年后（2027年1月）的世界。Boris 坦言，由于 AI 模型的指数级进化，人类线性的思维很难进行准确预测。他回顾了自己曾预测“人们将不再通过手写代码”，这一看似激进的观点如今已在他身上应验——过去两个月 Claude Code 编写了他 100% 的代码。他认为 Co-work 也将遵循此路径：处理所有连接应用、数据搬运等乏味工作。Boris 预言 Co-work 将演化出针对特定垂直领域（如 AutoCAD）的“数字同事（Digital Teammates）”，人们将像招聘员工一样“雇佣”这些具有特定技能的 AI Agent。

[原文] [Greg]: you know we're recording this uh what is it january 2026 if we if we come back here in 12 months it's January 2027 how do you think people are going to be using co-work you know I know you don't have a crystal ball exactly but what sort of use cases and and what is what does the product look like like describe the world in January 2027 with with co-work

[译文] [Greg]: 你知道我们正在录制这个，现在是……2026年1月（注：此处原文口误说成2026，结合语境应指当前时间）。如果我们12个月后回到这里，那就是2027年1月。你认为人们将如何使用 Co-work？我知道你没有水晶球能精准预测，但是会有什么样的用例？产品会是什么样子？描述一下有了 Co-work 的2027年1月的世界。

[原文] [Boris]: oh jeez Greg i I plan in like a oneweek timeline the model is just changing so fast it's it's so hard and I just feel like you know like the model is it's advancing exponentially and just like my puny human meat brain like can't grapple with exponential it's like we think in lineers and so I think this kind of exponential is just very very difficult to plan around

[译文] [Boris]: 噢天哪，Greg，我是按一周的时间线来做计划的。模型变化得太快了，这太难了。我只是觉得，你知道模型正在呈指数级进步，而我那微小的人类“肉脑（meat brain）”无法理解指数级变化，我们是线性思考的，所以我认为围绕这种指数级变化进行规划是非常非常困难的。

[原文] [Boris]: um okay but if if I had to speculate um a year ago I made and I think Dario also made this prediction that by the end of the year people wouldn't be writing code anymore and I think that was like sometime mid uh you know la last year or something in you know I I code every day uh I ship you know two 300 PRs every month or something like that uh and in the last two months quad quad code has written 100% of my code i haven't written a single line by hand

[译文] [Boris]: 嗯，好吧，但如果我不得不推测的话……一年前我做过一个预测，我想 Dario（Anthropic CEO）也做了这个预测，即到今年年底人们将不再写代码了。我想那大概是去年年中的时候。你知道我每天都写代码，我每个月提交两三百个 PR（拉取请求）之类的。但在过去两个月里，Claude Code 编写了我 100% 的代码，我没有手写过一行代码。

[原文] [Boris]: and this is something like I also predicted this you know like way back middle of last year it was sort of not intuitive because if you just think about kind of the experience at the time and you trace it linearly there's just no way that the model would be at that point so you really have to kind of believe in the exponential and just literally like plot it out and kind of follow the way that the line the line goes that's the only way that you would have predicted this and it was just it was absolutely right

[译文] [Boris]: 这就像我在去年年中预测的那样，但这在当时并不直观。因为如果你只考虑当时的体验并线性推导，模型绝不可能达到那个水平。所以你真的必须相信指数级增长，真的把它画出来，顺着那条线的走势去推演，这是你唯一能预测到这一点的方式，而它是绝对正确的。

[原文] [Boris]: and so I think for coding this is a work this is something that we're going to start to see in more and more places for more and more kinds of code that the model is able to just do all of it and when we think about co-work I think it's somewhat similar i think it's a little bit earlier and I think what we're going to see is for all this kind of tedious tasks like you know like connecting app A and B or kind of shuffling data back and forth or or whatever the model is just going to be able to do it and it's going to get increasingly good at it

[译文] [Boris]: 所以我认为对于编程来说，这是一个正在发生的事情，我们将开始在越来越多的地方、针对越来越多的代码类型看到模型能够完成所有工作。当我们考虑 Co-work 时，我认为情况有些类似，只是稍微处于更早期的阶段。我认为我们将看到的是，对于所有这种乏味的任务，比如连接应用 A 和 B，或者来回搬运数据之类的，模型将能够完成它，并且会变得越来越擅长。

[原文] [Boris]: this is I think in some ways it's a little scary and in some ways I think it's really exciting because you don't have to spend your time on this toilome work anymore you can just focus on the work that you enjoy um and also everyone I think just becomes much much more productive because you have an army of plots that that can do this

[译文] [Boris]: 我认为这在某些方面有点可怕，但在某些方面我认为这真的令人兴奋，因为你不再需要把时间花在这些劳累的工作（toilsome work）上，你可以只专注于你喜欢的工作。而且我认为每个人都会变得更加高效，因为你有一支“Claude 军团（army of Claudes）”可以做这些事。

[原文] [Greg]: okay i like that feature i like that feature a lot um it's a hard question it's a hard question um when you it's sort of like the genies out of the bottle and it's hard to predict like where the genie is going to go so I believe that co uh co-work is the gateway drug to cla code

[译文] [Greg]: 好的，我喜欢那个特性，我非常喜欢那个特性。这是个很难的问题，这是个很难的问题。就像精灵已经从瓶子里放出来了，很难预测精灵会去哪里。所以我相信 Co-work 是通向 Claude Code 的“入门药”。

[原文] [Boris]: i think that people are going to uh start using it and they're going to develop like vertical use cases like for whatever it is their business is like you mentioned AutoCAD like you probably weren't thinking about AutoCAD when you were de helping develop Cobalt uh co-work so I think there's going to be like these verticals um and I think I think that co-work is going to be similar to like vertical job boards where there's very specific roles that you can hire to people and I do think that there's going to be this uh combination between skills and these like digital teammates that you're going to quote unquote hire

[译文] [Boris]: 我认为人们会开始使用它，并且他们会开发出垂直领域的用例，无论他们的业务是什么。就像你提到的 AutoCAD，当你在帮助开发 Co-work 时可能并没有想到 AutoCAD。所以我认为会出现这些垂直领域。而且我认为 Co-work 会类似于垂直招聘网站，那里有你可以雇佣的非常特定的角色。我也确实认为会在“技能”和这些你要“雇佣”（加引号）的“数字同事（digital teammates）”之间出现某种结合。

[原文] [Greg]: yeah that's that's super interesting maybe we should make a bet and just see where it pans out in a year you know

[译文] [Greg]: 是的，那超级有趣。也许我们应该打个赌，看看一年后结果如何。

[原文] [Boris]: I I have no idea um but it it's it's definitely interesting to speculate cuz I I I just feel like the way this technology goes is so different than past technology waves it's sort of similar to the internet it's sort of similar to computers you know like maybe like telephones or something before that but the speed is just so much faster

[译文] [Boris]: 我完全不知道，但这绝对值得推测。因为我感觉这项技术的发展方式与过去的技术浪潮非常不同。它有点像互联网，有点像计算机，或者可能是像之前的电话之类的，但它的速度要快得多。

[原文] [Boris]: and because it's kind of piggybacking on all this like the internet could not exist without telephones uh telephones and kind of like phone lines being everywhere you couldn't have dialup without it you know mobile phones couldn't exist without the internet existing um so it's sort of like every layer of the stack it just gets more and more powerful and it spreads more quickly and so it's like on the back of all of this that AI can exist um and yeah it's it's just gonna be very exciting to see to see where it goes

[译文] [Boris]: 而且因为它某种程度上是依附于所有这些基础之上的。就像互联网没有电话就无法存在——没有遍布各地的电话线就没有拨号上网；没有互联网的存在就没有移动电话。这就像技术栈的每一层都变得越来越强大，传播得越来越快。所以 AI 就像是建立在所有这些基础之上的，是的，看看它会走向何方将会非常令人兴奋。

章节 8：Claude Code 进阶：Boris 的高效配置 (Claude Code Deep Dive: Boris's Setup)

📝 本节摘要：

话题转向了 Boris 那篇获得近 10 万次收藏的病毒式推文，其中详细介绍了他作为创作者如何使用 Claude Code。Boris 透露他的配置出人意料地“朴素（vanilla）”。他强调的核心理念是并行处理（Parallelism）——不再深入钻研单一任务，而是通过终端或移动端同时启动多个任务。他特别推崇 Opus 4.5 模型，认为其强大的规划能力使得“一旦计划好了，代码也就好了（once the plan is good, the code is good）”，这实际上是一种“规格驱动开发（Spec-driven development）”。此外，他还解释了一个反直觉的现象：使用更聪明（但也更贵）的模型实际上更省钱，因为它能通过更少的步骤一次性把事情做对。

[原文] [Greg]: i want to shift gears just for the last 10 minutes um because we mentioned Claude Code you had a you had a post that went absolutely viral i think you know what post I'm going to talk about 99,000 bookmarks which is crazy and I'm going to share my screen i want to go over it a little bit

[译文] [Greg]: 在最后 10 分钟我想转换一下话题，因为我们提到了 Claude Code。你发过一个帖子，绝对是疯传了，我想你知道我要说的是哪个帖子，99,000 次收藏（bookmarks），这太疯狂了。我要共享一下屏幕，我想稍微过一遍这个帖子。

[原文] [Greg]: this is me learning to use Twitter i think I made an account like a decade ago and I haven't really used it so um it's funny yeah it's been fun to learn you have like a just a few tweets but like this you know this one you figured it out you say "I'm Boris i created Cloud Code lots of people have asked for how I use Cloud Code so I wanted to show off my setup a bit my setup might be surprisingly vanilla cloud Code works great out of the box so I personally don't customize it much there's not no one correct there's no one correct way to use cloud code we intentionally built it in a way that you can use it customize it and hack it however you'd like each person on the cloud code team use it very differently so here it goes

[译文] [Greg]: 这就是我正在学习使用 Twitter。我想我在十年前就注册了账号，但一直没怎么用过，所以这很有趣，学习这个过程很有意思。你只有几条推文，但这这一条你确实搞懂了。你写道：“我是 Boris，我创建了 Claude Code（原文作 Cloud Code）。很多人问我怎么使用 Claude Code，所以我想稍微展示一下我的配置。我的配置可能出人意料地‘朴素（vanilla）’。Claude Code 开箱即用，效果很好，所以我个人并不怎么定制它。使用 Claude Code 没有所谓唯一正确的方法，我们特意以一种你可以随心所欲地使用、定制和破解它的方式来构建它。Claude Code 团队的每个人使用它的方式都非常不同。所以，以下是我的分享：”

[原文] [Greg]: could you just talk about some of the just expand on some of these and what you were saying you know what you were saying on here because I thought it was really interesting

[译文] [Greg]: 你能谈谈其中的一些点吗？稍微展开讲讲这些，以及你在上面所说的内容，因为我觉得这真的很有趣。

[原文] [Boris]: yeah I'd love to so this first one it's very similar to what I was showing in co-work now isn't to go super deep on one task it's to do a bunch of tasks in parallel and so you know in the when I'm working on quad code I I usually work in a terminal um or on the mobile app these are kind of the two services I use the most

[译文] [Boris]: 是的，我很乐意。第一点和我刚才在 Co-work 中展示的非常相似，那就是不要在一个任务上钻得太深，而是并行处理一堆任务。当我在开发 Claude Code（原文作 quad code）时，我通常在终端（terminal）里工作，或者在移动 App 上工作，这是我使用最多的两个界面。

[原文] [Boris]: um but like I said everyone on the team is different every user prefers something different so we build all of these and so usually what I do is I'll start a task in kind of one tab and once Quad is thinking about it and starting to work on a plan I'll move on to the second tab and I'll ask it to make a plan for the second thing then I'll move on to the third one ask it to make a plan

[译文] [Boris]: 但就像我说的，团队里的每个人都不同，每个用户偏好的东西也不同，所以我们构建了所有这些。通常我做的是，我会在一个标签页（tab）里启动一个任务，一旦 Claude（原文作 Quad）开始思考并着手制定计划，我就会转到第二个标签页，让它为第二件事制定计划，然后我会转到第三个，让它制定计划。

[原文] [Boris]: and then finally like when uh you know I've run out of immediate tasks to do I'll go back to the first tab i'll see if the plan looks good I might go back and forth a little bit and then once the plan looks good I usually go into just auto accept edits right away because I think with Opus 4.5 once the plan is good the model can just execute it pretty much perfectly

[译文] [Boris]: 最后，当我手头没有紧迫的任务要做时，我会回到第一个标签页，看看计划是否看起来不错。我可能会稍微来回调整一下，一旦计划看起来不错，我通常会直接进入“自动接受编辑（auto accept edits）”模式。因为我认为有了 Opus 4.5，一旦计划好了，模型基本上就能完美地执行它。

[原文] [Boris]: this is definitely not the case with previous models and so I think there was a lot of excitement about Opusport 4.5 in um you know over the last couple months and I I think this is kind of one of the big reasons it's just gotten very good at coding but also excellent at planning so once the plan is good the code is good and so yeah my my work now is just jumping between tabs kind of tending to the clouds make sure they're unblocked answering their questions with co-work I think I think it's actually quite similar now

[译文] [Boris]: 以前的模型绝对不是这种情况。所以我认为过去几个月大家对 Opus 4.5（原文作 Opusport 4.5）非常兴奋，我认为这是一个主要原因——它不仅非常擅长编码，而且极其擅长规划。所以“一旦计划好了，代码也就好了”。所以我现在的工作就是在标签页之间跳转，照看这些 Claude（原文作 clouds），确保它们没有被阻塞，回答它们的问题。对于 Co-work，我认为现在情况实际上非常相似。

[原文] [Greg]: i like that i'm going to I'm going to quote you on that once the plan is good the code is good because that's so true right because if you nail the plan the code should you know the agent should do the work

[译文] [Greg]: 我喜欢这个说法，我要引用你这句话：“一旦计划好了，代码也就好了”。因为这太真实了，对吧？如果你搞定了计划，代码就应该……你知道，代理（Agent）就应该完成工作。

[原文] [Boris]: yeah yeah exactly i think like sometime last year there was all this buzz about specri development and you know it just feels like it's feels a little like too QT and like a little too rigid to me but I think this is sort of a form of of spec driven development it's like there there's some kind of spec you know i think it's just like a plan that's all it has to be it's just a text file it doesn't have to be in a particular format once you have that you're good

[译文] [Boris]: 是的，没错。我想去年某个时候有很多关于“规格驱动开发（Spec-driven development）”的讨论。对我来说，那感觉有点太“QT”（可能指可爱或某种特定的过时风格），也有点太僵化了。但我认为这（目前的做法）算是某种形式的规格驱动开发。就像是有某种规格，你知道，我认为它就像一个计划，这就是它所需要的一切。它只是一个文本文件，不需要特定的格式，一旦你有了那个，你就搞定了。

[原文] [Greg]: number two you say I also run five to 10 clouds uh in in parallel with my local clouds as I code in my terminal I will often hand off local sessions to web using and or manually kick off sessions in Chrome and sometimes I will teleport back and forth i also start a few sessions from my phone obviously from cloud iOS app you got to every morning and throughout the day and check in on them later what do you mean by that

[译文] [Greg]: 第二点你说：“我也并行运行 5 到 10 个 Claude（原文作 clouds），与我的本地 Claude 并行。当我在终端中编码时，我经常将本地会话移交给 Web 端使用，或者手动在 Chrome 中启动会话，有时我会来回传送。我也会通过手机启动一些会话（显然是通过 Claude iOS App），每天早上以及全天都会这样做，稍后再去检查它们。”这是什么意思？

[原文] [Boris]: this morning I kicked off I think like three quads as soon as I woke up i just had like some thought in the morning about well maybe I should like build this thing or fix this bug or whatever i was like checking Twitter and someone had a bug report so I just opened my phone and you know in the Quad app you on on the left side you click the little menu and there's a code tab um so you can just like access quad code there that's what I use for a lot of my code

[译文] [Boris]: 今天早上我一醒来就启动了大概三个 Claude（原文作 quads）。早上我有一些想法，比如我也许应该构建这个东西，或者修复那个 Bug 之类的。我在刷 Twitter，有人提交了一个 Bug 报告，所以我直接打开手机。你知道在 Claude App 里，你在左侧点击那个小菜单，有一个 Code 标签页，你可以直接在那里访问 Claude Code，我很多代码就是这么用的。

[原文] [Boris]: and it's funny I I never would have guessed that this is the way that I code if you ask me a year ago I would never have predicted that the way I code now was like probably half of it is just on my phone and it sort of just works

[译文] [Boris]: 这很有趣，如果你一年前问我，我绝对猜不到这就是我现在的编码方式。我绝不会预测到我现在大概有一半的代码只是在手机上完成的，而且它确实有效。

[原文] [Boris]: um and then web is kind of the other part so once I've run out of tabs cuz it's just like you know it's kind of a pain to manage a bunch of different good checkouts cuz in each tab in my terminal I actually have a totally separate git checkout and I don't really use work trees or anything like that i just keep it pretty simple um and in web if I if I just ran out of terminal tabs I'll start like overflowing to web and and starting tasks there

[译文] [Boris]: 然后 Web 端是另一部分。一旦我的标签页用完了——因为管理一堆不同的 git checkout 有点麻烦，我在终端的每个标签页里实际上都有一个完全独立的 git checkout，我并不怎么使用 work trees 或类似的东西，我只是保持它非常简单——如果在 Web 端，如果我的终端标签页用完了，我就会开始溢出到 Web 端并在那里启动任务。

[原文] [Greg]: beautiful so yeah I also I so recommending use iOS use web open multiple like that's what that's you'll get the most out of it that way

[译文] [Greg]: 漂亮。所以是的，我也推荐使用 iOS，使用 Web，多开任务，这样你才能从中获得最大收益。

[原文] [Greg]: number three you say "I use Opus 4.5 with Thinking for Everything it's the best coding model I've ever used and even though it's bigger and slower than Sonnet since you have to steer it less and it's better at tool use it's almost always faster than using a smaller model in the end and cheaper it's sort of counterintuitive." And I had to explain this to people a few times but because the model is smarter it actually uses less tokens in the end and uh it uses so many less tokens it's often cheaper than using a smaller less intelligent model even though the per token cost for that model is lower so a little counterintuitive but yeah just use the smartest thing if you can

[译文] [Greg]: 第三点你说：“我对所有事情都使用带有 Thinking（思考）功能的 Opus 4.5。这是我用过的最好的编码模型，尽管它比 Sonnet 更大、更慢，但因为你需要更少的引导，而且它更擅长工具使用，所以最终它几乎总是比使用较小的模型更快，而且更便宜。这有点反直觉。”我不得不向人们解释了几次这一点，但因为模型更聪明，它最终实际上使用了更少的 Token（代币），而且因为它使用的 Token 少得多，所以往往比使用较小、较不智能的模型更便宜，即使该模型的单 Token 成本更低。所以这有点反直觉，但是的，如果可以的话，就用最聪明的东西。

章节 9：工程化实践：知识库与复利工程 (Engineering Practices: Knowledge Base & Compounding Engineering)

📝 本节摘要：

本节深入探讨了工程团队如何通过 CLAUDE.md 文件构建共享知识库。Boris 强调，这只是一个简单的文本文件，但整个团队通过将 Claude 的错误记录其中，防止了错误复发。随后，他介绍了如何通过 GitHub Actions 将 Claude 集成到代码审查（Code Review）流程中。Boris 引用了“复利工程（Compounding Engineering）”的概念，并分享了他在 Meta 工作的经历——从过去手动记录错误编写 Lint 规则，进化到现在只需在 PR 中简单的 @Claude，就能让 AI 自动更新知识库或修复代码，从而实现效率的指数级积累。

[原文] [Greg]: number four our team shares a single CloudMD for the claude code repo we check it into Git the whole team contributes multiple times a week anytime we see Claude do something incorrectly we add it to the MD so Claude knows not to do it next time other teams maintain their own Claude MDs it is each team's job to keep theirs up to date and the CloudMD is just a text file so there's no special format people ask this all the time is there some special format that it has to be in it no it's just like it's just a text file so you can put whatever you want in it this is a screenshot of our QuadMD this is literally it so just really simple and you know you you could format this kind of however you want

[译文] [Greg]: 第四点：“我们的团队为 Claude Code 仓库共享一个单一的 CLAUDE.md 文件。我们将它检入（check into）Git，整个团队每周都会多次贡献内容。每当我们看到 Claude 做错了什么，我们就会把它添加到这个 Markdown 文件中，这样 Claude 下次就知道不要再犯了。其他团队维护他们自己的 CLAUDE.md，保持更新是每个团队的职责。”而且 CLAUDE.md 只是一个文本文件，所以没有特殊格式。人们总是问这个问题：“它必须是某种特殊格式吗？”不，它就像是一个普通的文本文件，所以你可以在里面写任何你想要的东西。这是我们 CLAUDE.md（原文作 QuadMD）的截图，真的就是这样，非常简单，你可以随心所欲地格式化它。

[原文] [Boris]: love it and then finally I think yeah number five oh no you have a you got a few more so uh number five during code review I'll often tag at.cloud on my co-workers PRs to add something to the cloud MD as part of the PR we use the cloud code GitHub action uh for this it's our version of Dan Chipper's compounding engineering what What do you mean what is compound engineering

[译文] [Boris]: 我很喜欢。然后最后我想……噢不对，你还有几点。所以第五点：“在代码审查期间，我经常会在同事的 PR（拉取请求）上标记 @Claude（原文作 at.cloud），作为 PR 的一部分向 CLAUDE.md 添加内容。为此我们使用了 Claude Code GitHub Action，这是我们版本的 Dan Shipper（原文作 Chipper）的‘复利工程（compounding engineering）’。”

[Greg]: 这是什么意思？什么是“复利工程”？

[原文] [Boris]: yeah oh my god so there's actually like two bugs in this tweet i think I think Dan actually calls it compound engineering not compounding engineering and then the atqu this is me learning how to use X um but it's actually at Claw there's there's no dot i just didn't I think there's like an actual user or something whose name is Quad i didn't want to attack them

[译文] [Boris]: 是的，天哪，这条推文中实际上有两个错误。我想 Dan 实际上称之为“复合工程（compound engineering）”而不是“复利工程（compounding engineering）”。然后那个 atqu（指推文中的提及符号），这是我在学习如何使用 X（Twitter）。实际上应该是 @Claude，中间没有点。我只是不想……我想可能真有个用户的名字叫 Quad，我不想打扰（attack/tag）他们。

[原文] [Boris]: um but yeah so so what you do is in quad code you run this /command/install GitHub action and what this does is it installs the Claude app in your GitHub repo and what that lets you do is you can then appment mention Claude whenever you want and just have it make changes and uh it can just work on PR so it'll push back to your branch and it'll push the changes right back you can also tag it on issues you can tag it kind of wherever i do this multiple times a day it's it's really really useful

[译文] [Boris]: 嗯，但是的。所以你要做的就是在 Claude Code（原文作 quad code）中运行 /command/install GitHub action，这会在你的 GitHub 仓库中安装 Claude 应用。这让你能够随时 @提及 Claude，让它进行更改。它可以直接在 PR 上工作，所以它会推送到你的分支，并直接推送更改。你也可以在 Issues（问题）上标记它，你可以在任何地方标记它。我每天都会这样做很多次，这真的非常非常有用。

[原文] [Boris]: i think one of the most common use cases is just like little fixes i think the other one is updating the quadmd um to keep the knowledge base up to date and you know you should never have to comment about something twice

[译文] [Boris]: 我认为最常见的用例之一就是像那样的小修复，另一个就是更新 CLAUDE.md（原文作 quadmd），以保持知识库的更新。你知道，你不应该被迫对同一件事评论两次。

[原文] [Boris]: um back when I was at Meta something that I did is um this is like in a in a previous life in a previous job something that I did is every code review that I did I would keep a spreadsheet of all the issues that came up and whenever the same kind of issue came up again I would just like to up the spreadsheet and whenever something hit I think like five or 10 or something I would write a lint rule and what that is is it's a way to automate that part of the code review so I don't have to comment about it again

[译文] [Boris]: 当我在 Meta 工作时，就像在上一辈子、上一份工作中，我做过一件事：对于我做的每一次代码审查，我会保留一个电子表格，记录所有出现的问题。每当同类问题再次出现时，我就更新电子表格。每当某个问题达到大概 5 次或 10 次时，我就会编写一条 Lint 规则（代码静态分析规则）。那是一种自动化代码审查的方法，这样我就不必再次评论它了。

[原文] [Boris]: and that was back in the days before OM and before the model was any good at coding and so this is the equivalent nowadays you just tag cloud and you have it update your cloudmd which is your team's knowledge base so really simple and what this means is you don't have to point anything out twice

[译文] [Boris]: 那是在大语言模型（LLM/OM）出现之前，也是在模型擅长编码之前的日子。而现在这（指 @Claude）就是等效的做法。你只需标记 Claude，让它更新你的 CLAUDE.md——也就是你团队的知识库。所以非常简单，这意味着你不必两次指出同一件事。

章节 10：核心建议与访谈结语 (Key Advice & Conclusion)

📝 本节摘要：

在访谈的最后，Boris 分享了使用 Claude Code 的第13条核心建议——“给 Claude 一种验证其输出的方式”。他用“蒙眼画家”做比喻，指出如果工程师无法运行代码或在浏览器中查看结果，就像画家看不见自己的画作一样，质量难以保证。Boris 总结道，使用这些工具没有唯一的正确方式，它就像一本“选择你自己的道路”的书或 RPG 游戏，鼓励用户亲自上手探索。节目最后以一个轻松的话题结束：来自法裔加拿大的 Greg 询问是否应该读作法语发音的 "Clo"（克罗），Boris 幽默地表示要在办公室试着用这个发音看看大家的反应。

[原文] [Greg]: do we've got you know we're not going to have time to do all of them what are the I don't think cuz you have a hard stop do you want to pick one or two to end with

[译文] [Greg]: 我们没有时间把所有点都讲完。既然你有硬性的结束时间（hard stop），你想挑一两个来作为结束吗？

[原文] [Boris]: yeah let's do um let's do maybe number 13 um yeah number 13 i think this is probably in in addition to using opus for when people ask about how to get better performance out of quad code there's three things that I recommend almost every time

[译文] [Boris]: 好的，让我们讲讲第 13 条。是的，第 13 条。除了使用 Opus 之外，当人们问我如何从 Claude Code 获得更好的性能时，我有三件事几乎每次都会推荐。

[原文] [Boris]: number one is use opus 4.5 with thinking always don't try to use a different model because opus will just give you better results and more efficiency overall the second thing is make sure you have a good quad and then the third thing is this this tip number 13 which is give cloud a way to verify its output

[译文] [Boris]: 第一，始终使用带有 Thinking（思考）功能的 Opus 4.5，不要尝试使用其他模型，因为 Opus 会给你更好的结果和整体更高的效率。第二，确保你有一个好的 Claude 配置。第三，就是这个第 13 条建议：给 Claude 一种验证其输出的方式。

[原文] [Boris]: and so we we just kind of saw with co-work how good cla is at using the Chrome extension in order to write email and in order to work with uh sheets and it's exactly the same thing if I'm building an app I always use the Chrome extension to have Quad test its own work and if Quad can verify its own output the result is going to be way way better

[译文] [Boris]: 我们刚才在 Co-work 中看到 Claude 在使用 Chrome 扩展写邮件和处理表格方面有多出色。这完全是一回事，如果我在构建一个 App，我总是使用 Chrome 扩展让 Claude 测试它自己的工作。如果 Claude 能够验证它自己的输出，结果将会好得多。

[原文] [Boris]: and it it's sort of like um you know imagine that you're a painter and you're you know you you make paintings and they have to be like pretty good they have to be maybe even like photorealistic or something um or just like you know some kind of like very detailed uh style and uh you you're you have to wear a blindfold you're just not going to be that good it's not going to come out that great

[译文] [Boris]: 这就像是，想象你是一个画家，你在作画，画作必须非常好，甚至可能要是照片级写实的，或者是某种非常细节的风格。但如果你必须戴着眼罩（blindfold），你就不会画得那么好，结果也不会那么棒。

[原文] [Boris]: whereas the same thing for an engineer like if you have to write code but uh you can never run the code or you can never see the output and you can never see the website it's just not going to be good and so it's the same thing with quad um as the model gets more intelligent that first shot is going to get better and better but really you want to give it a way to verify the output and it'll be much better so this is like running tests if you're an engineer uh starting a server also if you're an engineer or you know seeing seeing the output in a simulator or in a browser

[译文] [Boris]: 这对工程师来说也是一样的。如果你必须写代码，但你永远不能运行代码，或者你看不到输出，看不到网站，那结果就不会好。对于 Claude 也是如此。随着模型变得越来越智能，它的“第一次尝试（first shot）”会变得越来越好，但你真的需要给它一种验证输出的方法，这样效果会好得多。所以这就像是运行测试（如果你是工程师），或者启动服务器，或者在模拟器或浏览器中查看输出。

[原文] [Greg]: amazing and the ultimate tip I guess is just get your hands dirty right i think that's it

[译文] [Greg]: 太棒了。我想终极建议就是“亲自上手（get your hands dirty）”，对吧？我想就是这个。

[原文] [Boris]: yeah i mean there's no right there's no one right way to use this stuff like you know see see what's useful see what's not find your own workflows it's sort of I I heard someone describing quad code as like a find your own path book you know like one of those books where you have to like do you do you go to the dungeon or do you explore the forest like this kind of thing or or like a like an old like RPG video game it's just kind of like that it's like it's very free form there's no one right way to do it so just see what works for you

[译文] [Boris]: 是的，我的意思是使用这些东西没有所谓唯一的正确方式。去看看什么有用，什么没用，找到你自己的工作流。我听有人把 Claude Code 形容为一本“选择你自己的道路（Choose Your Own Adventure）”的书，你知道就是那种你必须选择“是去地牢”还是“去探索森林”的书；或者像是一个老式的 RPG（角色扮演）电子游戏。它就像那样，非常自由，没有一种绝对正确的做法，所以看看什么对你有效。

[原文] [Greg]: boris I appreciate you taking the time the generosity to spill the sauce and just to share with us how we can get the most out of both uh co-work and claude code everyone's thinking about it and everyone's trying to especially on this podcast you know the startup ideas podcast you have millions of people who are trying to figure out how I can be more productive and how I can build businesses around some of these things so thank you thank you for the time

[译文] [Greg]: Boris，我很感激你抽出时间，如此慷慨地分享秘籍（spill the sauce），告诉我们如何充分利用 Co-work 和 Claude Code。大家都在思考这个问题，每个人都在尝试，特别是在这个播客——《Startup Ideas》播客上，有数百万人试图弄清楚如何提高生产力，以及如何围绕这些东西建立业务。所以谢谢你，谢谢你的时间。

[原文] [Greg]: um I'll include links on where to follow Boris he doesn't tweet a lot but when he tweets it's it's worth paying attention to and I just have I want to leave with one thing just because my audience would kill me if I didn't ask this so as you know Boris I'm from French Canada and we speak French obviously in French Canada and I call Claude Clo am I the only one

[译文] [Greg]: 我会附上关注 Boris 的链接。他不常发推特，但只要发了就值得关注。我想以一件事作为结束，因为如果我不问这个问题，我的听众会杀了我的。你知道 Boris，我来自法裔加拿大，我们在那里显然说法语，我把 Claude 叫作 "Clo"（/kloʊ/，类似法语发音）。我是唯一一个这么叫的人吗？

[原文] [Boris]: oh man you're probably not the only one a lot of the a lot of the world speaks French which one sounds better what what feels right i mean to me Clo sounds better it's like Jean Clo Vanam even though people would say John Claude Vanam it's like that's my take that's my hot take to me it sounds better

[译文] [Boris]: 噢老兄，你可能不是唯一的，世界上有很多人说法语。哪个听起来更好？哪个感觉是对的？我的意思是，对我来说 "Clo" 听起来更好。就像 Jean-Claude Van Damme（尚格·云顿），虽然人们会说 John Claude Van Damme，但那是我的看法，那是我的“暴论（hot take）”，对我来说它听起来更好听。

[原文] [Boris]: oh you know Greg I I'm going to Today around the office I'm just going to call it Clo and we'll we'll see what people say i'll I'll report back

[译文] [Boris]: 噢你知道吗 Greg，今天在办公室里我就打算把它叫作 "Clo"，我们看看大家会说什么，我会回来报告结果的。

[原文] [Greg]: okay report back all right sounds good boris thanks again for coming on and I'll see you next time

[译文] [Greg]: 好的，回来报告。听起来不错。Boris，再次感谢你的到来，我们下次见。