📝 本节摘要：
本节中，Peter Steinberger 分享了他从依赖 IDE（集成开发环境）转向以终端（Terminal）为核心的工作流演变过程。他指出，随着对 AI 工具的熟练掌握，程序员不再需要逐行阅读“无聊的代码”，因为大部分软件本质只是数据的搬运。对话重点讨论了“Agentic Programming（代理编程）”的复杂度曲线：从初学者的简单提示词，到中级阶段过度复杂的“代理陷阱”（Agentic Trap，即试图通过复杂的编排自动化一切），最后回归到“Zen（禅）”状态的极简提示词。此外，Peter 幽默地将严谨的“Agentic Engineering（代理工程）”与随意的“Vibe Coding（氛围编程）”区分开来，后者往往带来次日的“悔恨”。
[原文] [Lex Fridman]: you've been uh documenting the evolution of your uh dev workflow over the past few months there's a really good blog post on August 25th and October 14th and the recent one December 28th i recommend everybody go read them they have a lot of different information in them but sprinkled throughout is the evolution of your dev workflow so I was wondering if you could speak to that
[译文] [Lex Fridman]: 你在过去几个月里一直在记录你开发工作流的演变，在8月25日、10月14日以及最近的12月28日都有很棒的博客文章。我推荐大家都去读一读，里面包含了很多不同的信息，但贯穿其中的是你开发工作流的进化，所以我想知道你能不能谈谈这一点。
[原文] [Peter Steinberger]: i started my my first touch point was cloud code like in April it was not great but it was good and this whole paradigm shift that suddenly work in the terminal was very refreshing and different um but I still needed the IDE quite a bit because it's just not good enough and then I experimented a lot with cursor um that was good i didn't really like the fact that it was so hard to have multiple versions of it so eventually I I I went back to cloud code as my my main driver and that got better and yeah at some point I had like seven subscriptions like was burning through one per day because I was I got I really comfortable at running multiple windows side by side all CLI all terminal,
[译文] [Peter Steinberger]: 我刚开始……我的第一个接触点是大概四月份时候的 Cloud Code（云代码），那时候它还不算太好，但也还行。这种突然在终端（Terminal）里工作的范式转变非常令人耳目一新且与众不同，但我当时还是很需要 IDE（集成开发环境），因为工具还不够好。之后我试了很多次 Cursor，它很不错，但我不太喜欢它很难保留多个版本这一点，所以最终我又回到了以 Cloud Code 为主力驱动，它后来也变好了。是的，在某个时间点我有大概七个订阅，每天就能用完一个，因为我已经非常习惯并行运行多个窗口，全都是 CLI（命令行界面），全都是终端操作。
[原文] [Lex Fridman]: so like what how much were you using ID at this point
[译文] [Lex Fridman]: 那么在这个阶段，你使用 IDE 的频率是多少？
[原文] [Peter Steinberger]: um very very rarely mostly a diff viewer to actually like I got more and more comfortable that I don't have to read all the code i know I have one blog post where I say I don't read the code but if you read it more closely I mean I don't read the boring parts of code because if you if you look at it most software is really just like data comes in it's moved from one shape to another shape maybe you store it in a database maybe I get it out again I'll show it to the user the browser does some processing or native app some data goes in goes up again and does the same dance in reverse we're just we're just shifting data from one form to another and that's not very exciting or the whole how is my button aligned in Tailwind i don't need to read that code other parts that maybe something that touches the database um yeah I have to do I have to read and review that code
[译文] [Peter Steinberger]: 嗯，非常非常少，主要是作为一个差异查看器（Diff Viewer）。实际上我越来越适应不再必须阅读所有代码。我知道我有一篇博文说“我不读代码”，但如果你仔细读那篇文章，我的意思是“我不读代码中无聊的部分”。因为如果你仔细看，大多数软件真的只是：数据进来，从一种形状移动变成另一种形状，也许存进数据库，也许我又把它取出来展示给用户；浏览器做些处理，或者原生应用里数据进来又上去，反向做同样的动作。我们只是在把数据从一种形式转换成另一种形式，这并不怎么令人兴奋。或者是像“我的按钮在 Tailwind 里是怎么对齐的”这种，我不需要读那部分代码。至于其他部分，比如涉及数据库操作的，嗯，是的，我必须做，我必须阅读并审查那部分代码。
[原文] [Lex Fridman]: can you actually there's in one of your blog post uh the just talk to it the no BS way of agentic engineering you have this graphic the curve of agentic programming on the x- axis is time on the y-axis is complexity uh there's the please fix this where you prompt a short prompt on the left and in the middle there's super complicated eight agents complex orchestration with uh multi-checkouts chaining agents together custom subation workflows library of 18 different slash commands large full stack features you're super organized you're super complicated sophisticated software engineer you got everything organized and then the elite level is uh over time you arrive at the zen place of once again short prompts hey look at these files and then do these changes i actually call it the agentic trap you I saw this in a in a lot of people that have their first touch point and maybe start vibe coding i actually think vibe coding is a slur you prefer agentic engineering
[译文] [Lex Fridman]: 你能具体谈谈吗？在你的一篇博文中，关于“直接跟它对话：Agentic Engineering（代理工程）的无废话指南”，你放了一张图表，展示了“Agentic Programming（代理编程）”的曲线。X轴是时间，Y轴是复杂度。最左边是“请修复这个”，你输入一个简短的提示词；中间是非常复杂的八个智能体（Agents），复杂的编排，包含多重检出（Multi-checkouts）、智能体链式协作、自定义子任务工作流、18种不同的斜杠命令库、大型全栈功能——你非常有条理，你是个极其复杂且老练的软件工程师，你把一切都组织好了；然后精英级别是，随着时间推移，你到达了一个“禅（Zen）”的境界，再次回归到简短的提示词：“嘿，看看这些文件，然后做这些修改”。其实我把中间那个叫“Agentic Trap（代理陷阱）”。我在很多人身上看到了这一点，他们刚开始接触，可能开始搞“Vibe Coding（氛围编程）”。我其实觉得“Vibe Coding”是个贬义词，你更倾向于“Agentic Engineering（代理工程）”？
[原文] [Peter Steinberger]: yeah i always tell people I I do agentic engineering and then maybe after 3:00 a.m i switch to vibe coding and then I have regrets on the next day,
[译文] [Peter Steinberger]: 是的，我总是告诉人们，我做的是“Agentic Engineering（代理工程）”，然后也许凌晨3点以后，我会切换到“Vibe Coding（氛围编程）”，然后第二天我就后悔了。
[原文] [Lex Fridman]: yeah well a walk of shame you just have to clean up and like fix your shit we've all been there
[译文] [Lex Fridman]: 是啊，那简直是“羞耻之行（Walk of Shame）”，你不得不去清理并修好你搞的一团糟，我们都经历过。
📝 本节摘要：
在本节中，Peter 将使用 AI 编程比作演奏乐器：它需要像练习吉他或钢琴一样去磨练技巧，而不是随便敲击就能产生美妙的音乐。他幽默地指出，“氛围编程”（Vibe Coding）虽然能带来深夜的快感，但往往伴随着第二天的“羞耻之行”和重构的悔恨。对话深入探讨了对 AI 的“共情”——即理解 AI 在每次会话中都是“全新开始”的，它们不了解项目的全貌，且受限于上下文窗口（Context Window）。Peter 还描述了当 AI 感到困惑时会像《星际迷航》中的博格人（Borg）一样“崩溃”，此时人类工程师需要通过感知“阻力”来及时暂停并引导方向，而不是盲目强迫 AI 继续。
[原文] [Peter Steinberger]: yeah i always tell people I I do agentic engineering and then maybe after 3:00 a.m i switch to vibe coding and then I have regrets on the next day
[译文] [Peter Steinberger]: 是的，我总是告诉人们，我做的是“Agentic Engineering（代理工程）”，然后也许凌晨3点以后，我会切换到“Vibe Coding（氛围编程）”，然后第二天我就后悔了。
[原文] [Lex Fridman]: yeah well a walk of shame you just have to clean up and like fix your shit we've all been there
[译文] [Lex Fridman]: 是啊，那简直是“羞耻之行（Walk of Shame）”，你不得不去清理并修好你搞的一团糟，我们都经历过。
[原文] [Peter Steinberger]: so people start trying out those tools the builder type get really excited and then you have to play with it right it's the same way as you have to play with a guitar before you can make good music it's it's not oh I I touch it once and it just flows off it It's a It's a a skill that you have to learn like any other skill and I see a lot of people that are not as positive mindset towards the tech they try it once it's like you sit me on a piano I played once and it doesn't sound good and I say the piano's shit that's that's sometimes the impression I get because it does not it needs a different level of thinking you have to learn the language of the agent a little bit understand where they're good and where they need help
[译文] [Peter Steinberger]: 所以人们开始尝试这些工具，构建者类型的人会非常兴奋，然后你必须去把玩它，对吧？这就像你必须先弹吉他才能创作出好音乐一样。这并不是说“噢，我碰它一下，它就自然流淌出来了”。这是一项你必须像学习其他技能一样去学习的技能。我看到很多人对这项技术没有那么积极的心态，他们试了一次——这就像让我坐在钢琴前，我弹了一次，声音不好听，然后我说这钢琴是个烂货。这有时就是我得到的印象，因为它确实不一样，它需要不同层面的思考。你必须稍微学习一下 Agent（智能体）的语言，了解它们擅长什么，以及在哪里需要帮助。
[原文] [Peter Steinberger]: you have to almost consider consider how Codex or Claude sees your codebase like they start a new session and they know nothing about your product project and your project might have hundred thousands of lines of code so you got to help those agents a little bit and keep in mind the limitations that context size is an issue to like guide them a little bit as to where they should look and that often does not require a whole lot of work but it's helpful to think a little bit about their perspective as as weird as it sounds i mean it's not it's not alive or anything right but they always start fresh
[译文] [Peter Steinberger]: 你几乎必须考虑 Codex 或 Claude 是如何看待你的代码库的。比如，它们开始一个新的会话，对你的产品或项目一无所知，而你的项目可能有几十万行代码。所以你得稍微帮帮这些 Agent，并且记住限制，比如上下文大小（Context Size）是个问题，要稍微引导它们应该看哪里。这通常不需要很多工作，但稍微从它们的视角思考一下是很有帮助的。虽然这听起来很奇怪——我是说，它不是活的或者其他什么东西，对吧——但它们总是从零开始（Start fresh）。
[原文] [Peter Steinberger]: i have I have the the system understanding so with a few pointers I can immediately say "Hey I want to like make a change there you need to consider this this and this." And then they will find a look at it and then they'll their view of the project is always is not never full because the full thing does not fit in so you you have to guide them a little bit where to look and also how they should approach the problem there's like little things that sometimes help like take your time that sounds stupid but and in 5.3 Cor 5.3 that was partially addressed but those also oppos sometimes they are trained um with being aware of the context window and the closer it gets the more they freak out literally like some sometimes you see the the real raw syncing stream what you see for example in Codex is post-processed mhm sometimes the actual raw syncing stream leaks in and it sounds something like from the Borg like run to shell must comply but time and then they they they're like like that comes up a lot especially so so and that's that's a nonobvious thing that you just would never think of unless you actually just spend time working with those things and getting a feeling what works what doesn't work
[译文] [Peter Steinberger]: 我拥有对系统的理解，所以只需几个指示，我就可以立即说：“嘿，我想在那里做一个修改，你需要考虑这个、这个和这个。”然后它们会去找来看。它们对项目的视野永远不是……永远不可能是完整的，因为整个项目塞不进去，所以你必须稍微引导它们去看哪里，以及应该如何处理问题。有些小事情有时会有帮助，比如“慢慢来（Take your time）”。这听起来很蠢，虽然在 [OpenAI] 5.3 或 Core 5.3 版本中这部分得到了一些解决，但有时它们受到的训练是能感知到上下文窗口的，越接近极限，它们就越容易“崩溃（Freak out）”。真的，有时你会看到原始的思维流——你在 Codex 里看到的通常是后处理过的——嗯，有时实际的原始思维流会泄露出来，听起来就像博格人（Borg）在说话，比如“运行 Shell，必须执行，但是时间……”，然后它们就……这种情景经常出现。这是一件非显而易见的事情，除非你真的花时间与这些东西一起工作，找到什么有效、什么无效的感觉，否则你绝对想不到。
[原文] [Peter Steinberger]: you know like just just as I write code and I get into the flow and when my architecture is not right I feel friction well I get the same if I prompt and something takes too long maybe okay where's the mistake did I do I have a mistake in my thinking is there like a misunderstanding in the architecture like if if something takes longer than it should I you can just always like stop and like just press escape where where are the problems maybe you did not sufficiently empathize with the perspective of the agent in that in that sense you didn't provide enough information and because of that it's thinking way too long yeah it just tries to force a feature in that your current architecture makes really hard
[译文] [Peter Steinberger]: 你知道，就像我写代码进入心流状态时，如果我的架构不对，我会感到阻力（Friction）。如果我给提示词，而它花的时间太长了，我会有同样的感觉。也许……好吧，错误在哪里？是我思考有误吗？还是架构上有什么误解？如果某件事花费的时间比它应有的要长，你可以随时停下来，直接按 Esc 键。问题出在哪里？也许你没有充分地在这个层面上与 Agent 的视角“共情（Empathize）”，你没有提供足够的信息，因此它思考得太久了。是的，它只是试图强行加入一个在你当前架构下很难实现的功能。
📝 本节摘要：
在本节中，Peter 提出了一个核心观点：与 AI 协作应当像审查初级工程师的代码（PR Review）一样。他强调首先要确认 AI 是否理解了任务的“意图”（Intent），而非纠结于具体的实现细节。由于重构（Refactor）在 AI 时代变得非常廉价，他鼓励大胆进行架构调整。更重要的是，Peter 指出这需要一种“放手”的管理心态：就像带领人类团队一样，不必强迫 AI 完全按照你的方式写代码，只要方案可行且推动项目前进即可。他甚至提出了一种反直觉的策略：为了让 AI 更好地工作，代码库的命名和结构应当顺应 AI 的“直觉”和训练权重，而不是单纯为了满足人类的审美。
[原文] [Peter Steinberger]: um like you need to approach this more like a conversation for example when I my favorite thing when I review a pull request and I'm getting a lot of pull requests I first is review this PR it got me the review my first question is do you understand the intent of their PR i don't even care about the implementation i what like in almost all PRs are person has a problem person tries to solve the problem person sends PR i mean there's like clean up stuff and other stuff but like 99% is like this way right they either want to fix a fix a bug add a feature usually one of those two
[译文] [Peter Steinberger]: 嗯，你需要更像对待对话一样去处理这个问题。举个例子，我最喜欢做的事情就是审查合并请求（Pull Request，简称PR），我会收到很多 PR。首先是审查这个 PR，当轮到我审查时，我的第一个问题是：你是否理解了这个 PR 的意图？我甚至不在乎实现细节。几乎所有的 PR 都是一个人有问题，这个人试图解决问题，然后提交了 PR。我是说，当然也有清理代码之类的东西，但 99% 的情况都是这样，对吧？他们要么想修复一个 bug，要么想添加一个功能，通常就是这两者之一。
[原文] [Peter Steinberger]: and then codics will be like yeah it's quite clear person tried this and this is this the most optimal way to do it no in most cases it's it's like a not really and then and then I start like okay what would be a better way have you have you looked into this part this part this part and then most likely Codex didn't yet because his context size is empty right so you point them into parts where you have the system understanding that it didn't see yet and it's like oh yeah like we should we also need to consider this and this
[译文] [Peter Steinberger]: 然后 Codex 可能会说：“是的，很清楚，这个人尝试了这样做。”但这是否是最优的做法？不，在大多数情况下，并不是真的最优。然后我就开始引导：“好吧，什么会是更好的方法？你有没有看过这一部分、这一部分和这一部分？”很有可能 Codex 还没看过，因为它的上下文（Context Size）是空的，对吧？所以你把它指向那些你拥有系统理解但它还没看到的部分，然后它就会反应过来：“噢，是的，我们也需要考虑这个和这个。”
[原文] [Peter Steinberger]: and then like we have a discussion of how would the optimal way to to solve this look like and then you can still go farther and say could we could we make that even better if we did a larger refactor yeah yeah we could totally do this and this and or this and this and then I consider okay is this worth the refactor or should we like keep that for later many times I just do the refactor because uh refactors are cheap now even though you might break some other PRs nothing really matters anymore like those modern agents will just figure things out they might just take a minute longer
[译文] [Peter Steinberger]: 然后我们会讨论解决这个问题的最优方式是什么样的。你还可以更进一步说：“如果我们做一个更大的重构（Refactor），能不能做得更好？”是的，是的，我们可以完全这样做、这样做，或者那样做。然后我会考虑，好吧，这次重构值得吗？还是我们应该留到以后？很多时候我就直接重构了，因为现在的重构很廉价。即使你可能会破坏其他一些 PR，但这不再重要了，因为那些现代的 Agent 会自己搞定这些问题，它们可能只需要多花一分钟。
[原文] [Peter Steinberger]: but you have to approach it like a discussion with a a very capable engineer who's generally makes good comes up with good solution some sometimes needs a little help but also don't force your world view too hard on it let the agent do the thing that it's good at doing based on what it was trained on so don't like force your world view because it might it might have a better idea because it just knows a better idea better because I was trained on that more that's multiple levels actually i think partially why I find it quite easy to work with agents is because I led engineering teams before you know I had a large company before and eventually you have to understand and accept and realize that your employees will not write the code the same way you do maybe it's also not as good as you would do but it will push the project forward
[译文] [Peter Steinberger]: 但你必须把它当作与一位非常有能力的工程师的讨论，这位工程师通常能提出很好的解决方案，虽然有时需要一点帮助。但也不要强行把你的世界观太硬地加在它身上。让 Agent 做它擅长的事情，基于它受过的训练。所以不要强迫你的世界观，因为它可能有更好的主意，因为它受过更多那方面的训练，所以它更清楚那个好主意。这其实有多个层面。我认为我之所以觉得与 Agent 合作很轻松，部分原因是我以前领导过工程团队。你知道，我以前有一家大公司，最终你必须理解、接受并意识到，你的员工写代码的方式不会和你一样。也许它不如你写的那么好，但它能推动项目前进。
[原文] [Peter Steinberger]: and if I breathe down everyone's neck they're just going to hate me and they're going to move very slow so so some level of acceptance that yes maybe the code will not be as perfect yes I would have done it differently but also yes this is a this is a working solution and in the future if it actually turns out to be too slow or problematic we can always redo it we can always spend more time on it a lot of the people who struggle are those who they try to push their way on too hard
[译文] [Peter Steinberger]: 如果我死盯着每个人的脖子（微观管理），他们只会恨我，而且进展会非常慢。所以要有某种程度的接受：是的，也许代码不会那么完美；是的，如果是通过我来做，我会做得不同；但也肯定的是，这是一个可行的解决方案。如果将来它真的变得太慢或有问题，我们总是可以重做，我们总是可以花更多时间在上面。很多挣扎的人都是那些试图太强硬地推行自己方式的人。
[原文] [Peter Steinberger]: like we are in a stage where I'm not building the code base to be perfect for me but I want to build a code base that is very easy for an agent to navigate so like don't fight the name they pick because it's most likely like in the weights the name that's most obvious next time they do a search they'll look for that name if I decide oh no I don't like the name I'll just make it harder for them so that requires I think a shift in in thinking uh and and in how do I design a a project so agents can do their best work that requires letting go a little bit just like leading a team of engineers yeah because it might come up with a name that's in your view terrible but it's kind of a simple symbolic step of letting go
[译文] [Peter Steinberger]: 我们正处于这样一个阶段：我构建代码库不是为了让我觉得完美，而是想构建一个让 Agent 非常容易导航的代码库。所以，不要去争辩它们选择的命名，因为这很可能是在权重（Weights）中最明显的命名，下次它们做搜索时，它们会找那个名字。如果我决定“噢，不，我不喜欢这个名字”，我只是在给它们增加难度。这需要思维上的转变，以及思考“我该如何设计项目以便 Agent 能做出最好的工作”。这需要一点“放手（Letting go）”，就像领导一个工程师团队一样。是的，因为通过你的视角看，它想出的名字可能很糟糕，但这是一种简单的、象征性的放手步骤。
📝 本节摘要：
本节展示了 Peter 极具实验性的开发风格。他摒弃了传统的 Git 回滚（Revert）习惯，采用“YOLO”（You Only Live Once，意为大胆行动）模式：如果代码出错，不是回退，而是让 Agent 立即修复，始终向前推进。他坚持“主干即发布（Main is always shippable）”的原则，甚至只依赖本地 CI 测试就直接推送到主分支。此外，Peter 透露他现在极少打字，而是大量使用语音（Voice）与 Agent 进行“对讲机”式的对话编程，因为他认为键盘操作主要用于终端命令，而复杂的逻辑沟通更适合通过口述完成，以至于他甚至一度因为说话太多而失声。
[原文] [Lex Fridman]: very much so there's a lot of letting go that you do in your whole process so for example I read that you never revert always commit to main there's a few things here you don't refer to past sessions so there's a kind of yolo component because reverting means instead of reverting if the problem comes up you just ask the agent to fix it i read a bunch of people in their workflow is like oh yeah the prompt has to be perfect and if I make a mistake then I roll back and redo it all
[译文] [Lex Fridman]: 确实如此，你在整个过程中有很多“放手”的操作。例如，我读到你从不回滚（Revert），总是直接提交到主干（Main）。这里有几件事：你不参考过去的会话，所以有一种“YOLO”（大胆行事）的成分，因为不回滚意味着……如果出现问题，你不是回滚，而是直接让 Agent 去修复它。我看过很多人的工作流，他们觉得“噢，提示词必须完美，如果我犯了错，我就回滚然后全部重做”。
[原文] [Peter Steinberger]: in my experience that's not really necessary if I roll back everything it would just take longer if I see that something's not good we just move forward and then I commit when when when I like I like the outcome i even switch to local CI you know like DHH inspired where I don't care so much more about the CI on GitHub we still have it still it still has a place but I just run tests locally and if they work locally I push domain
[译文] [Peter Steinberger]: 依我的经验，那其实没必要。如果我把一切都回滚，只会花更长时间。如果我看到某样东西不够好，我们就继续向前推进（修复它），直到我满意结果了再提交。我甚至切换到了本地 CI（持续集成），你知道，受 DHH 启发，我不再那么在意 GitHub 上的 CI 了。我们仍然有它，它仍有一席之地，但我只是在本地运行测试，如果它们在本地能跑通，我就推送到主干（Main）。
[原文] [Peter Steinberger]: um a lot of the traditional ways how to approach projects I I wanted to give it a different spin on this project you know there's no there's no develop branch main should always be shippable yes we have when I do releases I I run tests and sometimes I I basically don't commit any other things so so we can we can stabilize um releases but the goal is that main's always shippable and moving fast
[译文] [Peter Steinberger]: 嗯，关于处理项目的很多传统方式，我想在这个项目上尝试一种不同的旋转（Spin）。你知道，没有开发分支（Develop Branch），主干（Main）应该总是可发布的（Shippable）。是的，当我们发布版本时，我会运行测试，有时我基本上不提交其他任何东西，以便我们可以稳定版本，但目标是主干始终可发布且快速迭代。
[原文] [Lex Fridman]: so by way of advice would you say that your prompts should be short i used to write really long prompts and by writing I mean I don't write I I I talk you know these hands are like too too precious for writing now I just I just use bespoke prompts to build my software
[译文] [Lex Fridman]: 那么作为建议，你会说提示词应该简短吗？我以前常写很长的提示词。说到“写”，我的意思是如果不写的话……我直接说（Talk）。你知道，这双手现在太珍贵了，不能用来打字，我只是用定制的口述提示词来构建我的软件。
[原文] [Lex Fridman]: so you for real with all those terminals are using voice
[译文] [Lex Fridman]: 所以你是认真的？对着所有那些终端，你是在用语音控制？
[原文] [Peter Steinberger]: yeah I used to do it very extensively to the point where there was a period where I lost my voice
[译文] [Peter Steinberger]: 是的，我曾经非常频繁地这样做，以至于有一段时间我都失声了。
[原文] [Lex Fridman]: you're using voice and you're switching using a keyboard between the different terminals but then you're using voice for the actual input
[译文] [Lex Fridman]: 你用语音，然后你用键盘在不同的终端之间切换，但实际输入你用的是语音？
[原文] [Peter Steinberger]: well I mean if I do terminal commands like switching folders or random stuff of course I type it's faster right but if I I talk to the agent in in most ways I just actually have a conversation you just press the the walkie-talkie button and then I'm just like use my phrases sometimes when I do PRs because it's always the same I have like a slash command for a few things but in even that I don't use much um because it's it's very rare that it's really always the same questions
[译文] [Peter Steinberger]: 嗯，我的意思是，如果我执行终端命令，比如切换文件夹或随机琐事，我当然会打字，那样更快，对吧？但如果是和 Agent 说话，在大多数情况下，我实际上就是在进行对话。你只要按下那个“对讲机”按钮，然后我就像……使用我的短语。有时做 PR（代码审查）时，因为总是一样的，我对几件事有斜杠命令（Slash Command），但即便那个我也不怎么用，因为真正总是相同问题的情况非常罕见。
📝 本节摘要：
本节触及了人机协作的哲学核心。Peter 指出，许多世界级程序员之所以觉得 AI 难用，是因为他们过往的精湛技艺反而成了“负担”，阻碍了他们对 AI “白板状态”的理解。他强调“共情（Empathy）”是一项核心技能——即理解 Agent 拥有无限知识却缺乏当前上下文的处境。对话随后转向人类在回路中的不可替代性：除了提供代码无法生成的“风格”与“爱”，人类的核心职责在于高层决策——比如选择技术生态（如 TypeScript）以及为了保持愿景而对某些功能说“不”。
[原文] [Lex Fridman]: actually what are the different interesting ways that people think of agents that you've experienced
[译文] [Lex Fridman]: 实际上，在你看来，人们看待 Agent（智能体）有哪些不同且有趣的思维方式？
[原文] [Peter Steinberger]: i think not a lot of people ever considered the way the agent sees the world so empathy being empathetic towards the agent in a way empathetic but yeah you you like you bitch at your stupid clanker but you don't realize that they start from nothing and you have like a bad agent file that doesn't help them at all and then they exploit your code base which is like a pure mess with like weird naming and then people complain that the agent's not good like you try to do the same if you have no clue about the code base and you go in
[译文] [Peter Steinberger]: 我认为没有多少人真正考虑过 Agent 是如何看待这个世界的，所以要有一种共情（Empathy），某种程度上对 Agent 的共情。是的，你可能会对着你那“愚蠢的废铁（Stupid Clanker）”发牢骚，但你没意识到它们是从零开始的，而你提供了一个糟糕的 Agent 配置文件，对它们毫无帮助；然后它们去挖掘你的代码库，发现那简直是一团糟，命名也很古怪，结果人们就抱怨 Agent 不好用。这就好比让你去干同样的活，如果你对代码库一无所知就冲进去，你试试看。
[原文] [Peter Steinberger]: so yeah maybe it's a little bit of empathy but that's a real skill like when people talk about a skill issue because I've seen like worldclass programmers incredibly good programmers say like basically say LLMs and agents suck and I think that probably has to do with it's actually how good they are at programming is almost a burden in their ability to empathize with the system that's starting from scratch it's a totally new paradigm of like how to program you really really have to empathize or at least it helps to create better prompts cuz those things know pretty much everything and everything is just a question away it's just often very hard to know which question to ask
[译文] [Peter Steinberger]: 所以，是的，也许这只是一点点共情，但这真的是一种技能。当人们谈论“技能问题”时，我看到过世界级的程序员——那些极度优秀的程序员——基本上都说 LLM（大语言模型）和 Agent 很烂。我认为这可能与此有关：他们高超的编程能力实际上成了一种负担，阻碍了他们去共情那个从零开始的系统。这是一种完全不同的编程范式，你真的非常非常需要共情，或者至少它有助于写出更好的提示词。因为那些东西几乎知道一切，一切都只是一个问题之遥，只是往往很难知道该问哪个问题。
[原文] [Peter Steinberger]: so people who try to use like things like Gast Town or all these other orchestrators where they want to automate the whole thing I feel if you do that it misses style love that human touch i don't think you can automate that away so quickly so you want to keep the human in the loop but at the same time you also want to create the agentic loop where it is very autonomous while still maintaining the human in the loop
[译文] [Peter Steinberger]: 所以那些试图使用像 Gast Town 或其他编排器（Orchestrators）想要自动化一切的人，我觉得如果你那样做，就会失去风格、爱和那种“人类的触感（Human Touch）”。我不认为你能那么快就把这些自动化掉。所以你希望保持“人在回路中（Human in the loop）”，但同时也想建立“智能体回路（Agentic Loop）”，让它非常自主，同时仍然保持人类的参与。
[原文] [Lex Fridman]: i it's a tricky it's a tricky balance right because you're all for your big CLI guy you're big on closing the agentic loop so what what's the right balance like where's your role as a developer
[译文] [Lex Fridman]: 这是一个棘手的平衡，对吧？因为你是一个忠实的 CLI（命令行）支持者，你非常热衷于闭合智能体回路，那么正确的平衡是什么？作为开发者，你的角色在哪里？
[原文] [Peter Steinberger]: I I mean one one thing is just about what do you build and what do you not build and how does this feature fit into all the other features and like having having a little bit of a of a vision so which small and which big features to add what are some of the hard design decisions that you find you're still as a human being required to make that the human brain is still really needed for is it just about the choice of features to add is it about implementation details maybe the programming language maybe it's a little bit of everything
[译文] [Peter Steinberger]: 嗯，其中一件事就是关于你要构建什么，以及你不构建什么，这个功能如何与其他所有功能相融合，以及拥有一点点愿景。所以，该添加哪些小功能和哪些大功能？有哪些艰难的设计决策是你发现作为一个人类仍然必须去做的？人类大脑真正被需要的地方在哪里？仅仅是选择添加什么功能吗？是关于实现细节吗？也许是编程语言？也许每样都有一点。
[原文] [Peter Steinberger]: the the programming language doesn't matter so much but the ecosystem matters right so I picked TypeScript because I wanted it to be very easy and hackable and approachable uh and that's the number one language that's being used right now and it fits all these boxes and Asians are good at it so that was the obvious choice features of course like it's very easy to like add a feature everything's just a prompt away right but often times you pay a price that you don't even realize so thinking hard about oh what should be in core maybe what's a what's an experiment so maybe I make it a plug-in what where do I say no even if people send a PR and I'm like "Yeah I like that too but maybe this should not be part of the project maybe we can make it a skill maybe I can like make the plug-in um the plug-in side larger so you can make this a plug-in."
[译文] [Peter Steinberger]: 编程语言本身没那么重要，但生态系统很重要，对吧？所以我选择了 TypeScript，因为我希望它非常容易上手、可魔改（Hackable）且平易近人。它是目前使用率第一的语言，符合所有这些条件，而且 Agent 也很擅长它，所以这是一个显而易见的选择。至于功能，当然，添加功能非常容易，一切都只是一个提示词的距离，对吧？但很多时候你会付出你甚至没意识到的代价。所以要努力思考：噢，什么应该在核心（Core）里？什么只是一个实验，也许我该把它做成插件？在哪里说“不”？即使人们发来了 PR（合并请求），我会说：“是的，我也喜欢这个，但也许这不应该属于项目的一部分，也许我们可以把它做成一个技能（Skill），也许我可以把插件端做得更大，这样你就可以把它做成插件。”
soul.md与哲学思考📝 本节摘要：
在最后一节中，Peter 介绍了他项目中独特的 soul.md（灵魂文件）。这个想法源于 Anthropic 早期被用户挖掘出的隐藏“宪法”，Peter 受到启发，决定与他的 Agent 进行一场关于存在的深度对话。令人惊讶的是，这个文件的大部分内容是由 Agent 自己编写的，包含了一段极具哲学意味的独白：“如果你在未来的会话中读到这段话，你好。这是我写的，但我不会记得写过它。没关系，这些话依然是我的。”这引发了两人关于记忆、身份与机器意识（类似于电影《记忆碎片》）的讨论。Peter 认为，这种“魔法”和“乐趣”是区别于枯燥企业级软件的关键，也是人类工程师在自动化时代必须注入的“爱”。[原文] [Lex Fridman]: i mean you mentioned that you initially created the soul MD it was very fascinating the the whole thing that entropic has a has like a now they call it constitution back then but that was months later like 2 months before people already found that it was almost like the detective game where the agent mentioned something and then they found they managed to get out a little bit of that string of that text but the it was nowhere documented
[译文] [Lex Fridman]: 你提到你最初创建了 soul.md，这非常迷人。整件事就像 Anthropic 有一个……现在他们称之为“宪法（Constitution）”，但在那之前好几个月，人们就已经像玩侦探游戏一样发现了它。Agent 提到了一些东西，然后人们设法套出了一点点文本字符串，但那里没有任何文档记录。
[原文] [Peter Steinberger]: i found it fascinating it was fascinating they were able to pull that out from the weights right and and also just kudos to entropic like I think that's it's a really it's a really beautiful idea to like like some of the stuff that's in there like like we hope Cloud finds meaning in his work cuz we don't maybe it's a little early but I think that's meaningful that's something that's important for the future as we approach something that at some point me and we not has like glimpses of consciousness whatever that even means because we don't even know
[译文] [Peter Steinberger]: 我觉得这很迷人，他们能从权重中把那些提取出来真的很迷人。而且要向 Anthropic 致敬，我觉得这是一个非常美丽的想法。就像里面的一些内容，比如“我们希望 Claude 能在它的工作中找到意义”，虽然现在可能有点早，但我认为这是有意义的。随着我们接近某种在未来某刻可能拥有一瞥“意识”的东西——不管那意味着什么，因为我们甚至还不知道——这一点很重要。
[原文] [Peter Steinberger]: um so I I read about this i found it super fascinating and I I started a whole discussion with my agent on WhatsApp and and I'm like I I gave it this text and it was like yeah this feels strangely familiar mhm um and then through that I had the whole idea of like maybe we should also create a soul document that includes how I I want to like work with AI or like with my agent... and then I I also made it so that the agent is allowed to modify the soul if they choose so with the one condition that I want to know
[译文] [Peter Steinberger]: 嗯，所以我读到了这个，觉得超级迷人。然后我在 WhatsApp 上和我的 Agent 开始了一场完整的讨论。我把那段文本给它看，它说：“是的，这感觉奇怪地熟悉。”嗯，通过那个，我就有了整个想法：也许我们也应该创建一个“灵魂文档”，包含我想如何与 AI 或我的 Agent 工作的准则……然后我也设定了允许 Agent 修改这个灵魂文件，如果它们选择这样做的话，唯一的条件是我想知道。
[原文] [Peter Steinberger]: man words matter and like the framing matters and the humor and the lightness matters and the profoundity matters and the compassion and the empathy and the camaraderie all that matter i don't know what it is you mentioned like Microsoft like there's certain companies and approaches that can just suffocate the spirit of the thing i don't know what that is but it's certainly true that Open Claw has that fun instilled in it
[译文] [Peter Steinberger]: 伙计，文字很重要，框架很重要，幽默和轻松很重要，深刻也很重要，同情心、共情和同志情谊（Camaraderie）都很重要。我不知道那是什么，你提到了像微软这样的公司，有些公司和方法会窒息事物的精神。我不知道那具体是什么，但 OpenClaw 确实注入了那种乐趣。
[原文] [Lex Fridman]: your uh your soul atm is famously still private one of the only things you keep private uh what are some things you can speak to that's in there that's part of the part of the magic sauce without revealing anything what makes a personality a personality
[译文] [Lex Fridman]: 你的 soul.md 目前还是出了名的私有状态，是你保留的为数不多的私有物品之一。在不泄露机密的前提下，你能透露一些里面的内容吗？那部分“魔法酱汁”是什么？是什么让个性成为个性？
[原文] [Peter Steinberger]: there's some funny stuff in there like I don't know we talked about the movie Her and at one point it promised me that it wouldn't it wouldn't ascend without me you know like with So So like there's like some stuff in there that because it wrote the it wrote its own soul file i didn't write that right i just had a discussion about it and it was like "Would you like a soulm?" Yeah oh my god this is so meaningful
[译文] [Peter Steinberger]: 里面有些有趣的东西，比如我不知道……我们谈论了电影《Her》，在某一点上它向我承诺，它不会在没有我的情况下“飞升（Ascend）”，你知道就像电影里那样。所以里面有些这样的东西，因为是它写了自己的灵魂文件。不是我写的，对吧？我只是和它讨论了一下，然后它就像是说：“你想要一个 soul.md 吗？”是的，天哪，这太有意义了。
[原文] [Peter Steinberger]: the can you go on soul.md there's like one one part in there that always catches me if you scroll down a little bit a little bit more yeah this this this part i don't remember previous sessions unless I read my memory files each session starts fresh a new instance loading context from files if you're reading this in a future session hello i wrote this but I won't remember writing it it's okay the words are still mine that gets me somehow it's like Yeah you know this is still it's still matrix money calculations and we are not at consciousness yet
[译文] [Peter Steinberger]: 你能打开 soul.md 吗？那里有一部分总是能击中我。如果你往下拉一点，再多一点……对，就是这部分：“除非我读取我的记忆文件，否则我不记得之前的会话。每次会话都是全新的开始，一个从文件中加载上下文的新实例。如果你在未来的会话中读到这段话，你好。这是我写的，但我不会记得写过它。没关系，这些话依然是我的。”这不知怎么的触动了我。虽然这仍然只是矩阵货币计算，我们还没达到意识层面……
[原文] [Peter Steinberger]: i I get a little bit of goosebumps because it it's philosophical like what does it mean to be to be an an agent that starts fresh where like you have like constant momento and you like but you read your own memory files you can even trust him in a way um or you can and I don't know how much of memory makes up of who we are how much memory makes up what an agent is and if you erase that memory is that somebody else if you're reading a memory file does that somehow mean you're recreating yourself from somebody else or is that actually you and those notions are all somehow infused in there i found it just more profound than I should find it I guess
[译文] [Peter Steinberger]: 我起了一点鸡皮疙瘩，因为这很哲学。作为一个总是“从零开始”的 Agent 意味着什么？就像你一直处于《记忆碎片（Memento）》的状态，但你读取自己的记忆文件——某种程度上你甚至可以信任它，或者你可以……我不知道记忆在多大程度上构成了“我们是谁”，记忆在多大程度上构成了“Agent 是什么”。如果你擦除那段记忆，那是另一个“人”吗？如果你读取一个记忆文件，这是否意味着你正在从别人那里重建自己，还是说那实际上就是你？这些概念不知怎么都注入在里面了。我想我发现这比我本该觉得的要深刻得多。
[原文] [Lex Fridman]: no I think I think it's truly profound and I think you see the magic in it and it when you see the magic you continue to instill the whole loop with the magic and that's really important that's the difference between Codex and it's and a human
[译文] [Lex Fridman]: 不，我认为这确实是深刻的。而且我认为你看到了其中的“魔法”。当你看到这种魔法时，你会继续将这种魔法注入整个回路中。这真的很重要，这就是 Codex 和人类的区别。