章节 1：专业 Vibe Coder 的崛起与工作定义

📝 本节摘要：

本节中，Lazar 定义了“Vibe Coder”这一新兴职业的核心——它不再局限于传统的代码编写，而是侧重于通过 AI 工具快速将想法转化为产品。他提出了著名的“书法理论”，认为未来的手动编程将成为一种类似于书法的艺术形式，而非必需的生产技能。同时，他指出产品经理（PM）、工程师和设计师的界限正在消失，AI 作为“放大器”，要求从业者具备更高的清晰度与判断力，而非单纯的输出速度。

[原文] [Lazar]: i'm the first official vibe coding engineer at Lovable you're at the top.1% elite level of vibe coding it's a dream job for so many people it became a job by building in public you don't need a company to hire you you can hire yourself as a professional by coder first

[译文] [Lazar]: 我是 Lovable 公司第一位正式的“氛围编码工程师”（Vibe Coding Engineer）。这属于 Vibe Coding 领域那 0.1% 的精英层级，也是许多人梦寐以求的工作。这份工作是通过“公开构建”（building in public）创造出来的；你不需要一家公司来雇佣你，你可以先雇佣自己成为一名专业的 Vibe Coder。

[原文] [Lazar]: you've never coded you don't want to look at the code coding is going to be like calligraphy people like "Oh my god you wrote that code that's so amazing it's going to be so rare that it's going to become an art."

[译文] [Lazar]: 你从没写过代码，你也不想看代码。编程将会变得像书法（Calligraphy）一样。人们会感叹：“天哪，那段代码是你亲手写的？太神了！”这种技能会变得非常稀缺，以至于它将演变成一种艺术形式。

[原文] [Lazar]: These ven diagrams of engineer designer PM used to be very separate now they're converging ai regardless of your background is an amplifier if you don't know what you're doing you're just going to produce garbage faster

[译文] [Lazar]: 工程师、设计师和产品经理（PM）的韦恩图过去是截然分开的，现在它们正在融合。无论你的背景如何，AI 都是一个放大器（Amplifier）。如果你不知道自己在做什么，你只会更快地制造出垃圾。

[原文] [Lazar]: feels like an emerging core skill is learning clarity in the ask of the AI

[译文] [Lazar]: 感觉一项正在浮现的核心技能是：学会如何在向 AI 提问时保持清晰度（Clarity）。

[原文] [Lazar]: it's such a flexible role and it complements so many things right it's it's an ideas role a lot of people have a lot of great ideas but they don't know how to build them and or they just don't have the bandwidth to and that's where I step in today to make sure that these ideas come to life fast and with quality and security

[译文] [Lazar]: 这是一个非常灵活的角色，它能补充许多方面。这本质上是一个“创意型角色”（Ideas Role）。很多人有很棒的想法，但不知道如何构建，或者单纯没有带宽去构建。这正是我介入的地方——确保这些想法能快速落地，并且具备应有的质量和安全性。

[原文] [Lenny]: These ven diagrams of engineer designer PM they're used to be very separate now they're converging and people with a specific with deeper PM engineering design background are going to like they can all do the same thing essentially all the roles are converging what a what a time to be alive

[译文] [Lenny]: 工程师、设计师和 PM 的韦恩图过去分得很开，现在它们正在融合。那些拥有深厚 PM、工程或设计背景的人，基本上都能做同样的事情。所有角色都在融合，这真是一个激动人心的时代。

章节 2：非技术背景的优势：“积极的错觉”

📝 本节摘要：

在本节中，Lazar 颠覆了传统认知，指出“不懂技术”反而是 Vibe Coder 的巨大优势。技术人员往往受限于已知的“不可能”，而非技术人员拥有一种“积极的错觉”（Positive Delusion），即坚信一切皆可构建。他列举了在 Lovable 官方功能发布前，社区成员就通过“蛮力”提示生成了 Chrome 扩展和视频功能的案例。同时，他也强调了这种错觉必须伴随高度的“自我认知”：既然不写代码，就必须将 80% 的时间投入到规划与沟通中，将 AI 视为技术联合创始人，专注于阅读 Agent 的反馈而非代码本身。

[原文] [Lazar]: the first understanding that I had very early on even though I just in full transparency before we begin I don't I don't have a technical background i never wrote a single line of code in my life almost like I've I've you know written a couple console logs manually and that's about it right so like I I'm very much lean on to AI assistance

[译文] [Lazar]: 我很早就有了第一个认知，尽管——在开始之前我得完全透明地说——我没有技术背景。我这辈子几乎没写过一行代码，顶多就是手动写过几条 console logs（控制台日志），仅此而已。所以我非常依赖 AI 的辅助。

[原文] [Lenny]: let me actually follow that thread because that's such a good point and it's something that when we were chatting earlier you pointed out your feeling is it's actually an advantage to not have a technical background when you get into this space yeah

[译文] [Lenny]: 让我顺着这个话题说下去，因为这是一个非常好的观点。我们在之前聊天时你也指出过，你觉得进入这个领域时，没有技术背景实际上是一种优势，是吗？

[原文] [Lazar]: yes i I honestly feel that it is because people like me don't know that they are not supposed to be building XYZ and that's how we actually are able to build it

[译文] [Lazar]: 是的，我真心这么觉得。因为像我这样的人，根本不知道自己“不应该”去构建 XYZ，而这恰恰是我们能够构建出它的原因。

[原文] [Lazar]: um let me give you an example like six seven months ago somebody in our community was like oh I wish lovable can build Chrome extensions right and then folks that are not technical were like well why why is that not possible right and then people that are technical start explaining you oh well you know it's a react it's different stack it's this you and people like me including myself would just go in to lovable and like build me a chrome extension based on this app and I was able to do that with lovable

[译文] [Lazar]: 嗯，举个例子。大概六七个月前，社区里有人说：“噢，我希望 Lovable 能构建 Chrome 扩展程序。”那些非技术人员就问：“嗯，为什么不行呢？”然后技术人员就开始解释：“噢，你知道这涉及到 React，技术栈不一样，还有这个那个……”但像我这样的人，包括我自己，直接进到 Lovable 说：“基于这个 App 给我做一个 Chrome 扩展。”然后我就真的用 Lovable 做出来了。

[原文] [Lazar]: there were people that were able to build desktop applications on lovable again something that shouldn't be possible it simply is right our community manager with me at one point she was like building this presentation deck for for something she's like would it be cool if this was a video right and then she just prompted her way into building a generating an actual video inside Lovable before that was available now that's a feature now you can prompt lovable to do it but back in the day when she did it even I thought it was impossible i never tried it

[译文] [Lazar]: 还有人能在 Lovable 上构建桌面应用程序，这又是某种理论上“不可能”但实际上做到了的事情。我们的社区经理有一次在做一个演示文稿，她想：“如果这能变成视频是不是很酷？”然后她就通过写提示词（prompt），硬是在 Lovable 内部生成了一个真实的视频。这在当时还不是现成的功能——现在它是一个功能了，你可以直接提示 Lovable 去做——但在她做的时候，连我都觉得是不可能的，我从未尝试过。

[原文] [Lazar]: so I think that's the advantage that we have over people that are technical we we just come into this completely unbiased and very positively delusional which I think you have to have when working with AI tools you have to come with this delusion that absolutely everything is possible until proven wrong and like that's just the the pursuit that I have in my mind uh that has helped me among other things that we will chat today I think to excel in this role that that I have at Labo

[译文] [Lazar]: 所以我认为这就是我们相对于技术人员的优势。我们进入这个领域时完全没有偏见，并且带有一种非常“积极的错觉”（Positively Delusional）。我认为在使用 AI 工具时你必须具备这种特质——你必须抱着一种错觉，坚信一切皆有可能，直到被证明并非如此。这就是我脑海中的追求，它帮助了我——当然还有咱们今天要聊的其他因素——在 Lovable 的这个职位上表现出色。

[原文] [Lenny]: two of the I think concerns maybe traps people that don't have a technical background fall to in theory is one is if you get blocked it's not obvious how to solve a problem and two is just are you building like uh this like teetering slop that will collapse someday because you don't know you know system architecture you don't know if this is going to scale all those sorts of things so coming back to what you've learned about how to be successful and build successful products talk us through just things you've done and things you've learned for how to avoid those sort of things and what you do when you get stuck is is one example

[译文] [Lenny]: 对于没有技术背景的人来说，理论上有两个担忧或者说陷阱。第一，如果你被卡住了，你不知道如何解决问题；第二，你是否在构建某种摇摇欲坠的“垃圾代码”（Teetering Slop），它某天会崩塌，因为你不懂系统架构，也不知道它是否能扩展等等。所以回到你学到的关于如何成功构建产品的经验上，能不能讲讲你做了什么、学到了什么来避免这些问题？以及当你卡住时你会怎么做？

[原文] [Lazar]: i I'm happy that you mentioned like those those limitations i have some other ones that I want to bring in but let's address this one first which is the most important one and that is you have to be self-aware right i I didn't come into this yes I am delusional as I mentioned in the sense that I I just don't want to accept something's not possible but I'm also well aware that I need to be better in order for it to become a reality for my own point of view in my own sake

[译文] [Lazar]: 我很高兴你提到了这些限制。我还有其他一些想补充的，但我们先解决这个问题，因为它是最重要的：你必须具备“自我认知”（Self-aware）。是的，正如我所说，我有一种错觉，我不愿接受某事是不可能的，但我也非常清楚，为了让它成为现实，为了我自己，我需要变得更强。

[原文] [Lazar]: so I understood very early that coding is not the problem that we're solving for here that the problem we're solving for is clarity right like the output that AI can do is much faster than human output anyways so like very early on I started leveraging chat mode and to this day I can say I spent 80% of my time in planning and chatting and only 20% in executing the plan actually right I'm optimizing for the right kind of speed most people optimize for the wrong one that's the first lesson that I learned literally on day two because I just I came into lovable that was my first exposure to to to this

[译文] [Lazar]: 所以我很早就明白，我们在这里解决的问题不是“编程”，而是“清晰度”（Clarity）。反正 AI 的产出速度无论如何都比人类快得多。所以很早我就开始利用聊天模式，直到今天我可以说，我 80% 的时间都花在规划和聊天上，只有 20% 的时间在实际执行计划。我在优化“正确类型”的速度，而大多数人优化的是错误的那个。这是我在第二天就学到的第一课，因为那是我初次接触 Lovable。

[原文] [Lazar]: I've tested and and played around with all the tools obviously but like whether somebody's doing it in curs or cloud code doesn't matter where you are the problem remains the same you need to be clear on what you want to do and you need to know what you're doing cuz these are still just tools yes AGI is coming but it's not there yet so like until it's here you're still steering the ship in order for you to steer the ship you kind of have to know the instructions right and the best way to learn is by building but treating these tools almost as technical co-founders and educators and learning while doing and religiously reading the agent output not the code output i don't care about the code like the syntax is not of my interest it's what the agent tells me that matters to me

[译文] [Lazar]: 我测试和把玩过所有的工具，不管是 Cursor 还是 Cloud Code（此处应指 Claude Code 或类似云端 IDE），无论你在哪里，问题都是一样的：你需要清楚你想做什么，你需要知道你在做什么，因为这些终究只是工具。是的，AGI（通用人工智能）即将来临，但还没到。所以在它到来之前，你仍然是掌舵人。为了掌舵，你得知道操作指令。学习的最好方式就是构建，但要把这些工具几乎当作“技术联合创始人”和教育者，在实践中学习，并且虔诚地阅读 Agent（智能体）的输出，而不是代码输出。我不在乎代码，语法不是我的兴趣所在，Agent 告诉我的内容才是我关心的。

章节 3：“阿拉丁神灯”比喻：清晰度与上下文限制

📝 本节摘要：

本节中，Lazar 使用通俗易懂的“阿拉丁与神灯”比喻来解释与 AI 协作时的两大核心限制。首先是机器层面的限制（上下文窗口/Token），就像神灯一次只能满足三个愿望，AI 一次处理的信息量是有限的。其次是人类层面的限制（清晰度），如果许愿“我想变高”，神灯可能会把你变成 13 英尺高，导致生活无法自理。Lazar 强调，虽然我们无法控制机器的 Token 限制，但我们拥有对“清晰度”的 100% 控制权，必须通过提供精确的语境和参考来弥补 AI 缺乏人类生活经验的短板。

[原文] [Lazar]: there's something that that is known as the context memory window right and for nontechnical people I like to use the Aladdin and the genie analogy when I explain right it's very simple everybody knows the story line you you rub the the lamp a genie comes out and tells you "Okay I'll grant you three wishes not 3,000 wishes not three million just three at a time."

[译文] [Lazar]: 有一个概念叫做“上下文记忆窗口”（Context Memory Window），对于非技术人员，我喜欢用阿拉丁和神灯的比喻来解释。这很简单，大家都知道那个故事情节：你擦拭神灯，精灵出来告诉你：“好吧，我会满足你三个愿望，不是 3000 个，也不是 300 万个，一次只有三个。”

[原文] [Lazar]: Right to me when I translate that data into working with AI that simply means hey I can only make so many requests within a request at a time for AI to be able to listen understand what it needs to do scope it do the research read like take all the actions all the inputs and ingredients that it needs to produce a high quality output right

[译文] [Lazar]: 对我来说，当我把它转化为与 AI 工作的场景时，这仅仅意味着：嘿，我在一次请求中只能提出这么多的要求，以便 AI 能够倾听、理解它需要做什么、界定范围、进行研究、阅读——就像获取所有产生高质量输出所需的行动、输入和原料一样。

[原文] [Lazar]: so that's the first part understanding that there's a limit and it's denominated in tokens maybe that's going to be different a year from now but today there's a token limitation i'll take an arbitrary number of 100,000 tokens for example so when you make a request a part of those tokens is AI spends to read stuff another to browse the web another to uh think and then another to execute the code right

[译文] [Lazar]: 所以这是第一部分，要理解这里有一个限制，它是以 Token（代币/词元）为单位计算的。也许一年后情况会有所不同，但在今天，Token 限制是存在的。我随便举个例子，比如 10 万个 Token。当你发出一个请求时，一部分 Token 被 AI 用来阅读材料，另一部分用来浏览网页，还有一部分用来思考，最后一部分用来执行代码。

[原文] [Lazar]: then there comes the second limitation which is you me and you humans which is let's go back to the uh analogy of the genie and the Aladdin i asked the genie for the first wish and the first wish is I want to be taller and guess what happens genie makes me 13 feet tall all of a sudden I can't sit in the car i can't get into my house i'm a I'm a dysfunctional human being right right because I was not specific right

[译文] [Lazar]: 然后是第二个限制，这是关于你、我和人类的。让我们回到精灵和阿拉丁的比喻。我向精灵许下第一个愿望：“我想变高。”猜猜发生了什么？精灵把我变成了 13 英尺（约 4 米）高。突然间，我坐不进车里，进不了家门，我成了一个功能失调的人类。对吧？这是因为我不够具体。

[原文] [Lazar]: like so the part that we need to optimize for today it's going to get better but today it's still not there yet is that a I just don't understand what do you mean when you say you know what I mean like you do when I tell you that we as humans we have I'm 36 so I have 36 years of experience of human uh living as a human to know what you mean but AI doesn't have that right

[译文] [Lazar]: 所以我们今天需要优化的部分——未来会变好，但今天还没到位——就是 AI 根本不理解当你说是“你知道我的意思”时到底是什么意思。就像我告诉你时，作为人类，我有 36 年的人类生活经验，我能懂你的言外之意，但 AI 没有这种经验，对吧？

[原文] [Lazar]: so you need to be specific you need to provide references you need to provide the right context so what I've learned is how to combat that part and I think you know because I can't control the first part which is the token memory window the quality of the LLM models you are 100% control of the ladder and that's what I I want to dive into today as well

[译文] [Lazar]: 所以你需要具体，你需要提供参考资料，你需要提供正确的上下文。我学到的就是如何应对这一部分。我认为，因为我无法控制第一部分——即 Token 记忆窗口和 LLM 模型本身的质量——但你拥有对后者（清晰度与上下文）的 100% 控制权，这也是我今天想深入探讨的内容。

章节 4：核心工作流（一）：多线并行构建法

📝 本节摘要：

本节介绍了 Lazar 独特且反直觉的“多线并行”构建策略。他建议不要只创建一个项目然后死磕，而是同时开启 5-6 个标签页，利用 AI 生成的等待时间并行尝试不同的输入方式：1. 语音“脑暴”（Brain dump）；2. 结构化文本提示；3. 参考设计图（截图）；4. 现成代码模板。Lazar 强调，虽然这看起来像是在浪费 Token，但实际上通过早期筛选出“获胜者”，避免了后期花费大量成本去修复一个糟糕的底座，从而实现了真正的降本增效。

[原文] [Lazar]: This is the first mind mindset shift that I want to put into people's minds right if you just have a vague idea let that be your first version of the project open cursor lovable whatever it is that you're using and just input a brain dump prompt right just talk into it lovable specifically I don't know about the other tools has a really cool voice function you click it you just dictate the hell of it and just press send right don't even wait for it to finish open a new window again lable.dev

[译文] [Lazar]: 这是我想植入大家脑海中的第一个思维转变。如果你只有一个模糊的想法，就把那当作你项目的第一个版本。打开 Cursor、Lovable 或你正在使用的任何工具，直接输入一个“脑暴提示词”（Brain Dump Prompt）。只要对着它说话就行——Lovable 尤其如此，我不确定其他工具怎么样，但它有一个非常酷的语音功能。你点击它，拼命口述你的想法，然后点击发送。别等它完成，直接打开一个新窗口，再次进入 Lovable.dev。

[原文] [Lazar]: in here you're like "Okay as I was brain dumping I think I found a good thread right i think things are getting clearer so let me start another project now with more clarity more deliverability like I know which features I want which pages I want maybe I can even find a good reference maybe I can go on Maven maybe I can go on dribble maybe I can go wherever get a good screenshot get a good animation and attach it because most of these tools accept files as a part of the input"

[译文] [Lazar]: 在这里你会想：“好吧，刚才脑暴的时候，我觉得我找到了一个好的思路，事情变得更清晰了。所以现在让我开启另一个项目，这次要有更高的清晰度和可交付性。”比如我知道我想要哪些功能、哪些页面。也许我还能找到一个好的参考，去 Maven、去 Dribble 或者任何地方，截一张好的图，找一个好的动画，然后把它附上去，因为大多数这类工具都接受文件作为输入的一部分。

[原文] [Lazar]: so that's your second project started now things are even more clear now you you you expose yourself to quality and now you're like well what if I what if I found a template that actually is already out there why reinventing the wheel i'm building a platform that somebody else built why not expose AI to what quality looks like right so what I'll do is I I'll go to and find a library 21st dev or uh um or a build or like whatever places which allow me not to export screenshots but export code snippets because guess what even though English is the number one programming language Lovable and all other tools still communicate in code the best if you want to get pixel perfect results just give them code it will it will interpret it better than your English or Spanish or whatever language that you use

[译文] [Lazar]: 这是你启动的第二个项目（注：此处逻辑上指代带参考图的版本，实为并行中的第三条线）。现在情况更清晰了，你接触到了高质量的内容。你会想：“如果我能找到一个现成的模板呢？为什么要重新造轮子？”我在构建一个别人已经建过的平台，为什么不向 AI 展示高质量的代码长什么样？所以我会去像 21st.dev 或者其他地方，找一个允许我导出“代码片段”而不是截图的库。因为你猜怎么着？虽然英语是第一编程语言，但 Lovable 和所有其他工具仍然是用代码交流得最好。如果你想得到像素级完美的结果，直接给它们代码，它的解读能力会比解读你的英语、西班牙语或任何语言都要好。

[原文] [Lazar]: So that's the third way you're like "Okay now I'm even more deliberate i'm not I'm not even uh uh going as as wide as like giving it vague concepts i'm giving it code snippets like I want this exact design i want this exact type of functionality." So that's your third project and then by the time you do all of these three you're already at a level of clarity that you wouldn't have if you just sat with a an empty piece of paper or maybe a maybe chatting just with Chad GPT but not taking action

[译文] [Lazar]: 所以那是第三种方式（注：指代码模板法）。你会想：“好，现在我更加深思熟虑了。我甚至不再给出模糊的概念，我直接给它代码片段，告诉它‘我想要这个确切的设计，我想要这个确切的功能类型’。”这是你的第三个项目。当你把这三件事都做了，你所达到的清晰度，是你仅仅对着一张白纸，或者只和 ChatGPT 聊天而不采取行动所无法比拟的。

[原文] [Lazar]: you're going to get three four five six different concepts that you can compare as you're comparing them clarity just keeps coming like and things get better and better to understand and you're also solving for one big problem that you mentioned you used the term AI slop and I like it because a lot of people when they say AI slop they don't refer the uh beautifying the code but beautifying the design right this process that I just mentioned actually gives you four or five different design options and in the long run save you massive amounts of credits because a lot of people obsess over the concept of oh when I give them this this hack they're like oh but that doesn't that cost more i'm like yes upfront it may cost a little bit more in the long run if you really want to finish this project you're actually saving hundreds of credits and maybe even hundreds of dollars not to mention the amount of days simply because you started from a point of better clarity and better refinement process right

[译文] [Lazar]: 你会得到三、四、五、六个不同的概念方案供你比较。在比较的过程中，清晰度会源源不断地涌现，事情变得越来越好理解。而且这也解决了你提到的一个大问题——你用了“AI Slop”（AI 垃圾/劣质品）这个词，我很喜欢，因为很多人说 AI Slop 时指的不是代码的美化，而是设计的美化。我刚才提到的这个过程实际上给了你四五种不同的设计选项。从长远来看，这为你节省了大量的积分（Credits）。很多人纠结于这个技巧，他们会说：“噢，但这难道不会花更多钱吗？”我会说：“是的，前期可能会多花一点点，但如果你真的想完成这个项目，从长远来看，你实际上节省了数百个积分，甚至数百美元，更不用说节省的时间了，仅仅因为你是从一个更清晰、更精炼的起点开始的。”

[原文] [Lenny]: someone may think okay of course you're just getting us to spend all these lovable tokens This is what a lovable person would tell me but I what I'm feeling is this is where you could save the most money because if you get it correct in the beginning you save so much work trying to get it back to where you want it to go a million% that I'm actually saving people like I'm I'm actually going against what I should be saying if I was thinking about lovables I would be like "No no just try to fix it in perpetuity." But that's not We're not in business of doing that

[译文] [Lenny]: 有人可能会想：“好吧，你当然想让我们花光这些 Lovable Token，这是 Lovable 的人才会说的话。”但我感觉到的是，这才是你最能省钱的地方。因为如果你一开始就做对了，你就省去了后面为了把它拉回正轨而做的海量工作。

[Lazar]: 一百万个百分点的同意。我实际上是在帮大家省钱。如果我只为 Lovable 考虑，我应该说：“不不不，就在那个错误的版本上修一辈子吧。”但我实际上是在反其道而行之。因为我们不是做那种生意的。

章节 5：核心工作流（二）：文档驱动与上下文管理（PRD与MD文件）

📝 本节摘要：

在确定了项目原型（“获胜者”）后，Lazar 强调必须停止漫无目的的“Vibing”，转而进入严谨的工程化管理阶段。他详细介绍了一套由 AI 生成的文档体系，包括总蓝图（Master Plan）、实施计划（Implementation Plan）、设计规范（Design Guidelines）、用户旅程（User Journeys）以及核心的任务列表（Tasks.md）。通过将这些 Markdown 文件作为“真理之源”投喂给 AI，并在规则文件（Rules.md）中强制 AI 先读文档再行动，他有效地解决了上下文丢失的问题，将 AI 从一个仅仅听从指令的执行者变成了具备全局视野的“技术联合创始人”。

[原文] [Lazar]: after you you've built hundreds of projects like I did like you you you see the winner like the winner is so obvious it's not even a competition you maybe do one or more two prompts to calibrate it and when you're like "Okay the winner is here." At that point I either ask the tool that I'm using or I'll maybe let's say go to Chad GPT or whatever and ask the LLM to produce a series of PRDs what PRDs are for again people that are not familiar with the terms they're are project requirements documents or for me I call them like sources of truth

[译文] [Lazar]: 在你像我一样构建了数百个项目之后，你能一眼看出哪个是“获胜者”。胜者是如此明显，甚至不需要竞争。你可能再用一两个提示词微调一下，当你觉得“好，就是它了”的时候，我会要求我正在使用的工具，或者去 ChatGPT 之类的地方，让 LLM 生成一系列 PRD。对于不熟悉这个术语的人来说，PRD 就是“产品需求文档”，或者我称之为“真理之源”（Sources of Truth）。

[原文] [Lazar]: right what what needs to be true for this project to be successful from a couple of perspectives I usually build something that I call a master plan it's basically a compass saying here's what we're building right it's like talking to a human I really treat loable like a human being so it's like this is what we're building

[译文] [Lazar]: 对，就是从几个不同的角度来看，这个项目要成功必须满足哪些条件。我通常会建立一个我称之为“总蓝图”（Master Plan）的文档。它基本上就是一个指南针，说明“这就是我们要构建的东西”。这就像在和人说话，我真的把 Lovable 当作一个人来看待，所以这就像是在告诉它：这就是我们要造的东西。

[原文] [Lazar]: then I build an implementation plan which is this is how we are going build it in this is the sequence right it's very important to me again going back to quality taste human nature i need to define because I'm still working with a system that is not emotionally intelligent yet i need to define how I want the app to look and feel so another PRD that I build is design guidelines and then finally something that just circles it all around which is like okay when we know how things look and when we know how we're building it how does the user journey look like

[译文] [Lazar]: 然后我会建立一个“实施计划”（Implementation Plan），即“我们将如何构建它，顺序是怎样的”。这对我非常重要。再次回到质量、品味和人性的話題，因为我合作的系统目前还不具备情感智能，所以我需要定义我希望这个 App 看起来和感觉起来是怎样的。所以我建立的另一个 PRD 是“设计规范”（Design Guidelines）。最后是一个把所有东西串联起来的文档，即：既然我们知道了它长什么样，也知道了怎么构建，那么“用户旅程”（User Journey）是怎样的？

[原文] [Lazar]: when I'm done doing that I build one final document which I call either plan MD or tasks.md and MD part is um uh you know uh markdown basically I'm just using markdown format because I've learned that AI likes to read markdown and what that serves is it serves as a source of truth on like actual tasks and subtasks that it will need to execute to get to the finish line right

[译文] [Lazar]: 当我做完这些，我会建立最后一个文档，我称之为 plan.md 或者 tasks.md（任务列表）。MD 指的是 Markdown 格式，我用它是因为我发现 AI 喜欢阅读 Markdown。这个文档的作用是作为“真理之源”，列出它为了到达终点线所需执行的实际任务和子任务。

[原文] [Lazar]: and then there's the final final layer which is depending on what tool you use cloud code or or or cursor have what's known as rules.md or agent.md what you're basically doing with rules or agent files is you're letting the agent know how you want it to behave and what it should focus on in the long run so that you don't have to repeat yourself with every prompt

[译文] [Lazar]: 然后还有最后、最后的一层，取决于你用什么工具——Claude Code 或者 Cursor 都有所谓的 rules.md（规则文件）或者 agent.md。用这些规则或 Agent 文件，你基本上是在告诉 Agent 你希望它如何表现，以及从长远来看它应该关注什么，这样你就不用在每次提示时都重复自己。

[原文] [Lazar]: right so in lovable there's a there's a separate menu for that in your project settings where you can define project uh knowledge and usually what I'll say hey read all the files before you do anything like don't do anything before you read all the prds read tasks.mmd to see which task is next then execute on that next next set of tasks and when you're done tell me what you did and how I should test it

[译文] [Lazar]: 在 Lovable 里，项目设置中有一个单独的菜单可以定义“项目知识”（Project Knowledge）。通常我会说：“嘿，在做任何事之前先阅读所有文件。在读完所有 PRD 之前别动手。阅读 tasks.md 看看下一个任务是什么，然后执行那一组任务。当你完成后，告诉我你做了什么，以及我该如何测试它。”

[原文] [Lazar]: I would literally go to chat GPT as I said and brain dump into it in my just type lovable GPT uh lovable PRD generator you'll see my name there right and and and that I'm the author go in brain dump it will ask you a couple of questions to get clarity and just produce four files for you and you can just go ahead and and upload those

[译文] [Lazar]: 实际上，我会去 ChatGPT，正如我所说，把我的想法“倾倒”（brain dump）进去。直接输入 "Lovable GPT" 或 "Lovable PRD Generator"，你会看到我的名字，我是作者。进去后，把你脑子里的东西倒出来，它会问你几个问题以明确需求，然后直接为你生成这四个文件，你就可以直接上传了。

章节 6：实战技巧：四步调试法与自我进化

📝 本节摘要：

这一节是关于当 AI 生成的代码出错（Bug）时的实战应对指南。Lazar 提出了一个名为“4x4”的调试框架：1. 使用工具自带的“尝试修复”按钮；2. 查看控制台日志（Console Log）以增加“感知层”；3. 引入外部“顾问”（如 Codex 或 Claude）进行代码审查；4. 承认是自己的提示词问题，回滚版本并重试。最关键的一步发生在问题解决后：他会反问 AI “我该如何改进提示词”，并将这些教训写入 rules.md，从而实现系统的自我进化。

[原文] [Lazar]: no matter how good of a plan you have in place you're going to run into problems eventually and I have like a small little framework that I call 4x4 just again analogies right 4x4 if you if you have it on your car you're going to get yourself out of the mud much easier than than uh the other way around

[译文] [Lazar]: 无论你的计划有多完美，你最终都会遇到问题。所以我有一个我称之为“4x4”的小框架。再次借用比喻，如果你车上有 4x4（四轮驱动），你从泥潭里脱困就要比没有容易得多。

[原文] [Lazar]: four different ways to debug attempt one of each only once... first one is again every tool is different i'll I'll reference Lovable's workflow... when something breaks Lovable's agent is smart enough to say hey I made a mistake... and uh have this little button usually which is uh called try to fix so you agent basically admits it made a mistake you click on a button and most times when it's a smaller issue it corrects the course fixes it no problem

[译文] [Lazar]: 四种不同的调试方法，每种只尝试一次……第一种，虽然每个工具不同，但我以 Lovable 的工作流为例。当东西坏了，Lovable 的 Agent 足够聪明，会说“嘿，我犯了个错”，通常会有一个叫“尝试修复”（Try to fix）的小按钮。Agent 基本上承认了错误，你点击按钮，大多数时候如果是小问题，它会修正路线并解决掉，没问题。

[原文] [Lazar]: there comes the second part which is okay I need to bring the awareness layer and what I do there is I go and very simply open the preview sandbox dev environment of my app whatever try to run the the the function that's broken rightclick read the console log... or you can prompt any tool and say hey I don't think you're seeing the problem so instead of me yelling at you let's find it together... i want you to write console logs in relevant files so that we can monitor every step along the way

[译文] [Lazar]: 然后是第二部分，即“好吧，我需要引入‘感知层’（Awareness Layer）”。我会做的是非常简单地打开我的 App 的预览沙盒或开发环境，尝试运行那个坏掉的功能，右键点击，阅读控制台日志（Console Log）……或者你可以提示任何工具说：“嘿，我觉得你没看到问题所在，与其我对你大吼大叫，不如我们一起找找。我要你在相关文件中写入控制台日志，这样我们可以监控沿途的每一步。”

[原文] [Lazar]: but then there are situations when even that's not sufficient so you're like okay I need to go even deeper and that's where like code reviews and evaluations come into play my go-to tool today for that is codeex openai... I'm like in the first try as if you remember like I used the tool and I was like total vibes... In the third one I'm using an external tool as a facilitator which is like I'll either connect to codeex and chat with codeex to then fix the problem in lovable

[译文] [Lazar]: 但有些情况连这也解决不了，你会想：“好吧，我需要更深入。”这时候代码审查和评估就派上用场了。我今天首选的工具是 OpenAI 的 Codex。在第一步尝试中，如果你还记得，我是完全凭感觉（Vibes）依赖工具本身……在第三步中，我使用外部工具作为协作者，比如我会连接到 Codex 并与它聊天，然后再回到 Lovable 去修复问题。

[原文] [Lazar]: and then the fourth one is is usually the best one because of the time when there are problems it's my fault like no matter how your ego is big guys that you're watching this it's your fault trust me you had a bad prompt... you go and say "Okay I tried these three things i'm just going to take three steps back and I'm going to think about my prompt a little bit more take a couple breaths go for a walk have some coffee come back with a clear mind and try again."

[译文] [Lazar]: 第四种通常是最好的一种，因为当出现问题时，通常是我的错。不管你们的自尊心有多强，正在看这个视频的朋友们，相信我，这就是你的错，是你写了个烂提示词……你会说：“好吧，我试了那三件事都不行，我要后退三步，再多思考一下我的提示词，深呼吸几次，去散个步，喝杯咖啡，以此清醒的头脑回来再试一次。”

[原文] [Lazar]: and then I do the final thing which is this and this is the key one actually when the problem gets fixed I go into the chat mode and I and I ask Lola i say "Okay I needed to do four different things to fix this how can you help me learn how to prompt you better so that next time I have a problem we do it in one go?"

[译文] [Lazar]: 然后我会做最后也是最关键的一件事。当问题被修复后，我会进入聊天模式问 Lovable：“好吧，我刚才得做四件不同的事才修好这个。你能不能帮我学习如何更好地向你提提示词，这样下次遇到问题时我们可以一次搞定？”

[原文] [Lazar]: once you go through this conversation you're like "Okay let me eliminate myself again completely out of the equation cuz I won't remember to prompt you better two days from now." Put this into rules put this what we just learned into rules.mmd because I I'm making you read the rules every time anyways so you might as well just record it there

[译文] [Lazar]: 一旦你进行了这段对话，你会想：“好吧，让我再次把自己完全排除在等式之外，因为两天后我肯定记不住要怎么更好地提示你。”把这个写入规则，把我们刚学到的东西写入 rules.md。因为反正我每次都让你读规则，你不妨直接把它记录在那里。

章节 7：技能演变：从代码转向审美与判断力

📝 本节摘要：

在本节中，Lazar 指出 AI 将产品开发的底线提升到了“足够好”（Good Enough），因此未来的竞争核心在于如何创造“世界级”的魔法体验。他预言设计师将是继产品经理之后的下一个赢家，因为 AI 目前更擅长逻辑决策而非情感设计。他重申了“编程即书法”的观点，认为手动写代码将变成一种稀缺的艺术表演。最后，他建议构建者不要纠结于技术栈（如 React vs HTML），而应将时间投资在“接触时间”（Exposure Time）上——即通过大量阅览优秀设计来提升审美，因为在 AI 时代，制造垃圾和制造魔法的速度一样快，区别仅在于你的品味。

[原文] [Lazar]: in the old world um good enough was good enough right because even producing good enough was not easy right 10 years 15 years ago just producing was more than plenty more than good enough... but guess what the gap is now this because everybody produces good enough with AI absolutely everyone does it so now learning and optimizing for how do I produce worldclass and magic is the the key lesson

[译文] [Lazar]: 在旧世界里，“足够好”就已经足够好了，因为哪怕是产出“足够好”的东西也不容易，对吧？10 年或 15 年前，仅仅能把东西做出来就已经绰绰有余、非常不错了……但你猜现在的差距在哪里？因为有了 AI，每个人都能产出“足够好”的东西，绝对每个人都能做到。所以现在的关键一课是，学习并优化“我该如何产出世界级和魔法般的产品”。

[原文] [Lazar]: If I was a betting man as they say I I'd bet that the next class that wins are designers because we're training these tools to be more clear to be better to make better technical decisions i don't think we will train them just yet to be make better emotional decisions and I think design is all about emotion and that's where like the level up the skill up needs to come

[译文] [Lazar]: 如果我是个赌徒，正如俗话所说，我会打赌下一个赢家阶层是“设计师”。因为我们正在训练这些工具变得更清晰、更好，做出更好的技术决策，但我认为我们暂时还无法训练它们做出更好的“情感决策”。而我认为设计完全是关于情感的，这就是需要升级技能的地方。

[原文] [Lazar]: coding is going to be like calligraphy you writing code is going to be the equivalent of like you write you fine printing like on a on a canvas and people oh my god you wrote that code that's so amazing it's going to be so rare that it's going to become an art right it's not going to be it's going to be commoditized completely like it it already is in a sense

[译文] [Lazar]: 编程将会变得像书法一样。你亲手写代码将等同于你在画布上进行精美的书写，人们会惊叹：“天哪，那是你亲手写的代码？太神了！”这种技能会变得非常稀缺，以至于它将演变成一种艺术形式。它不再是必需品，它将被完全商品化——从某种意义上说，现在已经是了。

[原文] [Lazar]: text tag doesn't matter anymore right it doesn't matter like people obsess over oh is this written in HTML is this written in React it doesn't matter like it never matter but now matters even less the end user just wants a stellar experience

[译文] [Lazar]: 技术栈（Text tag，原文口误应为 Tech stack）不再重要了，对吧？真的不重要。人们纠结于“噢，这是用 HTML 写的吗？这是用 React 写的吗？”这不重要。以前就不重要，现在更不重要了。终端用户只想要一个星级般的卓越体验。

[原文] [Lazar]: the best way to level up exposure time set aside more time on learning than building read the agent output learn how it's thinking so that you know what's possible but then also go and get inspired follow good designers on X find tools where great designs are produced and follow their creators

[译文] [Lazar]: 升级的最佳方式是“接触时间”（Exposure Time）。留出比构建更多的时间去学习。阅读 Agent 的输出，学习它是如何思考的，这样你就知道什么是可能的。然后去寻找灵感，在 X（推特）上关注优秀的设计师，找到那些能产出伟大设计的工具，并关注它们的创作者。

[原文] [Lazar]: because you can code fast but you can code garbage fast as well as magic fast it's the same amount of time it's you and your input that matters forget about decisions on tech stack forget about which backend are you using which front end are you using that doesn't matter quality taste design that's all you need to optimize for in the future that's ahead of us

[译文] [Lazar]: 因为你可以编码得很快，但你制造垃圾的速度和制造魔法的速度是一样快的，花费的时间也一样。关键在于你和你的输入。忘掉关于技术栈的决策，忘掉你用什么后端、什么前端，那都不重要。质量、品味、设计——这就是你在未来的道路上唯一需要优化的东西。

章节 8：职业路径：如何在 AI 时代构建未来

📝 本节摘要：

在这最后一章中，Lazar 分享了他非线性的职业道路，将其比作电影《贫民窟的百万富翁》——从林业工程师到服务员，每一段看似无关的经历都为此刻做好了准备。他建议有志成为 Vibe Coder 的人首先要“雇佣自己”，通过公开构建（Building in Public）和无保留地分享知识来建立声誉。他揭示了一个求职秘诀：不要发简历，而是发送一个用该公司工具构建的 App。最后，他呼吁听众克服恐惧，从消费者转变为构建者，因为在 AI 时代，技术栈已不再重要，重要的是你创造魔法般体验的品味与行动力。

[原文] [Lazar]: well my personal path and personal journey was anything but linear like I I've done so many things in in life like um blue collar jobs looked at even at subway while I was studying and stuff like that like um I'm I'm an engineer by trade but not a software engineer i'm a forestry engineer so no coding but still engineering is engineering I feel you still develop certain set of skills doing that

[译文] [Lazar]: 嗯，我的个人路径和旅程绝不是线性的。我在生活中做过很多事情，比如蓝领工作，上学时甚至在赛百味（Subway）打过工之类的。我也算是个工程师，但不是软件工程师，我是林业工程师，所以完全不写代码。但这依然是工程学，我觉得你在做这些事时仍然开发了一套特定的技能。

[原文] [Lazar]: I waited tables a long time so you develop some human skills you understand what people like what they don't like right I've again blue collar jobs like teach you hard work and like it's as I said the path was not linear but I feel almost like a slum dog millionaire the movie storyline which is like everything that happens to the character brings them into a position to be able to answer the qu the questions in the in the quiz better

[译文] [Lazar]: 我当了很久的服务员，所以开发了一些人际交往技能，你能理解人们喜欢什么、不喜欢什么。正如我所说，蓝领工作教会了你努力工作。虽然路径不是线性的，但我感觉这就像电影《贫民窟的百万富翁》的情节：角色经历的所有事情，都让他处于一个能够更好地回答测验问题的位置。

[原文] [Lazar]: well for me I feel like it became a job by building in public... I was building in public and sharing I as I said I made a YouTube channel and I I shared all the failures and all the knowledge all the projects that I was building i used social media a lot like LinkedIn was my go-to

[译文] [Lazar]: 对我来说，我觉得这份工作是通过“公开构建”（Building in Public）得来的……我在公开构建并分享。正如我所说，我做了一个 YouTube 频道，分享所有的失败、所有的知识以及我正在构建的所有项目。我大量使用社交媒体，LinkedIn 是我的首选。

[原文] [Lazar]: give away all the secrets like there are no secrets whatsoever uh if you're sitting on a good concept you're missing out let's just share it immediately if you figure something out

[译文] [Lazar]: 把所有的秘密都送出去吧，根本没有什么秘密可言。如果你抱着一个好的概念不放，你就在错失良机。如果你弄懂了什么东西，就立刻分享它。

[原文] [Lazar]: I've seen people do something i'm going to give people a secret away a couple of hires stood up by not sending resumes but sending lovable apps they built lovable apps to show what they're why they're good fit for a role and we as lovable employees will always open an app that uses lovable.appd domain always if you send me a DM send me a lovable app don't send me anything long send me an app that tells me what what you want from me or how do you see us collaborating and working together right

[译文] [Lazar]: 我看到有人做了一件事——我要告诉大家一个秘密——有几个应聘者脱颖而出，不是因为发了简历，而是因为发了 Lovable App。他们构建了 Lovable App 来展示为什么他们适合这个职位。作为 Lovable 的员工，如果你发给我一个使用 lovable.app域名的 App，我永远都会打开看。如果你给我发私信，发给我一个 Lovable App，别发长篇大论。发给我一个 App，告诉我你想要什么，或者你觉得我们可以如何合作。

[原文] [Lazar]: you don't need a company to hire you you can hire yourself as a professional vibeer first i think the reason why it I clicked with Anton and with Elena and with everyone else because I was already doing it like all all I did I just changed the the the the vehicle but I was already doing it professionally before I got hired

[译文] [Lazar]: 你不需要一家公司来雇佣你，你可以先雇佣自己成为一名专业的 Vibe Coder。我认为我和 Anton、Elena 以及其他人一拍即合的原因是，我已经那样做了。我所做的只是换了个载体，但在被雇佣之前，我已经是在专业地做这件事了。

[原文] [Lazar]: anybody that's scared like just try it it switches from fear to excitement immediately because then you see what's possible firsthand just go in build something build anything and the the fear goes away you should only be afraid if you're doing nothing if you're doing absolutely nothing yes be terrified by all means be terrified and then take a step towards doing something about it

[译文] [Lazar]: 任何感到害怕的人，只要试一试就好。这种感觉会立刻从恐惧转变为兴奋，因为你会亲眼看到什么是可能的。进去构建点什么，构建任何东西，恐惧就会消失。只有当你什么都不做时，你才应该感到害怕。如果你绝对什么都不做，是的，务必感到恐惧，然后迈出一步去改变它。

[原文] [Lazar]: text tag doesn't matter anymore right it doesn't matter like people obsess over oh is this written in HTML is this written in React it doesn't matter like it never matter but now matters even less the end user just wants a stellar experience

[译文] [Lazar]: 技术栈（注：原文 Text tag 为 Tech stack 口误）不再重要了，对吧？真的不重要。人们纠结于“噢，这是用 HTML 写的吗？这是用 React 写的吗？”这不重要。以前就不重要，现在更不重要了。终端用户只想要一个星级般的卓越体验。

[原文] [Lazar]: forget about decisions on tech stack forget about which backend are you using which front end are you using that doesn't matter quality taste design that's all you need to optimize for in the future that's ahead of us

[译文] [Lazar]: 忘掉关于技术栈的决策，忘掉你用什么后端、什么前端，那都不重要。质量、品味、设计——这就是你在未来的道路上唯一需要优化的东西。