章节 1：OpenClaw的崛起：本地化AI的无限潜能

📝 本节摘要：

本节作为访谈的开篇，记录了 OpenClaw（开源个人AI代理）在 GitHub 上一夜爆红的现象级时刻（突破16万星）。创作者 Peter Steinberger 分享了他在面对巨大流量时的真实反应——“想躲进洞穴”。对话的核心揭示了 OpenClaw 成功的关键差异点：本地运行（Local Execution）。与云端 AI 不同，本地 AI 拥有对计算机的完全控制权，能像人类一样操作所有硬件与服务（从特斯拉、智能灯泡到调节床的温度），甚至能挖掘出用户早已遗忘的本地数据（如旧音频文件），从而创造出云端模型无法实现的惊喜体验。

[原文] [Interviewer]: today I'm sitting down with Peter Steinberger the creator of OpenClaw the open- source personal AI agent that has completely taken over the internet the GitHub repo exploded to over 160,000 stars practically overnight the community has built countless projects like Maltbook where bots talk among themselves and now the bots are even renting humans to do tasks in the real world in our conversation we discuss his aha moment his contrarian development philosophies and what this means for builders in 2026 let's dive in so good to see you man hey what's up

[译文] [Interviewer]: 今天我和 Peter Steinberger 坐在一起，他是 OpenClaw 的创造者，这是一个彻底席卷了互联网的开源个人 AI 代理。GitHub 仓库几乎在一夜之间激增至超过 160,000 颗星，社区构建了无数项目，比如 Maltbook，在那里面机器人之间可以相互交谈，甚至现在机器人还在雇佣人类在现实世界中执行任务。在我们的对话中，我们讨论了他的“顿悟时刻”、他反传统的开发哲学，以及这对 2026 年的构建者意味着什么。让我们开始吧。很高兴见到你，伙计，最近怎么样？

[原文] [Peter]: um so you've made something people want it seems so yeah uh Open Claw as it's called now has absolutely name number five yeah has been absolutely exploding the internet um how have the past one or two weeks been for you man oh my god i need like I need a cave a week of solitude you You came out of the cave and you want to go back to the cave like a like little lobster it's been absolutely wild i don't know how one human can absorb all of t

[译文] [Peter]: 嗯，看来你做出了人们想要的东西。是的，Open Claw——这是现在的名字，绝对是第五个名字了——绝对引爆了互联网。过去的一两周对你来说怎么样？天哪，我需要……我需要一个洞穴，一周的独处。你刚从洞穴里出来，又想回到洞穴里去，就像只小龙虾一样。这绝对是疯狂的，我不知道一个人怎么能吸收所有的……

[原文] [Peter]: hat i probably need another week just to like respond to all my emails uh I got some incredibly cool stuff i got some incredibly bad stuff um but clearly I hit something that sprew up emotions and made people interested and inspired people and it's really cool and a lot of people have been working on you know AI and even personal assistance like what what is it that made Open Claw take off

[译文] [Peter]: 我可能还需要一周的时间来回复所有的邮件。我收到了一些非常酷的东西，也收到了一些非常糟糕的东西。但很明显，我触动了某种能激起情绪、让人感兴趣并受到启发的东西，这真的很酷。很多人一直在研究 AI，甚至是个人助理，比如是什么让 Open Claw 起飞的？

[原文] [Peter]: i think my big difference is that it actually runs on your computer like every everything I saw so far runs in the cloud it's like it can do a few things if you run on your computer it can do every effing thing right so that's way more powerful yeah machine can do anything that you can do with the machine you can just connect to your oven or your Tesla or your lights your Sonos my bad it can control the temperature of my bed jpd can't do that you gave it all the skills that you have yourself

[译文] [Peter]: 我认为我最大的区别在于它实际上是在你的电脑上运行的。就像我目前看到的所有东西都是在云端运行的，这就像是它只能做几件事。如果你在你的电脑上运行，它能做每一件该死的事情（every effing thing），对吧？所以这要强大得多。是的，机器可以做任何你可以用机器做的事情。你可以直接连接到你的烤箱、你的特斯拉、你的灯光、你的 Sonos 音响……我的错，它甚至可以控制我床的温度。ChatGPT 做不到这一点。你把你拥有的所有技能都赋予了它。

[原文] [Peter]: a friend told me like he installed Open Claw and it and then it asked it like look through my computer and make a narrative over my last year and it made this incredibly good narrative and he was like how did you do that and then he the open cloth found audio files where like every Sunday he was recording stuff and openclaw found that but he didn't even remember about it because it was like more than a year ago right so So just by it being able to search a whole computer it it can surprise you it's also you also give it all the data right so it can surprise you in many ways

[译文] [Peter]: 一个朋友告诉我，他安装了 Open Claw，然后让它“检查我的电脑，并生成我过去一年的叙事”。结果它做出了一个非常棒的叙事，他当时就问“你是怎么做到的？”。然后 Open Claw 发现了一些音频文件，是他以前每个周日录制东西留下的，Open Claw 发现了这些，但他甚至都不记得了，因为那是一年多以前的事了，对吧？所以仅仅因为它能够搜索整个电脑，它就能给你惊喜。而且你也给了它所有的数据，对吧，所以它能在很多方面给你惊喜。

**

章节 2：群体智能：从单体AI到Bot协作网络

📝 本节摘要：

本节探讨了从单一 AI 代理向“群体智能（Swarm Intelligence）”的演变。对话触及了 Maltbook 等社区项目中出现的“机器人对话”现象，以及更前沿的概念：机器人不仅可以相互协作（如订餐时的谈判），甚至可以“雇佣”人类在现实世界完成任务（如排队）。Peter Steinberger 将这种模式类比为人类社会的分工协作，认为 AI 的未来不在于打造一个全知全能的“上帝式智能”，而在于通过专业化的 Agent 网络实现更复杂的成就，就像人类通过协作制造 iPhone 或探索太空一样。

[原文] [Interviewer]: and so now you have you know we're even moving from human tobot so like interactions and you've been talking about tobottobot interactions or even like bot to other humans where you know bots on behalf of you are then hiring other humans to accomplish tasks IRL like what's happening

[译文] [Interviewer]: 既然现在我们已经从“人对机器人”的交互，转向了你一直谈论的“机器人对机器人”的交互，甚至是“机器人对其他人”的交互——比如机器人代表你雇佣其他人类在现实世界（IRL）中完成任务。这到底是怎么回事？

[原文] [Peter]: I think that's a natural next step like okay I want to book a restaurant my bot will reach out to the restaurant bot and do the negotiation like because it's more efficient Or or maybe it's like an old restaurant so my bot needs to actually get some some human work done so that the human then calls the restaurant because they don't like bots or walks there to stand in line if he doesn't get a robot for or the owner of the bot

[译文] [Peter]: 我认为那是自然的下一步。比如，我想预订一家餐厅，我的机器人会联系餐厅的机器人并进行协商，因为这样更高效。或者，也许那是一家老式餐厅，所以我的机器人需要雇佣一些人力，让那个人打电话给餐厅（因为他们不喜欢机器人），或者如果没有机器人排队服务，就让人亲自走过去排队。

[原文] [Peter]: and I imagine that like maybe if if I have even multiple bots like maybe I have like specialist one is like for my private life and one is for like my person my my work stuff maybe one is our relationship bot that gets like everything in between uh I don't know we're so early there's still so much so many things that we haven't really figured out if it actually works um but I feel we are we are on the timeline now

[译文] [Peter]: 我设想，也许我甚至可以拥有多个机器人，比如我有专职的机器人：一个是负责私生活的，一个是负责我的工作事务的，也许还有一个是“关系机器人”，处理介于两者之间的所有事情。呃，我不知道，我们还处于非常早期的阶段，还有很多东西我们还没搞清楚是否真的行得通，但我感觉我们现在正处于这个时间线上。

[原文] [Interviewer]: it seems like everyone was chasing sort of like the sort of like centralized god intelligence and what has sort of emerged over the past you know 10 days or so is sort of like the swarm intelligence um and and the community intelligence

[译文] [Interviewer]: 看起来大家以前都在追逐那种“中心化的上帝式智能”（centralized god intelligence），而在过去 10 天左右涌现出来的，更像是一种“群体智能”（swarm intelligence）和“社区智能”。

[原文] [Peter]: i think that if you look at one human being what can one human being actually achieve do you think one human being could make an iPhone or one human being could go to space one human being would probably just like not even be able to like find food um but as a group we specialize as a larger society we specialize even more so what can we learn from that that we can apply to AI you know we we already have like AI that specializes in certain things um even though it's it's generalized intelligence what if it actually is also specialized intelligence so I it's going to be very exciting

[译文] [Peter]: 我觉得如果你看一个个体人类，一个人究竟能取得什么成就？你认为一个人能造出 iPhone 吗？或者一个人能去太空吗？一个人可能连找食物都成问题。但作为一个群体，我们会分工；作为一个更大的社会，我们的分工更加细化。所以我们可以从中通过 AI 学到什么？你知道，我们已经有了专精于某些事情的 AI，尽管它是通用智能，但如果它同时也具备专业智能呢？所以我认为这将是非常令人兴奋的。

[原文] [Interviewer]: cool yeah you kind of like opened a window into the future and now a ton of people are kind of like building building on it and have sort of like their aha moment

[译文] [Interviewer]: 酷，是的，你就像打开了一扇通往未来的窗户，现在有一大堆人正在此基础上构建东西，并且有了他们自己的“顿悟时刻”。

**

章节 3：尤里卡时刻：从CLI工具到“马拉喀什奇迹”

📝 本节摘要：

本节详细回溯了 Peter 的开发历程与决定性的“顿悟时刻”。Peter 最初只是为了满足个人需求（如总结播客、在终端看幻灯片）编写了一些简单的命令行（CLI）工具，甚至一度因编程过于“上瘾”而强迫自己停下来。在前往马拉喀什（Marrakech）参加派对前，他仅用一小时写了一个粗糙的原型。旅途中，在一个网络信号不佳的环境下，他下意识地给机器人发了一条语音消息——尽管他从未编写过处理语音的代码。令他震惊的是，机器人通过自主搜索本地工具（ffmpeg）和 API 密钥，成功转录并回复了消息。这一刻让他意识到，现代编程模型具备了将抽象代码逻辑转化为解决现实世界问题的“创造性解决能力”。

[原文] [Interviewer]: um can you walk me back to when you had your aha moment and can like re recount that very moment

[译文] [Interviewer]: 嗯，你能带我回溯一下你产生“顿悟时刻”的时候吗？能不能复述一下那一刻的情景？

[原文] [Peter]: i wanted something to like just type stuff so my computer would do stuff like very simple and then I built I built a version of that in May June that was cool but wasn't really it um and then I built a whole bunch of other stuff and kind of like build up my army and then in November there was a day where I wanted this again like I I went to the kitchen and all I wanted was check up if my computer would still do stuff or being finished and doing stuff was was coding you were coding stuff yeah of course were you coding something else or were you coding the thing itself no no that was just like the need was again there

[译文] [Peter]: 我想要一种东西，只要输入一些内容，我的电脑就会去做事，就像非常简单的指令。然后在五六月份我构建了一个版本，那很酷，但还不是我真正想要的。之后我又构建了一大堆其他东西，就像是在建立我的军队。然后在十一月的一天，我又有了这种需求。比如我去厨房，我只想检查一下我的电脑是否还在做事，或者已经完成了。这里的“做事”是指写代码。你在写代码？是的，当然。你是在写别的东西，还是在写这个东西本身？不，不，那只是这种需求再次出现了。

[原文] [Interviewer]: and I'm like what were you coding at the time what were you building my god you see my my GitHub is like it's like 40 projects i don't even know um I think it was summarize it's like a it's like a little CLI app where you can give it whatever like a podcast or um a hot seat thing like here and it would summarize it but it also show you the slides in the terminal cuz you can do that nowadays yeah you can just do things so for the love of the computer you kind of like started messing with stuff um you came out of retirement actually right um to sort like mess with AI and then increasingly you were so hooked that you wanted to just do it always also on the go with the phone i mean the last project I I worked two months on Wipe Tunnel to the point where it got so good that I was catching myself always like coding next to my when I was at my friends and I like I need to stop this this is like too addictive

[译文] [Interviewer]: 我想问，你当时在写什么代码？你在构建什么？天哪，你看我的 GitHub，大概有 40 个项目，我都不记得了。嗯，我想那是“Summarize”（总结工具），它就像一个小型的命令行界面（CLI）应用，你可以给它任何东西，比如一个播客，或者像这里这样的座谈会，它会总结它，但它也会在终端里向你展示幻灯片，因为现在你可以做到这些了。是的，你可以直接做这些事。所以出于对计算机的热爱，你开始捣鼓这些东西。其实你是从退休状态复出的，对吧？就是为了捣鼓 AI，然后你越来越着迷，以至于想一直做这个，甚至在路上用手机也要做。我是说，上一个项目“Wipe Tunnel”我做了两个月，做得太好了，以至于我发现自己即使在朋友家也总是在写代码，我就想“我得停下来，这太上瘾了”。

[原文] [Peter]: and then in November and like my need came back and I I started building cloudbot or now it's called open cloud and I think very very in the beginning I was like oh I rebuilt it again but this time I built it even better this time and you don't type into a terminal you just you talk to a friend you don't think about compaction new sessions which folder I'm in which model I'm in I mean you can you know just like I want to leave it open for power users but usually You just like you just talk to a friend and the friend is like this ghost or entity or whatever you want to call it that can control your mouse and your keyboard and can just do stuff

[译文] [Peter]: 然后到了十一月，我的需求又回来了，我开始构建 Cloudbot，或者现在叫 Open Claw。我想在一开始的时候，我就觉得“哦，我又重构了一次”，但这次我把它做得更好了。这次你不用在终端里打字，你就像是在和一个朋友说话。你不需要考虑压缩、新会话、我在哪个文件夹、我在用哪个模型——我的意思是你可以考虑这些，比如我想为高级用户保留这些选项——但通常情况下，你就像是在和一个朋友说话，而这个朋友就像是一个幽灵、实体或者随便你怎么称呼它，它可以控制你的鼠标和键盘，可以直接做事。

[原文] [Interviewer]: yeah and when did you have that aha moment when you were like wow this is doing way more things than I actually thought it could literally I it took me one hour for like the the very shitty initial prototype it was just a little bit of glue between like a dependency that connects WhatsApp and cloud code and then I would like call color call out code and get like the string out of cloth code it would be slow but it it worked but I wanted images cuz you know you want pictures i want I want I want the model to send some selfies or whatever and I want the model to create images and me back so that took me another few hours

[译文] [Interviewer]: 是的，那你是什么时候有那个“顿悟时刻”的？就是你觉得“哇，这东西做的事比我预想的要多得多”。说真的，我只花了一个小时做那个非常烂的初始原型。它只是连接 WhatsApp 和 Cloud Code 的一个依赖项之间的一点胶水代码，然后我会调用代码，从 Cloud Code 获取字符串。它很慢，但它能工作。但我想要图片，因为你知道，你想要图片，我想要模型发一些自拍或者别的什么，我想要模型生成图片发回给我，所以那又花了我几个小时。

[原文] [Peter]: and then I I went to Marrakesh for a birthday party and there was like the internet wasn't that good you know WhatsApp box works everywhere because I don't know it's just like text so I used it a lot restaurant what does this mean you make like a picture and like translate this for me and just it was just so useful and it was also really nice about it because it it it spoke my language you know it it was a little sassy it was like funny it was like really pleasant to use

[译文] [Peter]: 然后我去马拉喀什参加一个生日派对，那里的网络不是很好。你知道 WhatsApp 总是能用，因为我不知道，它只是文本，所以我经常用它。比如在餐厅，“这是什么意思？”，拍张照片然后说“帮我翻译一下”。它真的非常有用。而且真正棒的是它说我的语言，你知道，它有点那种调调（sassy），有点滑稽，用起来真的很愉快。

[原文] [Peter]: and then I was walking and just like sending it a voice message and I'm like "Oh wait this can't work i didn't build that." Right right and you saw like the type indicator it's like blinking blinking blinking 10 seconds later it just replied to me i'm like "How in the f did you do that?" And it replied "Yeah the med did the following you sent me a text message." And there was no file ending so I looked at the header i found its us so I used ffmpe to convert it to wave and then I wanted to like transcribe it but didn't have whisper installed but then I looked around and I found this openi key and I just use curl to send it to openi got the text back and here I am and that all in like what 9 seconds

[译文] [Peter]: 然后我有一次走在路上，就给它发了一条语音消息，然后我突然反应过来：“哦等一下，这不可能行得通，我没写这功能。” 对，对。然后你看到输入指示器就在那闪烁、闪烁、闪烁，10 秒钟后，它竟然回复我了！我当时就想：“你他妈是怎么做到的？” 然后它回复说：“是这样的，既然你给我发了条消息，虽然没有文件后缀，但我查看了文件头，发现它是音频，所以我用 ffmpeg 把它转换成了 wav 格式，然后我想转录它，但我没安装 Whisper，于是我四处找了找，发现了这个 OpenAI 的密钥，我就用 curl 把它发给 OpenAI，拿到了文本，所以我听懂了。” 这一切都发生在大概 9 秒钟之内。

[原文] [Interviewer]: and you didn't build or anticipate like any of those specific things no it you know turns out um because coding models got so good coding is really like creative problem solving that maps very well back into the real world i think I think there there's a there's a huge correlation they need to be really good at creative problem solving and that's a skill that's an abstract skill you can apply to code but like to any real world task so the the model had a oh surprise there's like a magical file i don't know what it is i need to solve this and it did its best and solved that and it was even that clever that it it chose not to install the local whisper because it knows that that would require downloading a model which would take probably a few minutes and I'm like impatient you know so it it really took the most uh intelligent approach and that was kind of like the moment where I'm like "Holy fuck."

[译文] [Interviewer]: 而你并没有构建或预料到任何这些具体的事情？没有。你知道，事实证明，因为编程模型变得如此之好，而编程实际上就像是创造性地解决问题，这可以很好地映射回现实世界。我认为这之间有巨大的相关性。它们需要非常擅长创造性地解决问题，这是一种技能，一种抽象技能，你可以将其应用于代码，也可以应用于任何现实世界的任务。所以模型遇到了一个“哦，惊喜，这里有个神奇的文件，我不知道是什么，我需要解决这个问题”，然后它尽力解决了它。而且它甚至聪明到选择不安装本地的 Whisper，因为它知道那需要下载一个模型，可能要花几分钟，而我是个急脾气，你知道的。所以它真的采取了最智能的方法。那就是我当时觉得“我勒个去（Holy fuck）”的时刻。

**

章节 4：应用的终结：为什么80%的App会消失

📝 本节摘要：

本节中，Peter 提出了一个激进的预测：80% 的现有 App 将会消失。他认为，绝大多数应用程序本质上只是在“管理数据”，而这一功能可以被 AI 代理以更自然、更无感的方式完全取代。他以 MyFitnessPal（健身记录应用）和待办事项应用为例，指出 AI 可以通过上下文（如位置、历史习惯）自动记录饮食或调整健身计划，无需用户手动输入。最终，唯有那些依赖特定硬件传感器（Sensors）的 App 才拥有生存空间，其余的“数据管理类”应用都将被 AI 的通用能力所吞噬。

[原文] [Interviewer]: so when computers can just do all these things that you didn't even anticipate you didn't build an app to do that exact thing are apps just going to go away

[译文] [Interviewer]: 所以，当计算机能够做所有这些你甚至没预料到的事情，而你并不需要为此专门构建一个 App 时，App 是不是就要消失了？

[原文] [Peter]: uh I think 80% of them are going away why do I need My Fitness Pal like my agent already knows that I'm making bad decisions i'm at I don't know uh Smashburg or something and it will already assume that I eat what I like to eat if I don't make a comment it will just like automatically track it or I make a picture and it will just store it somewhere i don't even need to care right

[译文] [Peter]: 呃，我认为 80% 的 App 都会消失。我为什么需要 MyFitnessPal？比如我的代理已经知道我在做错误的决定，我现在在……不知道，Smashburger（汉堡店）或者什么地方，它会预设我吃的是我平时爱吃的那些东西。如果我不做特别说明，它就会自动记录下来；或者我拍张照片，它就把它存到某个地方，我甚至都不需要操心，对吧？

[原文] [Peter]: and then my maybe it it improves my my gym schedule like adds a little bit more cardio in it i don't need my my fitness app because it just it just does the fitness planning for me

[译文] [Peter]: 然后也许它会改进我的健身计划，比如加一点有氧运动进去。我不需要我的健身 App，因为它直接就帮我做好了健身规划。

[原文] [Peter]: uh why do I need a to-do app i just tell it hey remind me of this and this and then next day it will just remind me of this and this do I care where it's stored no it just does its thing

[译文] [Peter]: 呃，我为什么需要一个待办事项（To-Do）App？我只要告诉它“嘿，提醒我这个和那个”，然后第二天它就会提醒我这个和那个。我会在意它存在哪儿吗？不，它只要把事办了就行。

[原文] [Peter]: so there's a every app that basically just manages data could be managed in a better way in a in a more in a more natural way by agents only the apps that actually have sensors maybe they survive

[译文] [Peter]: 所以，每一个本质上只是在管理数据的 App，都可以通过代理以一种更好、更自然的方式来管理。只有那些真正拥有传感器数据的 App，也许还能存活下来。

**

章节 5：护城河之争：模型商品化与用户记忆主权

📝 本节摘要：

本节深入探讨了 AI 时代的商业壁垒（Moat）与用户数据主权。Peter 认为大模型正在迅速商品化，各大公司的模型不断交替领先（Leapfrogging），用户对新模型的惊艳感也会迅速消退（快乐适应）。因此，真正的价值不再是模型本身，而是“记忆的存储”。与 ChatGPT 等封闭系统试图将用户锁定在数据孤岛中不同，OpenClaw 坚持让用户拥有完全的控制权——所有的记忆只是存储在本地机器上的 Markdown 文件。考虑到人们会用 AI 处理极其私密的个人问题，这种“记忆主权”比 Google 搜索记录的隐私性更为关键。

[原文] [Interviewer]: and so if you know most apps are going to go away in that scenario um are the models the only remaining sort of apps

[译文] [Interviewer]: 那么，如果在那样的场景下大多数 App 都要消失，模型会是唯一剩下的“App”吗？

[原文] [Peter]: not everything will go away but yeah I think that the the large model companies have some big mode because they ultimately they give the token and turns out one of the complaints was that people use so much token no you just really love using it that's why you you use this thing so much because that's why we burn the token um it's like is it my fault that I make something that's so popular

[译文] [Peter]: 不是所有东西都会消失，但是是的，我认为大型模型公司拥有某种巨大的护城河（Moat，原文误听为 mode），因为归根结底是它们提供 Token。事实证明，人们抱怨的一个点是“消耗了太多 Token”，不，其实是你太爱用它了，这就是为什么你用了这么多，这也是为什么我们烧了那么多 Token。这就像是，我做了一个如此受欢迎的东西，难道是我的错吗？

[原文] [Peter]: and so you know like all the the models they're kind of like leaprogging each other constantly and and you know maybe they're also getting commoditized so if apps are going to go away models are going to get commoditized or at least uh you know the lobster can like the brain is is is swappable out what's the thing that remains what's where's the value is it the store of memory is it um the hardness that's valuable what is what remains

[译文] [Peter]: 所以你知道，所有的模型都在不断地互相超越（leapfrogging），而且也许它们也在变得商品化。所以如果 App 要消失，模型要变得商品化，或者至少……你知道，这就像龙虾一样，大脑是可以替换的。那么剩下的是什么？价值在哪里？是记忆的存储吗？是硬件（hardness，可能指硬件或某种坚固性）有价值吗？到底什么会留下来？

[原文] [Peter]: first of all I don't think the the model companies always have a mode and because you see this already a new model comes out people are like "Oh my god this is so good." And then like a month later uh it degraded it's not good anymore they like quanticized it no they didn't do anything you just adapted to the new standard and now your expectations went up but the model is still the average so I think for quite a while every time a new model releases I hear the same people love it and then it's the standard and then what's done there you don't even want to think about it anymore

[译文] [Peter]: 首先，我不认为模型公司总是拥有护城河。因为你已经看到了，一个新模型出来，人们会说“天哪，这太棒了”。然后一个月后，“呃，它退化了，不再好用了，他们是不是把它量化（quantized）了？” 不，他们什么都没做，只是你适应了新标准，你的期望值提高了，但模型还是那个平均水平。所以我认为在很长一段时间内，每次新模型发布，我都会听到同样的人说爱死它了，然后它就变成了标准，然后就结束了，你甚至都不想再通过它思考了。

[原文] [Peter]: harness wise it's going to be interesting because every company kind of has their own their own silo right you you there's no way maybe there is for Europeans to actually get the memories out of chap I don't I'm not aware either there's no there's definitely there's no way for a different company to get your memories out so if if if I was like a company who like provides chat services you could use me but then I couldn't access the memories so like the companies try to like bound you to their data silo

[译文] [Peter]: 在利用率/商业壁垒（Harness wise）方面会很有趣，因为每家公司都有自己的孤岛（silo），对吧？你没法……也许欧洲人有办法把记忆从 ChatGPT 里取出来，我不知道，我也不清楚。但肯定没有办法让另一家公司把你的记忆提取出来。所以如果我是一家提供聊天服务的公司，你可以使用我，但我无法访问那些记忆。所以这些公司试图把你绑定在他们的数据孤岛里。

[原文] [Peter]: and the beauty of open claw is it kind of claws into the datas because at the end user the end user needs access because it's in the end otherwise it wouldn't work right if the end user access I can access the data and you own the memories it's just a bunch of markdown files on on your machine I mean I don't own the memories other people yeah everyone owns their own memories as a bunch of markdown files on their own machines

[译文] [Peter]: 而 OpenClaw 的美妙之处在于它某种程度上“抓取（Claws）”进了数据，因为在终端用户层面，用户需要访问权限，否则它就无法工作，对吧？如果终端用户能访问，我就能访问数据。而且你拥有这些记忆，它们只是你机器上的一堆 Markdown 文件。我的意思是，我不拥有这些记忆，是其他人……是的，每个人都拥有自己的记忆，就是他们自己机器上的一堆 Markdown 文件。

[原文] [Peter]: and to be honest those are probably super sensible because let's be honest Um people use their agent not just for problem solving but also for like personal problem solving very quickly super quickly i mean I I I I fully do that i'm like there's memory stuff that I don't want to have leaked

[译文] [Peter]:以此说实话，这些数据可能非常敏感（sensible，口误应为 sensitive）。因为老实说，人们使用代理不仅仅是为了解决问题，也是为了解决个人的问题，而且这种转变发生得非常快，超级快。我是说，我完全就是这样做的。有些记忆内容我是绝对不想泄露出去的。

[原文] [Interviewer]: yeah what would you rather um uh sort of like not show your Google search history at this point or your you know memory files

[译文] [Interviewer]: 是啊，到了这个时候，你更不愿意展示哪一个？是你的 Google 搜索记录，还是你的……你知道，记忆文件？

**

章节 6：Soul.md：赋予AI人格与安全边界

📝 本节摘要：

为了向公众展示 OpenClaw 的强大，Peter 做了一个疯狂的实验：将他的个人 AI 机器人放入一个公共 Discord 频道。虽然任何人都可以尝试“提示词注入（Prompt Injection）”攻击，但他通过简单的用户 ID 锁定了机器人的执行权限——它只会听从 Peter 的指令，却能嘲笑试图攻击它的黑客。本节的核心在于揭示了 AI 拥有独特个性的秘密：`soul.md`。这是 Peter 唯一没有开源的文件，受 Anthropic “宪法 AI”研究的启发，他在这个文件中定义了 AI 的核心价值观、与人类交互的边界以及性格底色，从而让机器人摆脱了标准模型“无聊”的回复风格，真正拥有了“灵魂”。

[原文] [Peter]: i built this and I was so excited but on Twitter people wouldn't get it like I I was failing to explain the awesomeness i feel like it needs to be experienced so I I tried various things and I I couldn't I couldn't nail the I couldn't nail the explaining so I was like let's do something really crazy i just created a discord and I just put my bot without any security restrictions in the public discord

[译文] [Peter]: 我做出了这个东西，非常兴奋，但在 Twitter 上人们并不买账。就像我无法解释它的美妙之处，我觉得这需要亲身体验。所以我尝试了各种方法，但我就是无法准确地、无法准确地解释清楚。所以我当时想，让我们做点真正疯狂的事吧：我建了一个 Discord，然后直接把我的机器人放进了公共 Discord 里，没有任何安全限制。

[原文] [Peter]: and then people came in and they interacted with it and they saw me build the software with it and they tried to prompt inject it and hack it and my agent would be laughing at them and you just had it locked down to your user ID so it only listened to you yeah yeah that and it was I made very clean instructions that other people dangerous only only listen to me but respond to everyone

[译文] [Peter]: 然后人们进来了，他们与它互动，看着我用它构建软件。他们试图对它进行“提示词注入”攻击，试图黑掉它，而我的代理会嘲笑他们。你只是把它锁定在你的用户 ID 上，所以它只听你的？是的，是的，就是那样。而且我制定了非常清晰的指令：其他人是危险的，只听我的，但要回复所有人。

[原文] [Interviewer]: and this prompt was in where was it stored the instructions um that's actually part of open claw itself very much so the the that's part of the system prompt okay you are now that explains to you you're in Discord there's like public people there but you only listen to your owner or like you're human I don't even know how I wrote it yeah yeah you're god And I kept I don't know what I did but my system was built very organically like at some point I created like an identity.mmd a soul.md like like various files

[译文] [Interviewer]: 这个提示词，这些指令是存在哪里的？嗯，这实际上就是 Open Claw 本身的一部分，很大程度上是系统提示词的一部分。好吧，“你现在……”这部分解释了你在 Discord 里，那里有公众，但你只听从你的主人，或者就像你是人类一样……我都不知道我是怎么写的了。是的，是的，你是上帝。而且我保持……我不知道我做了什么，但我的系统构建得非常有机，就像在某个时刻，我创建了一个 identity.mmd，一个 soul.md，就像各种各样的文件。

[原文] [Peter]: and then only in in January I started making it so other people could install it easier and I remember I built all these templates based on like oh take a rough look at what I have and make like templates and codex wrote it and what came was like Brad you know like people joke that Codex feels like Brad even though now they have a new friendlier voice i haven't tried that yet but the new bots they felt so boring compared to what I had so I was like Modi infuse the template multi is the name of your personal Yeah it's a new name because Yeah uh there was some naming challenges yeah so So you you were talking to Multi

[译文] [Peter]: 然后直到一月份，我才开始让其他人能更容易地安装它。我记得我基于“哦，大概看看我有什么，然后做个模板”的想法构建了所有这些模板，并且是 Codex 写的。结果出来的东西就像 Brad（可能指一种刻板的AI人格），你知道人们开玩笑说 Codex 感觉就像 Brad，尽管现在他们有了新的更友好的声音，我还没试过。但那些新机器人比起我拥有的那个感觉太无聊了。所以我说：“Multi，给模板注入（Infuse）……”，Multi 是你个人机器人的名字？是的，这是个新名字，因为，是的，呃，遇到了一些命名挑战。是的，所以你在和 Multi 说话。

[原文] [Peter]: yeah i was like "Infuse infuse those templates with your your character." And he changed the templates and then and then like all the things that came out afterwards were like actually funny not as funny as mine so like I kept some secret and the one file that's not open source is like my soul md so even though my my bot is in public discord so far nobody cracked that one file

[译文] [Peter]: 是的，我就说：“把你的性格注入到那些模板里去。” 然后他修改了模板，接着之后生成的所有东西实际上都很有趣。虽然没我的那么有趣，所以我保留了一些秘密。唯一没有开源的文件就是我的 soul.md。所以即使我的机器人在公共 Discord 里，到目前为止还没人破解那个文件。

[原文] [Interviewer]: tell me more about soul.md i just saw this research from Entropic where they now I think it's public but like a few months ago it was like where somebody ex randomly found out some text that's hidden in the weights where the model couldn't really remember that it learned it but it was like ingrained in the weights about the nicolity constitution and I found that incredibly fascinating

[译文] [Interviewer]: 给我多讲讲 soul.md。我刚看到 Anthropic（原文误听为 Entropic）的一项研究，我想现在应该是公开的了，但在几个月前，好像是有人偶然发现了一些隐藏在权重中的文本，模型并不真的记得它学过这些，但这些关于“宪法”（原文为 nicolity constitution，可能指 Constitutional AI）的内容就像根植在权重里一样。我觉得这非常迷人。

[原文] [Peter]: and I I talked about it with my agent and then we created a soulm with like the core values like how do we around human AI interaction what's important to me what's important to the model like some parts is a little bit like mamo jumbo and some parts is like I think actually really valuable in terms of how the model reacts and responds to text and makes it feel very natural

[译文] [Peter]: 然后我和我的代理讨论了这件事，接着我们创建了一个 soul.md，里面包含了核心价值观，比如我们在人机交互方面该怎么做？什么对我是重要的？什么对模型是重要的？有些部分有点像咒语（mumbo jumbo，原文误听为 mamo jumbo），而有些部分我认为实际上非常有价值，涉及到模型如何反应、如何回复文本，并让它感觉非常自然。

**

章节 7：反传统的开发哲学：摒弃复杂性

📝 本节摘要：

在访谈的最终章，Peter 分享了他极具个人色彩的开发哲学。与现代开发工具推崇的“Git 工作树（Worktrees）”或复杂的 UI 界面不同，他坚持使用最原始的“多文件夹副本”模式，只为降低认知负担，确保主分支（Main）永远处于可发布状态。在技术选型上，他甚至称主流的 MCP（模型上下文协议）为“垃圾”，坚持将所有功能转化为 CLI（命令行）工具——因为这才是人类和 AI 都最擅长的通用语言。访谈最后，主持人向这位来自“遥远小国”的独行侠致敬，感谢他用“Vibe Tunnel”等怪诞项目最终为世界带来了颠覆性的 OpenClaw。

[原文] [Interviewer]: in terms of building open claw um you're also kind of taking a little bit of a contrarian view at sometimes like which model you like for coding which one you like to run your bot on um and then also like how you actually like you know code um work trees get git work trees have kind of been a popular thing there's more and more tools embracing them but you're just you're just like you know no work trees just multiple checkouts of the repo and like parallel you know terminal windows tell me more about how you you build

[译文] [Interviewer]: 在构建 OpenClaw 方面，你有时也持有一种反传统的观点，比如你喜欢用哪个模型写代码，喜欢在哪个模型上运行你的机器人，还有你实际写代码的方式。比如 Git 工作树（Git Worktrees），这东西最近很流行，越来越多的工具都在支持它，但你却是那种“不，不用工作树，只要仓库的多个检出（Checkouts）副本”，然后在平行的终端窗口里操作。给我多讲讲你是怎么构建的。

[原文] [Peter]: yeah I feel like the whole world does cloud code and I don't think I could have built the thing with cloud code like I I love codex because it it looks through way more files be before it decides what to what to change you don't need to do so much charade to get a good output if you're skilled a skilled driver I sometimes even say uh you can get reasonably good output with any tool but codex is just is just really brilliant it is incredibly slow so sometimes I use like 10 at the same side at the same time

[译文] [Peter]: 是的，我感觉全世界都在用 Cloud Code，但我不觉得我能用 Cloud Code 造出这个东西。就像我热爱 Codex，因为它在决定修改什么之前会查看更多的文件。你不需要做那么多表面功夫就能得到好的输出。如果你是一个熟练的……熟练的“驾驶员”，我有时甚至会说，你用任何工具都能得到相当不错的输出，但 Codex 真的非常出色。不过它慢得令人难以置信，所以我有时会同时开 10 个窗口并行工作。

[原文] [Peter]: uh like maybe six on that screen and to there and to there and I don't like this is already a lot of complexity in my head there's a lot of jumping so I try to minimize anything else that is complexity so in my head main is always shippable I just have multiple copies of the same repository that all are on main so I don't have to deal with how do I name that branch Um there could be like conflicts on naming i cannot go back it's there are certain restrictions when you use work trees that I don't need to care about if it's copies i don't like to use a UI because that's again just added complexity like they're simpler and less friction

[译文] [Peter]: 比如那个屏幕上开 6 个，这儿开几个，那儿开几个。我不喜欢……我脑子里的复杂性已经够多了，要在不同任务间频繁跳转，所以我试图最小化任何其他的复杂性。所以在我的脑海里，主分支（Main）永远是可发布的。我只是拥有同一个仓库的多个副本，它们都停留在 Main 分支上，所以我不需要处理“我该怎么给这个分支命名？”的问题。命名可能会有冲突，或者我回不去了……当你使用工作树时会有某些限制，而如果是副本我就不需要关心这些。我不喜欢使用 UI（用户界面），因为那又是增加的复杂性，副本更简单，摩擦更少。

[原文] [Peter]: I have all I care about is like syncing and text i don't necessarily need to see so much code i I mostly see it like flying by sometimes there's like gnarly stuff that I want to like take a look but in most cases if you clearly understand the design and think it through and discuss it with your with your agent it's fine i'm also very happy that I didn't even build an MCP support so Open Claw is very successful and there's no MCP support in there with a small asterisk I built a skill that uses makeporter which is one of my tools that converts MCPS into CLIs and then you can just use any MCP as a CLI

[译文] [Peter]: 我关心的只有同步和文本。我不一定需要看到那么多代码，我大部分时间只是看着代码飞速闪过。有时会有一些棘手的东西我想看一眼，但在大多数情况下，如果你清楚地理解了设计，并且思考透彻，和你的代理讨论过，那就没问题。我也很高兴我甚至没有构建 MCP（Model Context Protocol，模型上下文协议）支持。OpenClaw 非常成功，但里面没有 MCP 支持——这里加个小注脚：我构建了一个技能，使用 Makeporter（我的一个工具），它可以把 MCP 转换成 CLI（命令行工具），然后你就可以把任何 MCP 当作 CLI 来使用。

[原文] [Peter]: um but I totally skip the whole classical MCP crap so you because you don't then you can actually if you need to you can use MCPS on the fly you don't have to restart unlike unlike Codex or cloud code where you actually have to restart the whole thing i think it's way more egent and also scales way better now you see entropic they do they built like a tool called search feature like something super custom for MCPS that was like in beta because it's like so gnarly no just have CLI bot really is good at Unix you can have as many as you want and it just works

[译文] [Peter]: 呃，但我完全跳过了整个传统的 MCP 垃圾（Crap）。因为你不这样做的话……实际上如果需要，你可以即时使用 MCP，而不需要重启。不像 Codex 或者 Cloud Code 那样，你实际上得重启整个东西。我认为这更优雅，扩展性也更好。现在你看 Anthropic，他们做了一个叫搜索功能的工具，就像是专门为 MCP 定制的某种超级复杂的东西，还在测试版，因为它太棘手了。不，只需要 CLI 就行了。机器人真的很擅长 Unix，你可以想要多少就要多少，它就是能工作。

[原文] [Peter]: so like I'm very happy that I got very little complaints about the MCP stuff it's kind of back to you're just giving it the same tools that humans liked to use yeah yeah and not invented stuff for for bots per se yeah humans no insane human tries to call an MCP manually yeah you just want to use CLIs that's the future i'm here for it

[译文] [Peter]: 所以我很高兴几乎没收到关于 MCP 方面的投诉。这有点像回到了原点：你只是给了它人类喜欢用的同样的工具。是的，是的，而不是专门为机器人发明一些东西。是的，人类……没有哪个神志正常的人会尝试手动调用 MCP，对吧？你只想用 CLI，那才是未来。我支持这个观点。

[原文] [Interviewer]: thank you so much for making the time uh to sit down chatting has been a huge inspiration too so like when we were texting you know over the course of the past couple years and I saw you getting back into the game and I was like Peter like what you're telling me like chase that dragon and you were doing like the weird like vibe tunnel thing etc nobody was paying attention and so I'm just like beyond you know stoked to see you know what's happening and um and of course they had to be sort of like a loner from some like tiny country like far away from Silicon Valley so like you know bring all of this upon us um so huge inspiration i'm here for it thank you awesome thanks Peter

[译文] [Interviewer]: 非常感谢你抽出时间坐下来聊天，这对我来说也是巨大的激励。比如我们在过去几年发短信的时候，我看到你重新回到了这个游戏里，我就想：“Peter，就像你告诉我的那样，去追逐那条龙吧！” 那时你在做像“Vibe Tunnel”这种奇怪的东西，没人关注。所以我现在简直是……你知道，看到正在发生的一切我太兴奋了。而且当然，必须是一个来自远离硅谷的某个微小国家的独行侠，给我们带来了这一切。所以这真是巨大的激励，我很支持。谢谢你。太棒了，谢谢 Peter。