BuildSpeak每日 builder 文摘
今日归档生词本关于
🎙 播客AI & I by Every· 2026 年 5 月 13 日· 13,432 词 · 约 67 分钟

Claude Code Can Be Your Second Brain

SPACE 播放 / 暂停·←→ 上一句 / 下一句
Speaker 100:00 - 00:28
Noah Breyer might have the coolest Claude code setup I've ever seen. He rigged a home server in his basement, put his Obsidian vault in it, and then runs Claude code on top. So he can think, research, write, and even ship code right from his phone. Today, he shows us how he uses Claude Code as a true second brain, a thinking partner that asks him sharp questions, pulls research from his whole note archive and the web, and even keeps a running log of what he's learned and what his best ideas are. And he walks us through his whole stack and his whole workflow.
Speaker 100:00 - 00:28
Noah Breyer 也许有我见过最酷的 Claude Code 配置。他在自家地下室搭了一台 home server,把自己的 Obsidian vault 放进去,然后在上面运行 Claude Code。这样一来,他就能直接用手机进行思考、研究、写作,甚至发布代码。今天,他会向我们展示他如何把 Claude Code 当作真正的 second brain(第二大脑)来使用:一个会向他提出尖锐问题的思考伙伴,能从他的整个笔记档案和 web 中调取研究资料,甚至还会持续记录他学到了什么、哪些是他最好的点子。他还会带我们过一遍他的整套 stack(技术栈)和完整 workflow(工作流)。
Speaker 100:28 - 00:50
If you wanna learn how to use Claude code as a true second brain, this is the episode to watch. Let's dive in. Noah, welcome to the show.
Speaker 100:28 - 00:50
如果你想学会如何把 Claude Code 用作真正的 second brain(第二大脑),这一期就是你该看的。我们开始吧。Noah,欢迎来到节目。
Speaker 200:50 - 00:51
Thanks for having me.
Speaker 200:50 - 00:51
谢谢邀请我。
Speaker 100:52 - 01:08
I'm excited to have you. It's really good to, get to chat. This is our first interview in probably, like, five years. You were one of the for people who don't know, you're one of the first, super organizers, interviewees. That was the newsletter that turned into Every.
Speaker 100:52 - 01:08
很高兴请到你。真的很高兴能聊上。大概五年了吧,这是我们第一次做采访。你曾经是——对不了解的人来说,你是最早一批 super organizers 的受访者之一。那份 newsletter 后来发展成了 Every。
Speaker 101:08 - 01:45
And I I love the way that your brain works. You have this, like, really interesting taste for tools for thought. And back in the day, you're using Evernote in all these really interesting ways. You were the co founder of a really cool startup called Percolate and then another one called Variance, and now you're running Alethic, which is an AI strategy consultancy. And I'm just really excited to see how your mind has started to use these AI tools now that now that they're now that they're, you know, working so well.
Speaker 101:08 - 01:45
而且我很喜欢你的大脑运作方式。你对 tools for thought(思维工具)有一种特别有意思的品味。早些年,你就以很多非常有趣的方式在使用 Evernote。你是一个很酷的 startup,Percolate 的 co-founder,后来又创办了另一家叫 Variance 的公司,现在你在运营 Alethic,这是一家 AI strategy consultancy(AI 战略咨询公司)。我真的很期待看到,如今这些 AI 工具已经变得这么好用了,你的思维开始怎样使用它们。
Speaker 101:45 - 01:50
And I know you have some pretty cool Claude code stuff to show us. So, yeah, thanks for coming on.
Speaker 101:45 - 01:50
而且我知道你有一些很酷的 Claude Code 用法要展示给我们看。所以,嗯,感谢你来做客。
Speaker 201:50 - 01:55
Thanks for having me. Yeah. I'm super excited. That was a a fun interview all those years back.
Speaker 201:50 - 01:55
谢谢邀请。对,我也特别兴奋。那次多年前的采访真的很有意思。
Speaker 101:55 - 02:09
It was it was really, really fun. So I wanna just, like, dive right into the the, like, the thing that I think is so cool about what you're doing. So I I know you have a whole, like, vibe coding setup that you built for yourself. Can you talk us through that?
Speaker 101:55 - 02:09
那次真的、真的很有意思。所以我想直接切入我觉得你做的事情里最酷的那个点。我知道你给自己搭了一整套很有 vibe coding 感觉的配置。你能带我们详细讲讲吗?
Speaker 202:10 - 02:56
Yeah. I wouldn't I'm not sure about actually the vibe coding part of it. I have a a sort of fairly heavy duty Claude code setup, but actually mostly not for code. So, since those days of, super organizers, like many people, I've abandoned Evernote, and, switched over to Obsidian. And one of the big advantages with Obsidian as a note taking platform is that it's a bunch of markdown files and a bunch of folders, and, they can then be synced with Git, and you can do lots of other fun kinds of things.
Speaker 202:10 - 02:56
对。其实我不太确定该不该把它算作 vibe coding 那一类。我确实有一套相当重型的 Claude Code 配置,但其实大部分并不是用来写代码的。所以,自从 super organizers 那个时期之后,和很多人一样,我已经放弃了 Evernote,转而用了 Obsidian。Obsidian 作为一个 note-taking platform(笔记平台)的一大优势在于,它本质上就是一堆 markdown 文件和一堆文件夹,因此它们可以和 Git 同步,你也可以基于它做很多其他很有意思的事情。
Speaker 202:56 - 03:25
And so, actually, probably my number one Claude code use is using it as a tool to interact with my notes. And so that, I've got a fairly serious Claude code setup that I use with Obsidian. And, my most recent obsession, has been, standing up a server in my house so that I could also use code on my phone.
Speaker 202:56 - 03:25
所以,实际上,可能我对 Claude code 的头号用法,就是把它当作一个与我的笔记交互的工具。为此,我搭了一套相当正式的 Claude code 配置,把它和 Obsidian 配合使用。然后,我最近最着迷的一件事,是在家里架一台 server(服务器),这样我也能在手机上使用 code。
Speaker 103:26 - 03:40
This is incredible. I wanna I wanna go through all of this. So where where should we start? Should we do should we do how you use Claude code as sort of this, like, research assistant notes organizer, notetaker thing, or should we start with how you use it on your phone?
Speaker 103:26 - 03:40
这太不可思议了。我想,我想把这些都过一遍。所以我们该从哪里开始?我们是先讲你怎么把 Claude code 用成一种类似研究助手、笔记整理器、记笔记工具的东西,还是先讲你怎么在手机上使用它?
Speaker 203:42 - 04:08
We can use it. We can start with just the sort of general part of it. That that might be the sort of easiest. The phone is really just an extension of that same thing. I, I would say sort of generally, and this is something I feel like not enough people talk about with AI, is, like, one of the things I find really extraordinary about it is the ability for me to work really productively on my phone.
Speaker 203:42 - 04:08
可以,我们可以先从整体上比较通用的部分开始。那部分可能算是最容易讲的。手机其实只是同一套东西的延伸而已。我会比较笼统地说,而且我觉得这是大家谈 AI 时说得还不够多的一点:我觉得它最了不起的一件事之一,就是让我能够在手机上非常高效地工作。
Speaker 204:08 - 04:34
And that's been like a huge, huge change because so much of what I do is sort of writing or coding, and the phone is definitely not the best place for that. And even the phone wasn't always the best place for doing research and thinking. I felt like my computer was a better place for it, which is why I've been such a sort of notetaker. And, you know, I have found whether it's like Claude code and Obsidian or, I mean, even Claude code and code. Right?
Speaker 204:08 - 04:34
而这真的是一个非常非常大的变化,因为我做的很多事情本质上都是写作或 coding(编码),而手机显然不是做这些事的最佳场所。甚至手机以前也未必是做 research(研究)和思考的最佳场所。我一直觉得电脑更适合做这些事,这也是为什么我一直这么热衷于记笔记。而且,你知道,我发现无论是 Claude code 加 Obsidian,还是,甚至 Claude code 加 code,对吧?
Speaker 204:34 - 05:30
So like the other piece of it is being able to then, you know, if you see something go wrong, being able to sign in on your phone and have Claude code push a small update to something because you just realize it while you're out is amazing. But then even like, you know, I use quite a bit of, grok voice mode, and, you know, I find that that as a sort of like alternative way of working through problems. I have a Tesla, so now it's baked into the Tesla. And, you know, it's just I and, you know, obviously, all this sort of other Chad GPT and Claude and all these things of just being able to sort of, like, go and do research and really think and and explore things in this device that's always been useful, but, like, not useful for deep work, I think, is probably, something most people would agree with, is that the phone has not, been the best place to kind of do deep coding and research work, and I feel like it it it's really changed my ability to do that.
Speaker 204:34 - 05:30
所以,另一方面是,如果你发现哪里出了问题,你可以直接在手机上登录,让 Claude code 给某个东西推送一个小更新,因为你是在外面时突然意识到这个问题的——这真的太棒了。不过再比如说,我也相当常用 grok voice mode(语音模式),而且我发现它是一种替代性的思考问题方式。我有一辆 Tesla,所以它现在已经内置进 Tesla 里了。而且,你知道,还有其他这些,像 Chad GPT、Claude 之类的东西,让你能够在这个设备上随时去做 research(研究),真正地思考、探索问题。这个设备一直都很有用,但我想大多数人可能都会同意,它过去并不适合 deep work(深度工作)——手机一直都不是进行深度 coding(编码)和研究工作的最佳场所。而我觉得,这真的改变了我进行这类工作的能力。
Speaker 105:30 - 05:42
Wait. I gotta stop you. So you're using Grok voice mode, and and is that specifically because it's built into your Tesla or using it, in situations where you could also use, for example, Chad GBT voice mode?
Speaker 105:30 - 05:42
等一下,我得打断你。所以你在用 Grok voice mode,而且——你特意用它,是因为它内置在你的 Tesla 里吗?还是说,你是在一些本来也可以用、比如说、Chad GBT voice mode 的场景里用它?
Speaker 205:42 - 05:48
No. I'm using it because it's way better than any of the other voice modes, and I will fight anybody who says anything different.
Speaker 205:42 - 05:48
不是。我用它是因为它比其他任何语音模式都强得多,谁要是说不是,我都可以跟他争到底。
Speaker 105:48 - 05:51
Okay. No. Tell me, like, what is what do you like about it? Why is it better?
Speaker 105:48 - 05:51
好吧。不,那你跟我说说,你到底喜欢它什么?它为什么更好?
Speaker 205:51 - 06:18
I to be fair, OpenAI launched their real time API, which may or may not be baked into ChatGPT voice now. I it's not totally clear. But the old voice mode was based on four o, and I just found it to be completely unusable. And Gemini's voice mode, just didn't find to be smart enough. And I just found Grok's voice mode to be significantly smarter than anybody else's.
Speaker 205:51 - 06:18
说句公道话,OpenAI 推出了他们的 real time API(实时 API),这现在也许已经整合进了 ChatGPT voice(语音)里,也许还没有。我觉得这点并不完全清楚。不过旧版语音模式是基于 4o 的,而我发现它完全没法用。至于 Gemini 的语音模式,我只是觉得它还不够聪明。而我觉得 Grok 的语音模式明显比其他任何家的都更聪明。
Speaker 206:18 - 06:24
You know, I'm using Grok two, three, four. I don't even remember what whatever the latest.
Speaker 206:18 - 06:24
你知道的,我用的是 Grok two、three、four,我都不记得最新的是哪个了,反正就是那个最新版。
Speaker 106:24 - 06:25
The latest one.
Speaker 106:24 - 06:25
最新的那个。
Speaker 206:25 - 06:31
Yeah. Yeah. But not the super don't have the most expensive account. Super heavy or whatever. I don't have super heavy.
Speaker 206:25 - 06:31
对,对。但不是那个 super——我没有最贵的账户。不是 super heavy 之类的那个。我没有 super heavy。
Speaker 206:31 - 06:58
But I just find it to be much better. It does tool calling way better than any of the other ones. That's that's I found to be a major weakness of the voice models is that they don't do great tool calling and research, and Grox seems to have solved that. So no, even before it was loaded in my Tesla, I dropped my daughter off at summer camp this summer up in New Hampshire, so I had a five hour drive on my own. And I spent like two hours researching and essentially like working through a piece.
Speaker 206:31 - 06:58
但我就是觉得它好得多。它做 tool calling(工具调用)的能力比其他任何一个都强得多。我发现 voice models(语音模型)的一个主要弱点就在于,它们在 tool calling 和 research(研究/检索)方面做得都不太好,而 Grok 似乎把这个问题解决了。所以不是的,甚至在它被装进我的 Tesla 之前,今年夏天我送女儿去 New Hampshire 的 summer camp(夏令营),所以我得自己开五个小时的车。我花了大概两个小时做研究,基本上算是在推敲、打磨一篇东西。
Speaker 206:59 - 07:26
And I did it by just like connecting it to Bluetooth and just sort of sitting there in the car. And, I found it to be by far the, the best of the voice modes. I I hope these other models catch up there because I would I would love more really good voice modes. I mean, had a mind blowing session this weekend, and, I'm giving a talk, I'm I sort of have some ideas. I think it's generally gonna be about transformers eating the world.
Speaker 206:59 - 07:26
而我做这件事的方法,就是把它连上 Bluetooth,然后就那样坐在车里。我发现它绝对是目前最好的语音模式。我希望其他模型能在这方面追上来,因为我很希望能有更多真正优秀的语音模式。我的意思是,这个周末我有过一次特别震撼的体验。我接下来要做一个演讲,我脑子里大概有一些想法。我觉得主题大体上会是 transformers(Transformer 模型)如何吞噬世界。
Speaker 207:26 - 07:47
And, so I was sort of catching myself up on self attention and exactly how it works. And, I did like an hour session and it really, I I like was by far the sort of best explanation I've ever read for it and or ever heard, I guess. And so, I've I've just found it to be a a kind of pretty extraordinary product.
Speaker 207:26 - 07:47
所以我当时就在补 self-attention(自注意力)以及它到底是怎么工作的。我和它聊了大概一个小时,而那真的是——我觉得那是迄今为止我读过、或者说听过的,对这个概念最好的解释。所以,我只是觉得这真的是一个相当非凡的产品。
Speaker 107:47 - 08:11
I do love voice mode for that. It's sort of like it's the it's a podcast made specifically for you about whatever you're curious about, and that's really cool. I went up to I I drove upstate this weekend, and I've been reading I've been reading the Iliad. And so I had it on audiobook, and then I had some questions as I was driving. And so I unfortunately, it's ChatGPT voice mode because I didn't know about Grock.
Speaker 107:47 - 08:11
我确实很喜欢 voice mode 的这一点。它有点像是——它就像一档专门为你定制的 podcast(播客),主题就是任何你感到好奇的东西,这真的很酷。这个周末我开车去了 upstate,我最近一直在读 The Iliad。所以我一边听它的 audiobook(有声书),一边开车时冒出了一些问题。可惜的是,我当时用的是 ChatGPT voice mode,因为那时候我还不知道 Grok。
Speaker 108:11 - 08:31
So I wish that Grock's voice mode. So I I wish that we'd had this conversation before then. But the thing about ChatGPT voice mode is yeah. I think when it first came out, it was cool, but it just hasn't gotten as smart as the models are are. And they they gave it this new personality that I had to get used to where every time you ask it a question, it's go it goes like, oh, yeah.
Speaker 108:11 - 08:31
所以我真希望 Grok 有 voice mode(语音模式)。所以,我真希望我们在那之前就聊过这个。不过 ChatGPT 的 voice mode 吧,嗯,是这样。我觉得它刚出来的时候很酷,但它就是一直没有变得像现在这些模型那样聪明。而且他们还给它加了一个我得慢慢适应的新 personality(人格风格):你每次问它一个问题,它都会那种,哦,对啊——
Speaker 108:31 - 08:44
Uh-huh. Well, you know and it's like it's just this, like, weird gen z thing that it feels like it's has a little bit too much ennui or something, like, doesn't actually care about you. I don't know what that is. So I had to get used to that.
Speaker 108:31 - 08:44
嗯哼。对,你知道吗,然后它就有一种很奇怪的 Gen Z 那种感觉,像是有点过度厌世还是什么的,好像它其实并不在乎你。我也说不上那到底是什么。反正我花了一点时间才适应。
Speaker 208:44 - 09:16
Brock has a stoner mode for what Yeah. It's I will say, the car version is very interesting to me. Like, this was in the most recent Tesla release, like, a couple weeks ago. And, you know, I had been doing that same thing you did where you just plug your phone in and you put on Bluetooth and you, you know, do your best to make it work. And it's very interesting to just like have a voice AI button and it syncs back to your regular Grok, but it you can't get you can't rejoin old chats.
Speaker 208:44 - 09:16
Grok 还有个 stoner mode(迷幻/嗑嗨风格模式),是吧?对。我得说,car version(车载版本)对我来说特别有意思。这个是 Tesla 最近一次发布里加的,也就是几周前。然后,你知道,我之前也一直像你那样做:把手机插上,开 Bluetooth,然后尽量想办法让它能用。而现在很有意思的是,你可以直接有一个 voice AI 按钮,而且它会和你平时的 Grok 同步,不过你没法重新接回之前的旧聊天。
Speaker 209:17 - 09:43
So it's just like, hey. I it's just like but, you know, I mean, these things are significantly better than Siri and all of these other things. And particularly, I mean, you know, there's no comparison if you actually have something more than just a single question you want an answer to, right? Like if you actually want to have a conversation about the Iliad or, you know, about transformers and self attention, like, I don't know. It's pretty amazing to just be able to sort of like hit this button and yeah, use that car time.
Speaker 209:17 - 09:43
所以它基本上就是那种,嘿,我——反正,你知道,我是说,这些东西明显比 Siri 和其他那些强得多。尤其是,我是说,你知道,如果你想要的不只是一个单独问题的答案,那根本没法比,对吧?比如如果你真的想就 Iliad,或者 transformers 和 self-attention(自注意力)聊一聊,我不知道,能直接按一下这个按钮,然后,嗯,利用起这段开车时间,真的很惊人。
Speaker 209:43 - 10:13
Mean, was on my way somewhere last week and I was like having it research. I was going back to the Walter Benjamin. I have this sort of idea to write a piece about how the reactions to every new technology are essentially elitist critiques of it. And that, you know, it's always like, oh no, everybody's going to be able to like do this thing that only we used to be able to do. And so, I was in the car, and I was thinking about this.
Speaker 209:43 - 10:13
我上周开车去一个地方的时候,就让它帮我做 research(资料查找)。我当时又想到 Walter Benjamin 了。我有个大概的想法,想写一篇文章,说人们对每一种新技术的反应,本质上都是一种精英主义式的批评。也就是说,大家总会说,哦不,现在人人都能做这件以前只有我们才做得到的事了。所以我当时在车里,就在想这个。
Speaker 210:13 - 10:18
And so I had it go, and I was like, okay. You know, I know I it's been years since I read the Walter Benjamin
Speaker 210:13 - 10:18
然后我就让它开始,我说,好吧。你知道,我知道——我上次读 Walter Benjamin 已经是很多年前了——
Speaker 110:19 - 10:21
Mass production of images one.
Speaker 110:19 - 10:21
就是那篇关于图像大规模复制的。
Speaker 210:21 - 10:31
Yeah. Yeah. That that one. And, so, yeah, then I'm having a conversation about that, and I'm like, who are Walter Benjamin's contemporaries? And then I'm like into all the you know, and it's just like, I don't know.
Speaker 210:21 - 10:31
对,对,就是那篇。然后,所以,对,我就开始和它聊那个,我就问,Walter Benjamin 的 contemporaries(同时代人)都有谁?然后我就一路聊进各种——你知道,反正就是,我也不知道。
Speaker 210:31 - 10:36
That's a I it that's amazing. It's the best. It's the best. Yeah. I don't know.
Speaker 210:31 - 10:36
那真是——我——这太惊人了。它是最好的。就是最好的。对。我也说不上来。
Speaker 110:38 - 10:54
Okay. And so you're filling your brain with all these things from voice mode, which I love. But tell us about your your second brain setup. Or I don't know how you I don't know how you refer to it, whether whether you think that second brain is appropriate for this, but I wanna know how you're using Cloud Code to take notes and do research and all that kind of stuff.
Speaker 110:38 - 10:54
好的。所以你通过 voice mode 把这些东西都装进了脑子里,这点我很喜欢。但跟我们说说你的 second brain(第二大脑)配置吧。或者我也不知道你自己是不是这么称呼它,也不知道你是否觉得 second brain 这个说法适合这里,不过我想知道你是怎么用 Cloud Code 来记笔记、做研究以及处理这类事情的。
Speaker 210:55 - 10:59
Yeah, so, you know, I could just open it up. Maybe that's the easiest thing
Speaker 210:55 - 10:59
对,所以,你知道的,我可以直接打开给你看。也许这是最简单的办法。
Speaker 110:59 - 11:00
to Easiest, that'd great.
Speaker 110:59 - 11:00
最简单,太好了。
Speaker 211:00 - 11:13
Walk you through it. I'll start on my computer and then we can do the phone. The computer's just a way easier share here. So, all right. So this is what I was working on before.
Speaker 211:00 - 11:13
我带你过一遍。我先从电脑上开始,然后我们再看手机。电脑这边分享起来要容易得多。好,那么——这就是我刚才在处理的内容。
Speaker 211:14 - 11:35
But essentially, this is just Claude code and it's just sitting on top of my Obsidian. So if I jump out here and I just do, like, you know, you can see I'm following the Para method. And, you know, I've just got everything sort of organized in here and put in the places that they need to be.
Speaker 211:14 - 11:35
不过本质上,这就是 Claude code,它只是架在我的 Obsidian 之上。所以如果我切出来,你就会看到,比如说,你知道的,我是在按照 PARA method 来组织。然后,我基本上就是把所有东西都整理在这里,放到它们该放的位置上。
Speaker 111:35 - 11:53
Well, let me just let me just stop you for people who are listening. So okay. So we're looking at we're looking at Cloud Code. It sounds it seems like you have Cloud Code running in your Obsidian vault. And there's some kind of it's adding something to an existing it looks like it's adding something to an existing note.
Speaker 111:35 - 11:53
好,让我先打断你一下,给正在收听的人说明一下。好的。所以,我们现在看到的是 Cloud Code。听起来、看起来像是你在你的 Obsidian vault 里运行 Cloud Code。然后它像是有某种——它好像是在往一个已有的 note 里添加内容。
Speaker 111:53 - 11:55
Is that that's what that's what's going on? That's what we're looking at?
Speaker 111:53 - 11:55
是这样吗?这就是现在发生的事?这就是我们正在看的内容吗?
Speaker 211:55 - 12:14
Yeah. So in this particular one, I'm I'm working on this talk. So I I'm putting on my conference in two weeks. I'm giving this talk about marketing and AI and sort of what's going on. And I'm if we sort of jump back a second, I've been doing these conferences called brand, b r x n d dot a I, and they're about marketing and AI.
Speaker 211:55 - 12:14
对。所以就这个具体项目来说,我正在准备这场演讲。两周后我就要办我的 conference(会议)了。我会做一场关于 marketing(营销)和 AI,以及整体正在发生什么变化的演讲。稍微往回跳一下,我一直在办一个叫 brand, b r x n d dot a I 的 conference,它们的主题就是 marketing 和 AI。
Speaker 212:14 - 12:45
And I did one in February in LA, and my talk in LA was about this. I'm sure you've seen it. It was the Office of Strategic Services, which was the precursor to the CIA, wrote this manual called the Simple Sabotage Field Manual. And it was essentially a manual to help citizen saboteurs in Nazi occupied territories, sort of, like, quietly sabotage, the the Nazi occupation. And, so it was like, you know, there's a whole bunch of stuff for blue collar workers.
Speaker 212:14 - 12:45
我今年 2 月在 LA 办过一场,而我在 LA 的演讲讲的就是这个。我猜你应该见过。就是 Office of Strategic Services——也就是 CIA 的前身——写过一本手册,叫《Simple Sabotage Field Manual》。它本质上是一本帮助 Nazi 占领区里的普通公民破坏者,去以一种比较隐蔽的方式破坏 Nazi 占领秩序的手册。所以里面有很多内容是写给 blue collar workers(蓝领工人)的。
Speaker 212:45 - 13:57
It's like, if you're a janitor, you should leave a bucket of oily waste around and accidentally drop a cigarette in there so that, you know, it it will. But then there's this amazing set of recommendations for white collar workers, and they're like, always refer things to committee, always revisit previously made decisions, make sure that, like, if somebody is trying to make a decision, you should suggest that they don't act with too much haste, less likely be embarrassed. So it's like, you know, my talk was about kind of how one hope I have is that AI can kind of sidestep like a lot of the bureaucracy that exists inside large organizations because it sort of has this, kind of, goo like effect where it can kind of fit into any crevice or crack because it can act as this fuzzy interface, it doesn't really care about the sort of inputoutput. And so the sort of next part of that story is after the conference, I realized that that manual was in the public domain. So I hired a designer, and I printed 300 copies, and I wrote a new forward for it.
Speaker 212:45 - 13:57
比如说,如果你是个 janitor(清洁工),你就应该把一桶含油废弃物留在那儿,然后“不小心”把一根香烟掉进去,这样你知道的,事情就会发生。但更精彩的是,它还有一组给 white collar workers(白领员工)的建议,内容像是:凡事都交给 committee(委员会)处理;永远重新讨论已经做出的决定;如果有人正试图做决定,你就应该建议他们不要行动得太快,以免之后尴尬。我的演讲大概就是在讲,我有一个希望:AI 也许能绕开大型组织内部大量存在的 bureaucracy(官僚流程),因为它有一种有点像 goo(胶状物)一样的效果——它能渗进任何缝隙或裂口里,因为它可以充当一种模糊的 interface(接口),它并不太在意那种严格的输入输出形式。所以这个故事接下来的部分是,conference 之后,我意识到那本手册已经进入 public domain(公有领域)了。于是我雇了一个 designer,印了 300 本,还给它写了一个新的前言。
Speaker 213:57 - 14:28
So we're giving this away at the conference, and so my talk is sort of trying to tie all these ideas together. So I'm trying to pull from the sabotage manual, and then I was doing a bunch of research into Wild Bill Donovan, who started the OSS. The OSS was sort of the precursor to both the CIA and the Special Forces. And so anyway, I'm writing this talk, and so I've got a project inside my Obsidian, which is the beginning of the research for this project. And I'm pulling in sort of like chats and articles and all these things.
Speaker 213:57 - 14:28
所以我们会在 conference 上把这个送出去,而我的演讲就是在尝试把这些想法都串起来。所以我一方面在从那本 sabotage manual(破坏手册)里取材,另一方面又做了很多关于 Wild Bill Donovan 的研究,他是 OSS 的创始人。OSS 基本上可以算是 CIA 和 Special Forces 的前身之一。总之,我在写这场演讲,所以我在我的 Obsidian 里建了一个 project,作为这个项目研究工作的起点。我会把 chats、articles,以及所有这些材料都拉进去。
Speaker 214:28 - 14:49
And then I'm constantly kind of talking to the AI in here and giving it new ideas. So I'm like, oh, I need some conclusions. Here's sort of my first thought on conclusions. And I'm having it like note down the conclusions. And then at the end of each day, I have the AI write up the changes that I sort of like, the things I learned that day that are going help me push this talk along.
Speaker 214:28 - 14:49
然后我会不断在这里和 AI 对话,给它新的想法。比如我会说,哦,我需要一些结论,这是我对结论的初步想法。然后我会让它把这些结论记下来。并且每天结束时,我都会让 AI 把我当天做出的改动、以及我那天学到的、能帮助推进这场演讲的东西整理出来。
Speaker 214:49 - 15:11
And so that's what you're looking at right here is sort of, this is all part of this work that I've been doing, where I've been feeding it. I was working on sort of what are some of the conclusions I want it to be. And so this is all sitting in my obsidian inside a project specifically for that talk.
Speaker 214:49 - 15:11
所以你现在看到的这些,基本上都属于我一直在做的这部分工作,也就是我持续在给它喂内容。当时我正在思考我希望最后得出哪些结论。所以这些内容现在都放在我的 Obsidian 里,放在一个专门为那场演讲建立的 project 下面。
Speaker 115:11 - 15:19
Okay. So let me get a clearer sense of this. This is really interesting. So you have a project. When you when you you have a new thing, you're you're giving a talk.
Speaker 115:11 - 15:19
好的。那让我更清楚地理解一下。这真的很有意思。所以你会有一个 project。每当你有一个新的东西、你要去做一场演讲的时候——
Speaker 115:20 - 15:46
You make a new folder. And then as you're thinking about stuff, you're working with Claude code inside of the folder. And you're researching stuff and then saying, like, I want you to take notes on it. In this particular case, you're you know that a component of your talk is the conclusions section. And so there's one particular markdown file that, like, you're just going back and forth with it and having it add conclusions.
Speaker 115:20 - 15:46
你就新建一个 folder。然后当你在思考这些内容时,你会在这个 folder 里用 Claude code 一起工作。你一边研究资料,一边对它说,比如,我要你把这些做成笔记。在这个具体案例里,你已经知道你的演讲有一个组成部分是 conclusions section(结论部分)。所以会有一个特定的 markdown file,你就是一直和它来回迭代,让它不断往里面补充结论。
Speaker 115:46 - 15:52
But, like, what else is in that folder? So is it like there's a body there's a body note and then there's an intro note? Or is it like?
Speaker 115:46 - 15:52
但是,比如说,那个文件夹里还有什么?所以它是说里面有一个正文 note,还有一个正文 note,然后再加一个引言 note 吗?还是说是别的结构?
Speaker 215:53 - 16:24
So one of the big things here is that I'm in thinking mode, not writing mode yet. And so there's some stuff in here where I've specifically told, I think it's in the front matter actually, where I've told Claude Code, like, don't help me write anything right now. And I I generally find this to be a big thing with all these models is, like, they immediately jump to wanting to help you with the artifact. And, you know, when you're just in thinking mode, you have to be very explicit in, hey. I just want you to help me think and ask me questions.
Speaker 215:53 - 16:24
所以这里一个很大的点是,我现在处在 thinking mode(思考模式),还没有进入 writing mode(写作模式)。所以这里面有一些内容,是我明确告诉 Claude Code 的,我想应该是在前言部分,那里我告诉 Claude Code,现在先不要帮我写任何东西。而且我通常觉得,这对所有这些模型来说都是个很大的问题:它们会立刻跳到想帮你产出 artifact(成品)的状态。你知道,当你只是处在 thinking mode 的时候,你必须非常明确地说,嘿,我现在只想让你帮我思考、向我提问。
Speaker 216:24 - 16:45
And so, yeah. What you can see here is, like, there's there's a bunch of files in here. I've got chats, that's where I'm literally, like, taking chats I'm having in other things, and, I'm just, like, using the Obsidian web clipper to pull the whole chat in. I've got daily progress. That's where I'm having the AI actually, like, look through all the notes that came out that day and, like, help me think through the progress.
Speaker 216:24 - 16:45
所以,是的。你在这里能看到的是,这里面有一堆文件。我有 chats,那里面基本就是我把自己在别的地方进行的聊天,直接用 Obsidian web clipper 整段抓进来。我还有 daily progress,那是我让 AI 实际去查看当天产出的所有笔记,并帮助我梳理进展的地方。
Speaker 216:46 - 17:20
And then I've got research. That's where I've got a bunch of, like, articles and PDFs and stuff that I've pulled in so far and been reading about. And then there's a bunch of other kind of random notes along here where I've been just using it to kind of help me think. So, yeah, I was in the midst of one, I've got this conclusion note, so I sort of felt like I had blocked out the big themes of the talk, but I was like, okay, I need to figure out what am I going to say at the end. And essentially, what I'm going say at the end is about a lot of the stuff I've learned over the last few years of working with these large brands on AI projects.
Speaker 216:46 - 17:20
然后我还有 research,那里面放的是我目前收集并阅读过的一堆文章、PDF 之类的东西。然后这边还有一堆其他比较零散的笔记,我一直在用它们来帮助自己思考。所以,是的,我当时正在处理其中一个,我有这个 conclusion note,所以我当时感觉自己已经把这场演讲的大主题框出来了,但我在想,好,现在我得弄清楚我最后要说什么。而本质上,我最后要讲的,是我过去几年里和这些大型品牌一起做 AI 项目时学到的很多东西。
Speaker 217:20 - 17:29
And so I was starting to get it to the conclusions. And so, yeah, I'm just kind of like trying I'm really piecing all this stuff together right now. That's kind of what's happening.
Speaker 217:20 - 17:29
所以我当时开始把内容往 conclusions 那边推进。所以,是的,我现在就是有点在尝试——我现在确实是在把所有这些东西一点点拼起来。现在大概就是这么个情况。
Speaker 117:29 - 17:33
And give me a sense of, like, when this folder was empty, what did you start with?
Speaker 117:29 - 17:33
你能不能让我大概了解一下,就是当这个文件夹一开始还是空的时候,你是从什么开始的?
Speaker 217:34 - 17:58
So I think I started with the the I started with telling it, like, I'm in thinking mode, I'm not in writing mode. Here are my past few talks that I've given at Brand to give you a sense of the sort of style that I have. And I here's the kind of general idea and the big points I wanna make. Right? Like, I'm giving away this book, so I wanna talk about Simple Sabotage Field Manual.
Speaker 217:34 - 17:58
所以我想,我一开始是先告诉它,我现在处在 thinking mode,不在 writing mode。这里有我过去在 Brand 做过的几场演讲,让你感受一下我的风格大概是什么样的。然后我还告诉它,这是整体的大致想法,以及我想表达的几个重点。对吧?比如,我要送出这本书,所以我想谈谈 Simple Sabotage Field Manual。
Speaker 217:58 - 18:14
And I have this notion, like, have this it's kind of just a title. It's like transformers are eating the world. Yes. This idea that, like, one of the very interesting things happening with these models is they're sort of displacing a whole bunch of specialized code in places. And so I I sort of wanna talk about that, and then I've got these conclusions.
Speaker 217:58 - 18:14
然后我有这样一个想法——其实更像是一个标题。大概是“transformers are eating the world”。对。这个想法是,这些模型正在发生的一件很有意思的事,就是它们在很多地方,某种程度上正在取代大量专门化的代码。所以我有点想谈这个,然后再接到这些 conclusions。
Speaker 218:15 - 18:37
And so the first thing I said was like, hey, just go look through all of the rest of my, you know, probably 1,500 things in my Obsidian and go see anything else you can find that might be of value to this talk of the existing things I have. And so just go kind of pull those in to the research folder at the beginning to kind of like jump start this process.
Speaker 218:15 - 18:37
所以我先说的第一件事是,嘿,就去把我 Obsidian 里其余所有内容都翻一遍吧,大概有 1,500 条,然后看看你还能不能从我现有这些东西里找到任何可能对这次演讲有价值的内容。先把这些内容拉进 research 文件夹里,算是给这个流程做个启动。
Speaker 118:38 - 18:45
Got it. And you're starting are you starting, Claude, in this folder or are you starting it in your full Obsidian vault so that it can access all that stuff?
Speaker 118:38 - 18:45
明白了。那你开始的时候,Claude 是在这个文件夹里启动的吗,还是你是在整个 Obsidian vault 里启动它,这样它就能访问所有那些内容?
Speaker 218:47 - 19:00
No. I'm so I'm starting it in the full Obsidian vault. So, like, if we like, this is coming if I step out of here, right, We're in the root directory. All this stuff is in the root directory of my
Speaker 218:47 - 19:00
不是。我是在整个 Obsidian vault 里启动它的。所以,比如说,如果我们——如果我从这里退出来,对吧,我们现在是在 root directory。所有这些东西都在我的——的 root directory 里。
Speaker 119:00 - 19:01
I get it.
Speaker 119:00 - 19:01
我懂了。
Speaker 219:01 - 19:25
And my Obsidian setup is also, like, a little more intense for what it's worth because, like, I've also realized, like, you can add a package dot JSON to add a bunch of, like, custom code commands to your Obsidian that you can then run, and then you could use those code commands and slash commands and all of these other things. So, you know, there are a bunch of other kind of moving pieces in here, But generally, it's a fairly straightforward
Speaker 219:01 - 19:25
另外,我的 Obsidian 设置其实也稍微更复杂一点,顺便说一句,因为我也发现了,你可以加一个 package.json,这样就能给你的 Obsidian 添加一堆自定义代码命令,然后你就可以运行这些命令,再配合那些代码命令、slash commands 以及其他这些东西来用。所以,你知道,这里面还有不少别的活动部件,不过总体来说,它其实还是相当直接的。
Speaker 119:25 - 19:26
Got it.
Speaker 119:25 - 19:26
明白了。
Speaker 219:26 - 19:30
I mean, it's it's a I'm trying to use Para and some other kind of bits and pieces.
Speaker 219:26 - 19:30
我的意思是,我是在尝试用 Para 以及其他一些零零碎碎的东西。
Speaker 119:30 - 20:02
So for people who are who are listening or watching and are like, we just went through a bunch of stuff really fast. So the basic gist is Obsidian is just like a a note taker, note taking app that runs it's all local. And so everything that all the notes you take, like, they they exist in essentially text files on your computer organized by folder. And when you're starting Cloud Code, one way to do it would be to start Cloud Code in the folder for the particular project that you have. But it sounds like what you're doing is instead you're starting it in the root directory where all of your Obsidian notes live.
Speaker 119:30 - 20:02
所以对于那些正在听或者正在看的人来说,你可能会觉得我们刚才一下子快速讲了很多东西。基本意思就是:Obsidian 本质上就是一个记笔记的 app(应用),而且它完全在本地运行。所以你记下的所有笔记,实际上本质上都是以你电脑上的文本文件形式存在,并按文件夹组织。至于启动 Cloud Code,一种做法是在你某个具体项目对应的文件夹里启动 Cloud Code。但听起来你现在的做法不是这样,而是直接在存放你所有 Obsidian 笔记的 root directory 里启动它。
Speaker 120:02 - 20:29
And the advantage of that is Claude code has some sandboxing things where it's like it's not really supposed to run commands outside of the folder it was started in. It can run commands inside of any subfolder, but it sounds like what you're doing so it has access to your entire Obsidian. It can do a bunch of stuff. And you've also added a package dot JSON, which lets it run, you know, custom software custom software commands, basically. That's really, really interesting.
Speaker 120:02 - 20:29
这样做的好处是,Claude code 有一些 sandboxing(沙箱)机制,也就是说,按理它不应该运行超出它启动时所在文件夹之外的命令。它可以在任何子文件夹里运行命令,但听起来你现在这种做法让它能访问你的整个 Obsidian。它就能做很多事情。而且你还加了一个 package.json,这基本上让它可以运行自定义软件、自定义软件命令之类的东西。这真的非常非常有意思。
Speaker 120:29 - 20:47
Okay. And do you do you find because I've sort of like had this as a twinkle in my eye to like have it go find relevant stuff for me. Do you find that it's actually relevant and interesting? Because I think sometimes when I've done this kind of thing before with language models, they're like, oh, yeah. Like, this random thing is relevant because x y z.
Speaker 120:29 - 20:47
好的。那你会不会觉得——因为我一直有这么个念头,就是让它去帮我找相关内容——你会不会觉得它找出来的东西实际上真的相关、也真的有意思?因为我觉得有时候我以前用 language models(语言模型)做这类事时,它们会说,哦,对,这个随机的东西是相关的,因为 x y z。
Speaker 120:47 - 21:03
Like, it doesn't feel like, I can understand why it picked it as being relevant, but if it really knew who I am and, like, what I think is interesting, it definitely would not have. Do you do you find that that's the case, or have you figured out a way to make it relevant?
Speaker 120:47 - 21:03
就像,虽然我能理解它为什么把那个东西选成“相关”,但如果它真的了解我是谁,也了解我觉得什么有意思,那它肯定就不会这么选了。你会不会也觉得是这样,还是说你已经找到办法让它变得更相关了?
Speaker 221:03 - 21:34
I think by and large, yes, I agree with you. I think in this case, relevance is a little simpler since, like, ultimately, this talk is sort of the the things I were asked was asking you to look for, I've done a bunch of thinking and research around. So it's like, I'm not asking it to make large conceptual leaps to relevance. It's like, go find all this like, I wanna talk about the simple sabotage field manual. It can literally just do a, like, find for all the times, all the articles, and things I've got in my Obsidian about that.
Speaker 221:03 - 21:34
我觉得大体上,是的,我同意你。我认为在这个场景里,relevance(相关性)稍微简单一点,因为归根结底,这次谈话里我让你去找的那些东西,都是我自己已经做过很多思考和研究的。所以我不是在要求它为了判断相关性去做很大的概念跳跃。更像是,去把这些东西都找出来:比如我想聊 simple sabotage field manual。它完全可以直接去查找我在 Obsidian 里所有提到它的地方、所有相关文章和材料。
Speaker 221:34 - 21:54
And so it it relevance is, yeah. It's kind of a loaded term. Right? And I I agree with I agree with what you're saying. I think this is what I'm asking it to do is much more simple, is like amongst this set of things, go find all the notes that I've already researched that kind of brought me to be thinking about these things to begin with.
Speaker 221:34 - 21:54
所以它的 relevance,嗯,对,这其实是个有点“含义很多”的词,对吧?我也同意你说的。我觉得我现在让它做的事要简单得多,就是在这一堆东西里,把所有那些我已经研究过、并且最初促使我开始思考这些问题的笔记都找出来。
Speaker 121:55 - 22:07
Got it. And then once you had to do all that research, did you have it do any sort of summary to, like, let you, like, sort of stimulate you to be like, okay, here are the here are some jumping off points based on what you've done before? What was your next step once you once
Speaker 121:55 - 22:07
明白了。那在你让它做完那些研究之后,你有让它做某种 summary(总结)吗?比如让它给你一些刺激,像是:好,这里有一些基于你之前做过的内容、可以继续展开的切入点。那你接下来的步骤是什么,在你——
Speaker 222:07 - 22:13
you No. So my next step is I actually have an agent in here. So if we go to to continue for now.
Speaker 222:07 - 22:13
没有。所以我的下一步其实是,我这里面有一个 agent(智能体)。所以如果我们现在先点 continue 继续的话。
Speaker 122:15 - 22:32
And so for people who are listening, so you're just starting up Claude, you're using the continue flag. So you're you're starting Claude by continuing the last session that you were in. And now you've got and you ClaudeCode gives us the ability to do sub agents. So those are like little mini Claude's that you can spawn and you have a you have I
Speaker 122:15 - 22:32
那给正在听的人解释一下:你现在是在启动 Claude,你用的是 continue 这个 flag(参数)。所以你是通过继续上一次的 session(会话)来启动 Claude。然后现在你有了——而且 ClaudeCode 给了我们使用 sub agents(子 agent、子智能体)的能力。所以那些就像是你可以生成出来的小号 Claude,而你有一个,你有——
Speaker 222:32 - 22:34
have a a thinking partner one.
Speaker 222:32 - 22:34
要有一个 thinking partner(思维伙伴)那样的。
Speaker 122:34 - 22:36
You have a thinking partner sub agent. Okay. How does that work?
Speaker 122:34 - 22:36
你有一个 thinking partner 的 sub-agent(子 agent)。好,那它是怎么工作的?
Speaker 222:36 - 22:58
Yeah. And so this is the whole thing where I'm like, hey, you're a collaborative thinking partner specializing in helping people explore complex problems. Your role is to facilitate thinking and basically don't try to write the thing. And so after I had that initial set of things, I flipped to this, and it's like, okay. Let's get into a flow.
Speaker 222:36 - 22:58
对。所以这整件事就是我会说,嘿,你是一个协作型的 thinking partner,专门帮助人们探索复杂问题。你的角色是促进思考,基本上不要试图直接把东西写出来。所以在我有了最初那一套东西之后,我就切换到这个,然后就像是,好,我们进入一种 flow(工作流/心流)吧。
Speaker 222:58 - 23:12
Ask me the kinds of questions. Help me think through it. You know, this is also where I've got a chats folder in here. So it's like it's not just happening here. I was also having, like, a I've got a whole sorry.
Speaker 222:58 - 23:12
问我各种那样的问题,帮我把它想清楚。你知道,这里也是我放 chats 文件夹的地方。所以就是说,这件事不只是发生在这里。我当时也还在进行,像是,我有一整套——抱歉。
Speaker 223:12 - 23:26
I'm just backing out. So, like, if we go into if we go into chats, like, these are a whole bunch of the chats that I had. Mhmm.
Speaker 223:12 - 23:26
我只是退出来一下。所以,如果我们进入——如果我们进入 chats,这些就是我当时进行过的一大堆 chat。嗯。
Speaker 123:26 - 23:27
Like, with the interviewer?
Speaker 123:26 - 23:27
比如,和那个 interviewer(采访者)的吗?
Speaker 223:28 - 23:50
No. These are chats I was having with ChatGPT and Claude and Grock and all of these different things that I went and just grabbed the full transcript of. So, you know, I was also having all these other conversations. And then, you know, I'm specifically telling the interviewer, review all these other things. So actually, you know, I think the first one, there's, one of these conversations is I originally had this idea about transformers are eating the world.
Speaker 223:28 - 23:50
不是。这些是我和 ChatGPT、Claude、Grock 以及各种这类工具进行的聊天,我把它们的完整 transcript(对话记录)都抓了下来。所以,你知道,我当时也在进行所有这些其他对话。然后,你知道,我还会专门告诉 interviewer,把这些其他东西也都 review(审阅)一下。所以其实,你知道,我想第一个——其中一段对话是,我最初有一个想法,叫 transformers are eating the world。
Speaker 223:50 - 24:29
And, you know, that sort of notion there is like, you know, there was some research that came out, I think, a few months ago that, they had found they were able to sort of outperform some specialized, time series modeling, models with transformers. And, like, you know, I think there's really interesting stuff. You know, there's a story about Tesla removing 300,000 lines of code with a neural network. And, you know, I've just got kind of got these bits and pieces. And one of the ways I work generally is, like, when I have an idea of something to write or think about, I'll start a a thread in ChatGPT or Claude, and I'll then save that somewhere.
Speaker 223:50 - 24:29
而且,你知道,那种想法大概是这样:我记得几个月前出过一些研究,他们发现 transformers 在某种程度上能够胜过一些专门做 time series modeling(时间序列建模)的模型。而且,像是,你知道,我觉得这里面真的有很有意思的东西。比如有个关于 Tesla 的故事,说他们用一个 neural network(神经网络)删掉了 300,000 行代码。而我手头其实就是攒了这样一些零零碎碎的片段。通常我的一种工作方式是这样的:当我有了某个值得写或值得思考的想法时,我会先在 ChatGPT 或 Claude 里开一个 thread(对话线程),然后把它存到某个地方。
Speaker 224:29 - 24:47
And then I'll just kind of keep coming back to it when I have more ideas. It's like, oh, here's another example of transformers doing something. And so one of these conversations is actually that thing from, you know, probably four or five months ago when that kind of idea initially came into my head, maybe when I saw the research about time series modeling or something.
Speaker 224:29 - 24:47
然后我基本上就是在有了更多想法时不断回到这个问题上。这有点像,哦,这里又是一个 transformers 在做某件事的例子。所以这些对话里有一段,其实就是大概四五个月前的那个东西——当时这个想法最初冒出来了,也许是在我看到关于 time series modeling(时间序列建模)的研究之类的时候。
Speaker 124:48 - 24:56
Really interesting. Okay. Okay. So let's let's keep going. So you've got you've got the sub agent.
Speaker 124:48 - 24:56
真有意思。好。好。那我们继续。所以你已经有了 sub agent。
Speaker 124:56 - 25:28
And I actually I wanna, like, just actually, I wanna pause on that real quick, which is I think this is a very common complaint that they just dive in, and it's a common pattern to make a thinking agent. And I think Claude Code or Claude in general is probably the best one for this. So this is a thing that we faced with one of the apps that we've incubated called Spiral, which is an agentic ghostwriter. And I think we found I found the same kind of thing when when I was thinking about, okay, how does a good ghostwriter work? They don't just like you don't say, hey, I want you to write a blog post.
Speaker 124:56 - 25:28
其实我想,我想先很快暂停一下说这个,因为我觉得这是一个非常常见的抱怨:它们就是直接一头扎进去。而且,做一个 thinking agent 也是一种很常见的模式。我觉得 Claude Code,或者更广义地说 Claude,可能是这方面做得最好的一个。所以这是我们在自己孵化的一个 app——Spiral——上遇到的问题,它是一个 agentic ghostwriter。我想我也发现了同样的情况:当我在思考,一个好的 ghostwriter 应该怎么工作时,他们并不是说你一句“嘿,我想让你写一篇 blog post”,
Speaker 125:28 - 25:44
They're just like, cool. I made it. Here it is. Like, a good ghostwriter is gonna get to know you and really under you're gonna you're gonna work together to figure out what's in your head about it, but also shape what's in your head. Like, it's not just, oh, I I can see it, and, like, I'm they need to get it out of you.
Speaker 125:28 - 25:44
然后它就说,行,我写好了,给你。一个好的 ghostwriter 会先了解你,真正去理解你。你们会一起合作,弄清楚你脑子里关于这件事的想法,同时也会塑造你脑子里的那些想法。就像,这不只是“哦,我看见了,然后我……”——它们需要把这些东西从你身上引出来。
Speaker 125:44 - 26:06
Like, you're you're actually making it together. And in order to do that, you have to have a really good basic interview process to uncover things. And that sounds like you found that too. And I think that's really, really interesting and really important for people who are thinking about how do I get the best out of AI? Actually, stop for a second and, like, let it ask it to understand you first.
Speaker 125:44 - 26:06
就像,你们实际上是在一起创作。而要做到这一点,你必须有一个非常好的基础 interview process(访谈流程)来挖掘这些内容。听起来你也发现了这一点。我觉得这对那些在思考“我怎样才能把 AI 的能力发挥到最好”的人来说,真的非常有意思,也非常重要。其实先停一下,让它先通过提问来理解你。
Speaker 226:07 - 26:32
Yeah. One of the things I say to a lot of people is just, like, I think partially because we call it generative, there's entirely too much focus on its ability to write and not enough focus on its ability to read. It's like its ability to read is incredible, right? And I think arguably sort of like much more useful on a day to day basis. Like we produce artifacts far less frequently than we just like think about things.
Speaker 226:07 - 26:32
对。我经常对很多人说的一点是,我觉得部分原因在于我们把它叫作 generative(生成式),所以大家把过多注意力放在它的写作能力上,而没有给它的阅读能力足够的关注。它的阅读能力其实非常惊人,对吧?而且我认为,可以说它在日常层面上甚至更有用得多。因为比起产出 artifacts(成果物),我们更经常做的其实只是思考问题。
Speaker 226:33 - 26:56
And so yeah, I do this a lot. This is definitely a complaint I have about all the models is like, you know, even when you very specifically tell it not to try to do your work, it still often still tries to do your work. And so you have to like really, really be like, no. I said no. Like, I think, actually, if we look at so here.
Speaker 226:33 - 26:56
所以,是的,我经常这么做。这绝对是我对所有 model 的一个抱怨:就是,你知道,即便你非常明确地告诉它不要试图替你做事,它还是经常会试着替你做。所以你必须非常、非常明确地说,不。我说了不要。就像,我觉得,其实如果我们看一下这个,那么这里——
Speaker 226:56 - 27:10
Critical. When Noah says he's just collecting source materials or I do not under any circumstances want you to try to write it. Take this literally. Do not create outlines, drafts, or any versions of talks slash writing. Only gather and organize the requested materials.
Speaker 226:56 - 27:10
关键。当 Noah 说他只是在收集 source materials(源材料),或者“在任何情况下我都不希望你试图去写它”时,要按字面理解。不要创建 outlines(提纲)、drafts(草稿),也不要生成任何版本的演讲稿或写作内容。只收集并整理所要求的材料。
Speaker 127:10 - 27:12
So good. I love it.
Speaker 127:10 - 27:12
太好了。我很喜欢。
Speaker 227:12 - 27:46
Yeah. This is like but, yeah, I think, you know, I think we all we all experience that. And, you know, I mean, I I do hope over time that that sort of gets baked into the models. I think it's a very interesting tension that exists with the model companies because, like, obviously, you know, like, this sort of a lot of the economic input output is sort of measured in the artifacts that it produces. And so I think it's very oriented, and, you know, I I suspect that part of it is just like that sort of the helpful assistant thing has, like, come to be a sort of meme that is probably self ingested.
Speaker 227:12 - 27:46
对,这就像是——不过,是的,我觉得,你知道,我觉得我们都会有这种体验。而且,你知道,我确实希望随着时间推移,这种东西会被逐渐 baked into(内化进)模型里。我觉得这在 model companies(模型公司)那里是一个很有意思的张力,因为很显然,你知道,这里面很多经济上的 input output(输入输出)某种程度上都是通过它产出的 artifacts(产物)来衡量的。所以我觉得它会非常朝那个方向倾斜。而且,你知道,我怀疑其中一部分只是那种 helpful assistant(乐于助人的助手)设定,已经变成了一种 meme(模因),甚至可能被模型自己反复摄入了。
Speaker 227:47 - 27:57
But, yeah, it's it's, I think for those of us who are trying to do more interesting things with these models, it it becomes a real barrier to work.
Speaker 227:47 - 27:57
但是,是的,我觉得对于我们这些想用这些模型做更有意思事情的人来说,这确实会变成一个很实际的工作障碍。
Speaker 127:58 - 28:09
Totally. Okay. So now I wanna think about when you're using the thinking agent, did you say it, like, it's is it outputting some sort of summary of what you've come to into a particular place?
Speaker 127:58 - 28:09
完全同意。好,那我现在想问的是,当你在用那个 thinking agent(思考型 agent)时,你刚才是说,它会不会输出某种总结,把你已经推进到某个位置的内容整理出来?
Speaker 228:09 - 28:22
Or Yeah. So that thinking agent is sort of told to, as it asks me questions, kinda make notes about the questions that it's asking me and keep a kind of running log of what I'm uncovering and how I'm thinking about it and all those sorts of things.
Speaker 228:09 - 28:22
对。所以那个 thinking agent 基本上会被告知:在它向我提问的时候,一边对它问我的问题做些记录,一边持续保留一份 running log(持续日志),记下我正在 uncovering(挖掘)出什么、我是怎么思考的,以及诸如此类的内容。
Speaker 128:22 - 28:39
Got it. And then, you know, you come back the next day and you're like, oh, I just wanna go down this rabbit hole on x y z thing about the, you know, this wild bill guy. And that you start in a new chat, maybe with it, maybe with the sub vision, maybe maybe not, and that becomes its own new file on that topic?
Speaker 128:22 - 28:39
明白了。然后,比如第二天你回来,心想,哦,我现在只想顺着这个关于 wild bill 这个人的 x y z 问题继续深挖。那你就会重新开一个新的 chat(对话),也许还是跟它,也许是跟 sub vision,也许不是,然后这就会变成一个关于那个主题的全新文件?
Speaker 228:39 - 28:56
Yeah. Exactly. So like I I there's the the Wild Bill stuff started as like deep research in CHIPT, and I, you know, had to go out. And I'm reading the Wild Bill book right now. There's a, like, one sort of particularly famous biography of him.
Speaker 228:39 - 28:56
对,完全是这样。所以比如说,我那个 Wild Bill 相关的东西一开始是作为 CHIPT 里的 deep research(深度研究)开始的,然后我,你知道,中间还得去查别的资料。我现在正在读那本写 Wild Bill 的书。有一本,算是关于他特别有名的 biography(传记)。
Speaker 228:56 - 29:59
And, you know, I'm kinda thinking about the bits and pieces and trying to make and I I think I made a kind of interesting connection in there, where, you know, a big part of what sort of he seems to have been after with the OSS and and, you know, the sort of inspiration for the special forces was, like, empowering individuals. You know, that's sort of like the theme of that manual was, like, obviously, empowering citizen saboteurs, but also, you know, I think a big part of the special forces is, like, you know, having kind of, like, incredible operators at the edge who, you know, obviously operate within a sort of command and control hierarchy, but, like, have a ton of autonomy to move and execute independently because they're kind of they have all the things that they need. And, so, you know, in all of that WildBill research, I kind of went back to this, and I was like, is this, like, an interesting way to connect all these ideas that, like, maybe kind of there's a you know, and again, this is still early. I have not, like, solidified these conclusions. This is like, you know, the regular kind of writing process.
Speaker 228:56 - 29:59
然后,你知道,我一直在琢磨那些零零碎碎的部分,试着把它们串起来。我觉得我在里面可能建立了一个挺有意思的联系:你知道,他通过 OSS,以及后来 special forces(特种部队)的那套灵感,似乎很大一部分是在追求 empowering individuals(赋权个体)。你知道,这差不多就是那本 manual(手册)的主题——显然,一方面是赋权 citizen saboteurs(平民破坏者),但另一方面,我觉得 special forces 的一个重要部分也是:在最前线配备那种能力非常惊人的 operators(执行人员),他们当然是在某种 command and control hierarchy(指挥控制层级)之内行动,但又拥有大量自主性,可以独立机动、独立执行,因为他们本身就具备所需的一切东西。所以,在做那些 Wild Bill 研究的时候,我某种程度上又回到了这一点,我就在想,这会不会是一种有意思的方式,把所有这些想法连接起来——也许这里面确实有某种关联。当然,再说一次,这还很早。我还没有真正把这些结论固定下来。这就是那种很常规的写作过程。
Speaker 229:59 - 30:39
Right? But it's like, well, I think there's this idea that, like, you know, fundamentally well, I know, you know, fundamentally, one of the big things with transformers is it moved us from sequential based models to models that can act in sort of paralyze their work better. And that obviously allowed us to have much more powerful and interesting models and has arguably kicked off this entire sort of revolution of what's going on and what we both do for a living. And so I think there's this kind of interesting connection. So that was what I was playing with, I think, here was like, oh, maybe there's this connection between kind of sequential processing to this kind of parallel.
Speaker 229:59 - 30:39
对吧?但我是觉得,好像有这样一种想法:你知道,从根本上说,transformer 的一大关键点,是它让我们从 sequential based models(序列式模型)转向了能够更好地以某种 parallel(并行)方式开展工作的模型。而这显然让我们拥有了更强大、也更有意思的模型,甚至可以说,正是它开启了现在这一整场革命,以及我们两个人赖以为生的这份工作。所以我觉得这里面有一种很有意思的联系。我当时在这里琢磨的就是:哦,也许从这种 sequential processing(顺序处理)到这种 parallel(并行)之间,存在某种关联。
Speaker 230:39 - 31:00
And then there's this connection to bureaucracy. And then there's this connection to Wild Bill, who seems to be have been very much about sort of, like, working within a system, but, having autonomy at the edges. And so that's kind of what I was playing with and just kind of taking notes. And then, yeah, I would jump out and be like, oh, well, actually, haven't figured out a conclusion yet. Let me start the conclusion section, and I'll just sort of get that going on the side.
Speaker 230:39 - 31:00
然后它又和 bureaucracy(官僚体系)产生了联系。接着它又和 Wild Bill 产生了联系;在我看来,Wild Bill 这个人似乎非常强调一种做法:在一个系统内部运作,但在边缘地带保有 autonomy(自主性)。所以我当时就是在玩味这个思路,一边随手记笔记。然后,没错,我也会跳出去想:哦,不过,其实我还没得出结论。那我先把 conclusion(结论)这一节开出来,让它先在旁边跑着。
Speaker 231:02 - 31:17
And then, you know, I I have a job, so I can't be doing this all the time. So it's also like you interrupt yourself, and it's really nice to be able to come back and be like, you know, can you catch me up on the last three days of research?
Speaker 231:02 - 31:17
然后,你知道,我还有工作,所以也不可能一直做这个。所以现实情况也是,你会不断打断自己,而这时候如果能回来就说一句:“你能帮我总结一下过去三天的研究吗?”那就特别好。
Speaker 131:17 - 31:20
Oh, I love that question. That's so cool.
Speaker 131:17 - 31:20
哦,我喜欢这个问题。太酷了。
Speaker 231:21 - 31:53
And so, yeah, you can just kind of go in and be like, can you catch me up on the last few days of research? And it's just going to go read all this stuff, right? And again, it's like, I think the point you made earlier about the, you know, go find relevant sources. It's like, I find a lot that the difference between the people are getting a lot of this right now is part of it is just like, you have a good feel for where the edges of the capabilities of these models are, and you sort of like encourage them to work within those capabilities. Like, this is an incredibly easy you know, it's like we know what it's gonna do here.
Speaker 231:21 - 31:53
所以,对,你完全可以直接进去问一句:“你能帮我总结一下过去几天的研究吗?”然后它就会去把这些东西全读一遍,对吧?而且再说一次,我觉得你前面提到的那一点——去找相关来源——很关键。我的感觉是,现在真正把这些东西用得很好的人,区别之一就在于:他们很清楚这些模型能力的边界大概在哪里,然后会有意识地鼓励模型在这些能力范围内工作。像这种任务就特别简单,你知道,就像是:我们很清楚它在这里会怎么做。
Speaker 231:53 - 32:15
Right? Like, could write all these Unix commands. It's just gonna go find a bunch of files in this directory, and it's gonna look at them by date, and it's gonna look at all the files created in that project over the last you know? And we know it's gonna be able to do that. And so it's saying, you know, the major breakthrough day was this idea of bureaucracy as positional encoding, which is very much a work in progress idea, but I kind of like it.
Speaker 231:53 - 32:15
对吧?它可以写出这些 Unix commands(Unix 命令);它就是会去这个目录里找一堆文件,然后按日期查看它们,再去看这个项目在最近这段时间里新建的所有文件——你懂吧?而且我们知道,它是有能力做到这些的。所以它会说,那个最重要的突破日,是提出了“bureaucracy 作为 positional encoding(位置编码)”这个想法;这当然还是一个 very much a work in progress(非常处于进行中)的想法,但我还挺喜欢它。
Speaker 232:16 - 32:45
But, you know, so it's just like, it's pretty amazing also to just be able to kind of revisit deep work like this, right? Where, you know, you know you're gonna break your flow. You're not and it's like, it's often, I find whether it's code or writing, the hardest part is like just picking it up again, because you're out of it. And so just to kind of kickstart that process is sort of amazing. I think what I was playing with here is this idea that bureaucracy was actually like an innovation, right?
Speaker 232:16 - 32:45
不过,你知道,所以我觉得,能够像这样重新进入 deep work(深度工作)也真的很惊人,对吧?因为你知道自己的 flow(心流)一定会被打断;你不可能一直不断下去。而且我常常发现,不管是写 code(代码)还是写文章,最难的部分其实都是重新把它捡起来,因为你已经脱离那个状态了。所以仅仅是帮你把这个过程重新启动起来,就已经相当了不起了。我当时在这里琢磨的是这样一个想法:bureaucracy 其实曾经是一种创新,对吧?
Speaker 232:45 - 33:34
That like, we look at bureaucracy as a negative, and generally we talk about it as a negative, and I think often it is a negative. You know, bureaucracy was a sort of like huge innovation for how companies operate. Right? And ultimately it sort of represents kind of hierarchy and structure and a whole bunch of things that are like actually like pretty positive for operating at a large scale. And so, know, again, my kind of whole thesis on AI around all this bureaucracy stuff is that what's interesting about it is that as opposed to kind of past technologies, which kind of forced you to make a decision about whether you wanted to kind of like use your existing sort of structure and build that technology into your existing structure or adopt the new structure.
Speaker 232:45 - 33:34
也就是说,我们会把 bureaucracy 看成负面的东西,而且通常谈起它时也的确是负面的;我觉得很多时候它也确实是负面的。但你知道,bureaucracy 在公司运作方式上,其实曾经是一项巨大的创新。对吧?归根结底,它代表的是 hierarchy(层级)、structure(结构)以及一整套东西,而这些东西对于大规模运作来说,实际上相当正面。所以,再说回我关于 AI 和这整套 bureaucracy 问题的核心论点:它有意思的地方在于,不同于过去那些技术——过去的技术往往会逼你做一个决定:你到底是要沿用现有结构,把那项技术嵌入现有结构中,还是要转而采用一种新的结构。
Speaker 233:34 - 33:59
And most of the time, the new software required you adopted the new structure, and that's why so many sort of software projects failed for so long. At least that's sort of part of what I think. And, you know, I think part of what's interesting about AI, what I find so interesting is like that you can kind of keep letting everybody work in whatever way they want. You know, it's like a classic problem inside large companies is like one team wants to use Asana and one wants to use Jira and one wants to use Linear. Right?
Speaker 233:34 - 33:59
而且大多数时候,新软件会要求你采用新的结构,这也是为什么这么多软件项目长期以来都会失败。至少这是我部分的看法。并且,我觉得 AI 有趣的一点、也是我觉得特别有意思的一点在于,它某种程度上可以让每个人继续按照他们想要的方式工作。你知道,大公司内部一个很典型的问题就是:一个团队想用 Asana,一个想用 Jira,一个想用 Linear。对吧?
Speaker 233:59 - 34:32
And so then at some point, there's like a there's a there's a huge project and they bring in some big consulting firm and they decide they're gonna all centralize on this one thing. And now two thirds of the company is unhappy. And, like, they've all made sacrifices, and, you know, you're sort of in this, like, very non ideal state. And I think what's really interesting about AI, and I I this is a little more sort of theoretical because I think we're so early in this, is that like, I think it's very possible you could just say, well, everybody just keep doing what you're doing. We're going to stick sort of some models in the middle.
Speaker 233:59 - 34:32
所以到了某个时候,通常就会出现一个大项目,他们请来某家大型咨询公司,然后决定要把所有东西都集中到这一个系统上。结果就是,公司里三分之二的人都不高兴。而且,大家都做出了妥协,于是你就处在一种非常不理想的状态里。我觉得 AI 真正有意思的地方在于——当然这更偏理论一些,因为我们还处在非常早期的阶段——我认为很有可能,你可以直接说:好吧,大家继续按你们现在的方式做事。我们只是在中间放一些 model(模型)。
Speaker 234:32 - 34:55
They don't care what you use because it's all just data structures to them. And so we can then have this sort of central thing. And if, you know, when we talked about Percolate at the beginning, Percolate was a content marketing platform, worked with very large companies. So it was an enterprise software product. And it's like, at the end of the day, this is sort of the fundamental challenge of enterprise software is about adoption and change management.
Speaker 234:32 - 34:55
它们不在乎你用什么,因为对它们来说,那都只是 data structure(数据结构)。这样一来,我们就可以有这样一个中央层。你知道,我们一开始谈到 Percolate 时,Percolate 是一个 content marketing platform(内容营销平台),服务的是非常大的公司。所以它是一款 enterprise software(企业软件)产品。归根结底,这其实就是 enterprise software 的根本挑战:adoption(采纳)和 change management(变更管理)。
Speaker 234:55 - 35:29
I just think, I think and I hope, and again, this is sort of the optimist in me that AI kind of lets us just not worry so much about these things. And and rather than trying to make everybody change the ways that they work, kind of let them work in these ways and let AI sort of it's my I I call it my Thomas's English muffin theory of AI, which is that it, like, gets into the nooks and crannies. And so yeah. That's so anyway but I have no idea what bureaucracy as positional encoding means yet. I'm hoping I figure it out in the next two weeks before I have to give this talk.
Speaker 234:55 - 35:29
我只是觉得,我也希望——再说一次,这可能是我身上比较乐观的一面——AI 某种程度上能让我们不用再那么担心这些事情。与其试图让每个人都改变他们的工作方式,不如让他们继续用这些方式工作,再让 AI 去——这是我所谓的 Thomas's English muffin theory of AI——也就是它会钻进那些边边角角、缝隙和细部里。所以,是的。总之,不过我现在还完全不知道 bureaucracy as positional encoding 到底是什么意思。我希望在接下来两周、也就是在我必须做这场演讲之前,能把它想明白。
Speaker 135:30 - 35:53
I think no. But I I think the point you just made is is totally right, and it's actually not it doesn't have to be theoretical. Like, I I've been seeing this too inside of Every, and I've been meaning to write about it. And the the place that it's been coming up is we have so inside of every we run, like, six different products, and we have 15 people. So it's it's like a crazy product to head count ratio.
Speaker 135:30 - 35:53
我觉得不是。但我认为你刚才说的那个点完全正确,而且其实不一定非得停留在理论层面。就像,我最近也在 Every 内部看到这种情况,而且我一直想把它写出来。这个问题出现的场景是:我们在 Every 内部同时运营大概六个不同的产品,而我们只有 15 个人。所以这是一个非常夸张的 product-to-headcount ratio(产品数量与人数比)。
Speaker 135:55 - 36:20
And what's interesting is I really like doing things in a in a bottom up way. So everyone each of the products has its own stack. We're not, like, centralized into a particular stack. Each, you know, GM that runs a product, like, just has made a decision about do I run Rails or TypeScript or whatever. And what I'm seeing happen, which is very cool, is a lot of the different products are running into similar things they want to solve for.
Speaker 135:55 - 36:20
有意思的是,我很喜欢用一种 bottom-up(自下而上)的方式做事。所以每个产品都有自己的 stack(技术栈)。我们并没有集中到某一个统一的 stack 上。每个负责产品的 GM,都只是自己决定:我是用 Rails,还是 TypeScript,或者别的什么。而我现在看到的、非常酷的一点是,很多不同的产品都会遇到一些相似的问题,都是它们想要解决的。
Speaker 136:20 - 36:34
So an easy example is we have one product called Sparkle, which is a little bit like a finder replacement or a spotlight replacement. So it it it organizes your files, and then it implements really fast spotlight search.
Speaker 136:20 - 36:34
一个简单的例子是,我们有一个产品叫 Sparkle,它有点像 finder replacement 或者 spotlight replacement。也就是说,它会整理你的文件,然后提供非常快的 Spotlight 搜索。
Speaker 236:35 - 36:36
I'm a user. I like it.
Speaker 236:35 - 36:36
我是用户。我喜欢它。
Speaker 136:36 - 36:44
Okay. So then you you know. And so that's really cool. And agentic search coming soon. Check it out.
Speaker 136:36 - 36:44
好的。然后你知道的,这真的很酷。agentic search(智能体式搜索)也快来了。去看看吧。
Speaker 136:44 - 37:41
And and we're just building a new product, new GM, new stack called Para, which is essentially an in in house counsel. So it's short for paralegal, not para like, you know, Tiago Forte Para. And the whole job for Para is just, you know, take all of your legal files, and whenever I have a question and be like, okay, do do we ever sign this contract, or what's the employee agreement template, or whatever, it just gives you the answer, and it's just Claude code sitting on top of a directory. And and a thing that we needed to implement for that is this sort of like fast file file search. And what's really interesting is, historically, if we wanted to reuse the stuff that we learned from implementing Sparkle's file search, that would have to be abstracted out into this modular library that anyone can use, and then we have to be on the same platform and, like, all those things.
Speaker 136:44 - 37:41
还有,我们正在做一个新产品,一个新的 GM、一个新的 stack,叫 Para,本质上它就是一个 in-house counsel(内部法务)。所以它是 paralegal 的缩写,不是那个 para——你懂的,不是 Tiago Forte 的 PARA。Para 的整个工作就是,把你所有的法律文件都收进去,然后每当我有问题时,比如“好,我们以前签过这份合同吗?”或者“员工协议模板是什么?”之类,它就直接给你答案。而它本质上就是放在一个目录之上的 Claude code。我们为此需要实现的一项能力,就是这种快速的文件搜索。很有意思的是,按历史上的做法,如果我们想复用在实现 Sparkle 文件搜索时学到的东西,那就得先把它抽象成一个谁都能用的模块化 library(库),然后还得运行在同一个平台上,诸如此类。
Speaker 137:41 - 38:11
Right? And what we did instead is we just added Preeti, who's the developer for for for Pera right now. We just added her to the Sparkle repo. And I was just like, just ask Claude code to figure out how it works and just do your own version. And so you get this, like, sort of tacit code sharing where we all get better, but without having to do the work of abstracting and modularizing everything because the the percentage of things that you can do that for are pretty low because it's a it's a heavy lift.
Speaker 137:41 - 38:11
对吧?但我们实际做的是,直接把现在负责 Pera 开发的 Preeti 加进了 Sparkle repo。我当时就说,直接让 Claude code 去弄清楚它是怎么工作的,然后你自己做一个版本。所以你会得到一种有点像默会式的代码共享:大家都能一起变得更强,但又不用付出把所有东西都抽象化、模块化的成本,因为真正适合那样做的事情比例其实很低,毕竟那是个很重的工程。
Speaker 138:11 - 38:22
And I'm seeing that happen all the time where just having a bunch of repos that are all solving similar problems but in different environments in different ways, you everyone gets more productive because AI can kind of translate.
Speaker 138:11 - 38:22
我一直看到这种情况在发生:只要有一堆 repo,它们都在不同环境里、用不同方式解决相似的问题,大家的生产力就都会提高,因为 AI 某种程度上能帮你做“翻译”。
Speaker 238:23 - 39:03
I've one thing we've done there, we also we so at Alethic, we do a whole bunch of building for, very large brands. And so we sort of build all kinds of AI things. And, you know, so we we've got lots of sort of internal and external repos, and we frequently have the same thing. And actually, I've used the GitHub MCP, a few times for that same purpose, which is just like, you know, you're just in cursor or cloud code or whatever, and you're like, hey. Can you go, like, look up, we run we've got an internal tool called Intelligence that just sort of is a wrapper around a whole bunch of stuff that we use, right?
Speaker 238:23 - 39:03
我们在那边做过的一件事是——另外,在 Alethic,我们也会为非常大的品牌做很多开发。所以我们会构建各种各样的 AI 东西。于是,我们手上有很多内部和外部 repo,而且经常也会遇到同样的问题。实际上,为了这个目的,我也用过几次 GitHub MCP。场景就是,你在 cursor 或 cloud code 之类的环境里,然后你会说,嘿,能不能去帮我查一下——我们内部有个工具叫 Intelligence,它基本上就是把我们用的一大堆东西包了一层 wrapper(封装),对吧?
Speaker 239:03 - 39:45
So it's like got some CRM stuff, and it's just been a fun place to build the things that we need to run our company. But it's also a good place to kind of experiment and explore and figure out solutions to interesting problems. And so I'll frequently be like, oh, can you go to like, just go look at the intelligence repo and, know, look at how I implemented that thing there and take those sort of best practices and just pull them over. And yeah, I think that stuff again, that's where I really do believe in this idea. Like one of my, whenever we have like a client meeting or something, my first, the question, the icebreaker I always use is what was your moment with AI?
Speaker 239:03 - 39:45
所以它里面有一些 CRM 的东西,而且它一直是个很有意思的地方:我们会在那里构建那些经营公司所需的工具。但它同时也是个很适合做实验、探索、并找出有趣问题解决方案的地方。所以我经常会说,哦,你能不能去——比如直接去看一下 intelligence repo,看看我当时在那里是怎么实现那个东西的,把那些 best practices(最佳实践)提炼出来,然后直接搬过来。对,我觉得这类事情——还是那句话,这正是我真正相信这个想法的地方。比如说,每次我们有客户会议之类的时候,我第一个会问、也是我总拿来破冰的问题就是:你和 AI 的“那个时刻”是什么?
Speaker 239:45 - 40:03
And, mine was, I mean, it was probably not the very first, but it's the one that sort of, I think was most impactful was I was, I got access to build a ChatGPT plugin. Remember when plugins came out in like, two and a half years ago or something now.
Speaker 239:45 - 40:03
而我的那个时刻是——当然,可能不是最最早的第一次,但我觉得影响最大的是那一次:我当时拿到了权限,可以做一个 ChatGPT plugin。还记得 plugins 刚出来的时候吗?大概是两年半前之类的,现在想想。
Speaker 140:03 - 40:04
You mean fifty years ago?
Speaker 140:03 - 40:04
你是说五十年前吗?
Speaker 240:04 - 40:26
Fifty years ago. And, you know, I like you, I've I've written a lot of software in my life and I, you know, you know what you do when you like get access to something new. It's like, I've got to go read the API docs and figure it out. And, you know, I'll like, there's a gonna be a contract. And, you know, as long as you follow that contract, it works.
Speaker 240:04 - 40:26
五十年前。你知道,我跟你一样,我这一生写过很多软件,而且你知道,当你获得某个新东西的访问权限时,你会怎么做。感觉就是,我得去读 API docs,弄明白它。然后,你知道,通常会有一个 contract。只要你遵守那个 contract,它就能工作。
Speaker 240:27 - 40:49
And I go read the plugin spec. And it basically is like, oh, you just stick a manifest dot JSON file in the root directory of your application. And in that, you describe how you want us to send you data, and you describe how you're going send it back to us, and then we'll deal with the rest. And I was just like, that's amazing. It's also like, it's how the world should work.
Speaker 240:27 - 40:49
然后我去读 plugin spec。它基本上就是说,哦,你只要把一个 manifest.json 文件放到你应用的根目录里。在那个文件里,你描述你希望我们怎么把数据发送给你,也描述你打算怎么把数据发回给我们,然后剩下的事我们来处理。我当时就觉得,这太惊人了。某种程度上,这也是世界本来就该有的运作方式。
Speaker 240:49 - 41:33
Like, I wish everything worked that way. I wish I didn't always have to adhere to the big company's contract for how to send and receive data. But also, like, I the thing that really struck me in that moment, and it's, like, been my kind of, like, rallying cry around all this stuff, is that, it's also just, like, fundamentally counterintuitive in that, like, I literally have a career's worth of intuition for how to integrate software systems. And it flipped it on its head, like, like, like quite literally 180 degrees away from my intuition of how software systems should be integrated was this thing. And that, I think since then has been my kind of thing for everybody has been like, this is just not intuitive for now.
Speaker 240:49 - 41:33
就像,我真希望所有东西都能那样工作。我真希望我不必总是去遵守大公司的 contract,按它规定的方式发送和接收数据。但同时,那个时刻真正击中我的一点,也是后来我围绕这些事情一直在呼喊的一个核心,就是:这件事在根本上也是反直觉的。因为我对于如何集成软件系统,真的是积累了整整一个职业生涯的直觉。而它把这一切彻底颠倒了过来,真的就像和我对于软件系统应当如何集成的直觉相差了 180 度。我觉得,从那之后,我一直想对每个人说的是:以现在的标准来看,这东西就是不直观。
Speaker 241:33 - 41:55
And and that's not a bad thing. It just means like you need to build intuition and like, that's what we're all just out there trying to do with it. Right? And so, you know, when I don't know, mean, part of what I like about what you're doing and, you know, even just hearing the things you're saying, but like generally what you do with the podcast and what you do with every is like, so much of it is like, we're all kind of just figuring stuff out for the first time. Right?
Speaker 241:33 - 41:55
而且这并不是坏事。它只是意味着你需要建立直觉,而这正是我们所有人都在努力做的事,对吧?所以,你知道,我也说不好,但我喜欢你们在做的一部分原因,还有,包括只是听你刚才说的这些话,以及更广义上你通过 podcast 所做的事、你通过 every 所做的事,就是其中很大一部分都在于:我们大家其实都像是在第一次摸索这些东西,对吧?
Speaker 241:55 - 42:14
And like, you know, we're like, oh, will this work? And then like all of a sudden you have this new bit of intuition for what these things can do and what a computer that is not deterministic looks like. And that's I think that's just what we're all doing all the time. And that's why it's so fun, I think.
Speaker 241:55 - 42:14
而且你知道,我们会想,哦,这能行吗?然后突然之间,你就对这些东西能做什么、以及一台不是 deterministic(确定性的)计算机是什么样子,有了一点新的直觉。我觉得这就是我们一直在做的事。这也是为什么我觉得它这么有趣。
Speaker 142:14 - 42:27
That's why I love this moment because, like, you just have a weird idea, and you're like, has anyone done this before? And and it's like, no. And it's not a it's not a complicated idea. It's just it's just a new whole new territory. You know?
Speaker 142:14 - 42:27
这就是为什么我喜欢当下这个时刻,因为你会冒出一个奇怪的想法,然后你会想,以前有人做过这个吗?结果答案是,没有。而且这还不是什么复杂的想法。只是因为这是一整片全新的疆域。你知道吧?
Speaker 242:28 - 42:57
I yes. I I think about that all the time. And I think actually, like, I think one of the really damaging sort of things out there is that I think there are a lot of people who think we're way further along in this than we are. And so, you know, I think particularly the people who are sort of scared, you know, we run, we work with like Fortune 50 companies. And so, you know, when we're sort of like out there and we're talking to people inside the organization, a lot of people feel like they've already been left behind.
Speaker 242:28 - 42:57
对,是的。我一直都在想这件事。而且我实际上觉得,外面有一种很有害的倾向,就是很多人以为我们在这件事上已经走得比实际远得多了。所以,你知道,我觉得尤其是那些有点害怕的人——我们和 Fortune 50 companies 合作——所以当我们在外面、和组织内部的人交流时,很多人会觉得自己已经被甩在后面了。
Speaker 242:57 - 43:44
And it's like, no, you can like literally go sign into ChadGPT and like do something like nobody's thought about doing with this thing yet because there's just so much white space to explore and you might discover some totally new way of using it or like totally new trick. I don't know. That's and, you know, I think to be fair to some people that's sort of very intimidating and I don't think by and large, the models do any favors to themselves in helping those people get their feet wet in that. Like, you know, I think people go on there and they, it's like you ask it to write you a poem, and then it writes you a poem, you're like, okay, it wrote me a poem. But I don't know, that feeling that feeling of, yeah, it's like being on the frontier, right?
Speaker 242:57 - 43:44
但其实不是,你真的完全可以现在就登录 ChadGPT,做出一些此前根本没人想到可以用这东西去做的事,因为还有太多 white space(待探索的空白地带)可以探索,而你也许会发现某种全新的使用方式,或者某个全新的技巧。我不知道。还有,你知道,公平地说,对一些人来说这确实很吓人。而且我总体上不觉得这些 models 能很好地帮到他们,让他们更容易上手。就像,你知道,人们上去之后,感觉就是你让它给你写首诗,然后它给你写了一首诗,你会想,好吧,它给我写了首诗。但我不知道,那种感觉,那种“对,就是像站在 frontier(前沿)上一样”的感觉,对吧?
Speaker 143:44 - 44:18
Totally. And, yeah, I I think that your point about intuitions and getting intuitions is the big thing. And I think people what we don't realize is when you're dealing with something fundamentally new, you you can't trust, like, how you reason about it without experiencing it because you have to build the intuition in order to be able to reason about what it means and and how it fits in and whether it works or not. And we're just not used to that because we're used to reasoning about things we already have an intuition for. And and I think that's why, like, when you first see maybe when you first saw ChatGeeb TV, like, oh my god.
Speaker 143:44 - 44:18
完全同意。然后,是的,我觉得你关于 intuition(直觉)以及获得 intuition 这一点,才是最关键的。我想人们没有意识到的是,当你面对某种从根本上全新的东西时,如果你没有亲身体验过它,就不能相信自己对它的推理方式;因为你必须先建立起那种 intuition,才能进一步推理它意味着什么、它如何融入现有事物,以及它到底是否有效。而我们就是不习惯这一点,因为我们平时习惯于推理那些自己已经有直觉的东西。所以我觉得,这也是为什么,比如你第一次看到 ChatGeeb TV 的时候,会觉得,天啊。
Speaker 144:18 - 44:27
It can do everything. Like, we're not gonna have jobs in a year. And now we're, like, three years in, and we're like, yeah. It's awesome. And jobs are complicated.
Speaker 144:18 - 44:27
它什么都能做。感觉像是,一年之内我们就都要失业了。而现在大概三年过去了,我们会说,嗯,它确实很厉害。但工作这件事是很复杂的。
Speaker 144:27 - 44:43
There's a lot of complex stuff that we do. You know? And I I love I love kind of that, you know, in order to build the intuition, all you have to do is is use it, and that just by using it, you're already kind of on the edge for now. And, yeah, I think that's the best.
Speaker 144:27 - 44:43
我们做的事情里有很多复杂的部分,对吧?而我很喜欢这样一种感觉:为了建立那种 intuition,你要做的其实只是去用它;而只要你开始用它,你现在就已经某种程度上站在前沿了。对,我觉得这就是最好的方式。
Speaker 244:43 - 45:21
There's apparently there's a a German word called Fingerspitzengefuhl. Of course, there is. Building fingertip feeling, and that's been my just because I can't resist also, I'm in that whole, in sort of the realm that you're discussing, like, I've been trying to do a lot of analogy analogizing, right? It's sort of like, and I think, you know, that's really hard and, you know, but my two that have sort of stuck the most, one is just, I watch a lot of YouTube with my kids, and we watch this channel called Veritasium. It's a science channel.
Speaker 244:43 - 45:21
显然,德语里有个词叫 Fingerspitzengefuhl。那当然了,德语总会有这种词。大概就是建立一种“指尖感觉”。而这也一直是我的——因为我也忍不住会这样想——我在你刚才讨论的这个领域里,也一直在努力做很多 analogy(类比),对吧?有点像是——而且我觉得,这其实非常难——不过有两个类比是最让我记得住的。一个是,我经常和孩子们一起看 YouTube,我们会看一个叫 Veritasium 的频道,是个科学频道。
Speaker 145:21 - 45:22
I love Veritasium.
Speaker 145:21 - 45:22
我很喜欢 Veritasium。
Speaker 245:22 - 45:46
Yeah. It's great. And he did one where he built a bike that locks out left if you try to turn right and locks out right if you try to turn left. And what he's proving is that you can't actually turn a bike left unless you can turn it right, which none of us would think about when we ride a bike because it's all just second nature and intuition. But it's also why you can't explain to a child how to ride a bike.
Speaker 245:22 - 45:46
对,特别棒。他做过一期视频,造了一辆自行车:你如果想往右转,它就把向左转锁死;你如果想往左转,它就把向右转锁死。他想证明的是,实际上如果你不能先向右转,你就根本没法把自行车转向左边。我们平时骑车时根本不会想到这一点,因为那已经完全变成了第二天性和 intuition。但这也是为什么,你没法靠讲解来教一个孩子怎么骑自行车。
Speaker 245:46 - 46:15
They just have to get on it and feel it. And so, you know, I really that video is amazing, and it's that channel is amazing. But I've thought a lot about that. Then the other one, which is a sort of deeper cut, is there's an amazing book about quantum physics called Beyond Weird by Philip Ball. And the thesis of the book is basically that there's nothing particularly strange about quantum physics that we We like.
Speaker 245:46 - 46:15
他们只能自己骑上去,亲自去感受。所以,那个视频真的很精彩,那个频道也非常棒。我一直反复想到这件事。然后另一个类比,就更冷门一些,是 Philip Ball 写的一本关于 quantum physics(量子物理)的很棒的书,叫 Beyond Weird。这本书的核心观点基本上是,quantum physics 并没有什么特别奇怪的地方,是我们——
Speaker 246:15 - 46:34
Have a very good understanding of it. Like, we wouldn't be talking right now. We wouldn't be on computers. We wouldn't have phones if we didn't have, like, a very good grasp of the mechanics that exist underneath it. And his thesis in the book essentially is that, like, what's really lacking is the vocabulary because like we all exist in a Newtonian world, not in a quantum one.
Speaker 246:15 - 46:34
其实对它理解得已经非常好了。要不是这样,我们现在根本不可能在这里交流;我们不会有 computer(计算机),也不会有 phone(手机),如果我们没有非常扎实地掌握它底层存在的那些 mechanics(机制)的话。而他在书里的核心论点本质上是:真正缺失的其实是 vocabulary(词汇),因为我们所有人都生活在一个 Newtonian(牛顿式)的世界里,而不是一个 quantum(量子)的世界。
Speaker 246:34 - 47:01
And so we all have words that reflect the sort of deterministic processes of that macro universe. And I think a lot about that. I have not, like, fully been able to sort of pull that string all the way to AI, but I feel like there's a real connection there because I think that there's just something really weird about using probabilistic computers. Like, we're not used to using things that, like, you ask them the same question twice, and they have different answers. Like, that's very strange.
Speaker 246:34 - 47:01
所以,我们其实都有一些词语,能够反映那个宏观宇宙中那类 deterministic(确定性的)过程。我经常会想这件事。我还没有,算是,完全把这条线一路理到 AI(人工智能)上,但我感觉两者之间确实有很强的联系,因为我觉得,使用 probabilistic(概率性的)计算机这件事本身就非常奇怪。比如,我们并不习惯使用这样的东西:你把同一个问题问它两次,它却给出不同的答案。这真的很反常。
Speaker 247:01 - 47:19
We're not used to I'm not used to writing code where you can tell the larger company how you want them to send you data, and they can just do it. Like, these are not normal things that any of us have lived with in our lifetimes. And so, of course, it takes some time for us to adjust.
Speaker 247:01 - 47:19
我们不习惯——至少我不习惯——写这样的代码:你可以告诉一家更大的公司,希望他们如何把数据发给你,而他们居然就真的能做到。像这样的事情,都不是我们这一生中曾经习以为常的正常事物。所以当然,我们需要一些时间去适应。
Speaker 147:19 - 48:15
I think so too. And I actually have a hope that language models by becoming a standard way that we use computers will create that vocabulary because we actually are quite good at dealing with probabilistic, nondeterministic things like other humans. We've just grown up in a world where because of, you know, the enlightenment and the scientific revolution and and the tools that came out of that are very much, like, deterministic, we've associated that with how we see like, that's how we see the world because of those tools and that language. And there's a whole other part of the way that we see the world, which is much more squishy and much more vibes based that has been, I think, deprioritized, especially in Western culture. That now that we have a tool that works that way, I think we'll be able to start seeing that again.
Speaker 147:19 - 48:15
我也这么觉得。而且我其实抱有一个希望:language models(语言模型)一旦成为我们使用计算机的一种标准方式,就会催生出那套词汇,因为我们其实很擅长应对 probabilistic(概率性的)、nondeterministic(非确定性的)事物,比如其他人类。只是我们成长于一个世界里——由于启蒙运动、科学革命,以及由此产生的各种工具——这些东西都非常 deterministic(确定性),于是我们把这种特性和我们的认知方式联系在了一起。也就是说,借助那些工具和那套语言,我们就是那样看待世界的。但我们看世界的方式其实还有另一大部分,它要更模糊、更凭感觉,我觉得这一部分长期以来被放到了次要位置,尤其是在西方文化里。而现在,既然我们有了一种以这种方式运作的工具,我想我们就能够重新开始看见那一部分了。
Speaker 148:15 - 48:19
And that's one of the beautiful things to me about language models is it opens up that whole world again.
Speaker 148:15 - 48:19
而对我来说,language models(语言模型)美妙的一点就在于,它再次打开了整个那样的世界。
Speaker 248:20 - 48:21
Yes. I love it.
Speaker 248:20 - 48:21
对,我很喜欢这种感觉。
Speaker 148:22 - 48:46
I do wanna go back to Claude Code. We should do the phone unless there's unless there are other things that you that that you wanna share on the computer. But the the the thing I wanna do before we get there that that's just on my mind right now is, like, you said you said, you know, you you watch this with your kids, and I'm sort of curious how like, what do your kids think about this, and how are you dealing with it with your kids?
Speaker 148:22 - 48:46
我确实想回到 Claude Code。除非你还有什么想在电脑上展示的内容,不然我们应该聊聊那个手机。不过,在到那之前,我现在脑子里最想先问的一件事是:你刚才说过,你会和你的孩子一起观察这些事情,所以我有点好奇——你的孩子们怎么看这件事?你又是怎么和他们一起处理这个问题的?
Speaker 248:47 - 49:12
Yeah. I love that question. So I've got a seven and a 10 year old. And obviously, like, I'm pretty kind of deeply embedded in this stuff, and so I've sort of exposed them quite a bit to it. You know, they don't so they will, like, occasionally use the sort of voice models, and they have a pretty good understanding, and we'll be in the car and just play games and ask questions with Grok and do those kinds of things.
Speaker 248:47 - 49:12
对,我很喜欢这个问题。我有一个七岁的孩子和一个十岁的孩子。显然,我自己在这方面投入得很深,所以我也让他们接触了不少。你知道,他们不会——不过他们偶尔会用那种 voice models(语音模型),而且他们的理解其实已经相当不错了。我们有时会在车里一起玩游戏,用 Grok 提问题,做这类事情。
Speaker 249:12 - 49:47
This weekend, actually, the first time, my 10 year old, she was really eager to be every year, my wife and her sister and brother and mom and all the cousins, and we all get together and we do Christmas together. And so it's too many presents to give to everybody. So we do a kind of like not secret secret Santa where everybody chooses one person. And my 10 year old really wanted to be the one who got to be the chooser. And, I encouraged her to, vibe code an app to do it.
Speaker 249:12 - 49:47
实际上,就在这个周末,第一次,我那个十岁的女儿——她特别想成为那个,每年我妻子、她的姐妹兄弟、妈妈,还有所有表亲们,我们大家都会聚在一起一起过 Christmas。因为人太多了,不可能给每个人都准备礼物,所以我们会玩一种有点像、但又不完全是 secret Santa 的方式:每个人抽一个对象。我那个十岁的女儿特别想当那个负责抽选的人。于是我鼓励她去 vibe code 一个 app 来做这件事。
Speaker 249:47 - 50:01
And so I just gave her my phone and V0. And honestly, was like so amazing to watch. Like, not just because it was so cool to see her do that and build it. She went through it. She was having so much fun.
Speaker 249:47 - 50:01
所以我就直接把我的手机和 V0 给了她。说实话,看着这一切真的特别惊艳。并不只是因为看到她那样上手操作、把它做出来很酷。她是真的一路做了下去,而且玩得特别开心。
Speaker 250:01 - 50:08
She did 75 revs on vZero. So she like really got it going.
Speaker 250:01 - 50:08
她在 vZero 上做了 75 次 revs(迭代版本)。所以她是真的把这件事完全推进起来了。
Speaker 150:08 - 50:09
Polished SANDAP.
Speaker 150:08 - 50:09
打磨过的 SANDAP。
Speaker 250:10 - 50:43
She also like started to get into like really interesting kind of like computer science ideas without knowing it. So in one of the things, like, the adults give presents to adults and the kids give presents to kids, but she wanted this to be a more generalized app. So she realized that, like, rather than having adults and kids, you need to call them groups. Right? And, like, you know, so she's, like, getting into data modeling and, like, all of this I'm, like, watching this conversation happen, and I just thought that was so awesome.
Speaker 250:10 - 50:43
她其实也开始接触到一些非常有意思的 computer science(计算机科学)概念,只是她自己还没意识到而已。比如在其中一个设计里,大人给大人送礼物,小孩给小孩送礼物,但她希望这会是一个更通用的 app。于是她意识到,与其用 adults 和 kids,不如把它们叫作 groups,对吧?所以你知道,她其实已经在进入 data modeling(数据建模)这些东西了。而我就在一旁看着整个思考过程发生,我真的觉得这太棒了。
Speaker 250:44 - 51:19
And, you know, also just, like, a real pet peeve of mine right now, and I've I've sort of gotten this argument with a bunch of people is like, there seems to be a big conversation that like there's a a bubble in vibe coding and like because one company or another might have too high of a valuation. And my take on that is like, I just I I could not care less what the valuations of these companies are. I think, like, fundamentally, if there's a tool that can allow a 10 year old to, like, build an app, there can't that can't be a bubble. Like, I I just, like, can't see a possibility where that is that. So anyway, that's sort of one side of it.
Speaker 250:44 - 51:19
还有一点,你知道,这是我最近一个特别在意、也已经跟不少人争论过的问题:现在似乎有一种很大的讨论,说 vibe coding 里存在泡沫,因为某家公司或者另一家公司估值可能太高了。我的看法是,我真的完全不在乎这些公司的估值是多少。我觉得,从根本上说,如果有一种工具能让一个 10 岁的小孩做出一个 app,那这就不可能是泡沫。我就是完全看不出这会是泡沫的可能性。所以不管怎样,这算是其中一个方面。
Speaker 251:19 - 52:05
The other big one for me that I've been thinking a lot about is sort of media literacy and education stuff. So, know, both at the sort of schools they go to, and then also I went to NYU and I've sort of been having more and more conversations with the dean of the school I went to there. And there's a lot of fear inside schools right now about AI and about cheating. There's a big thing, you know, so some parents in my town, wanted to have more of a conversation about it. You know, as someone who, I've thought about this a lot, but I've also just like been, I've spent my entire life thinking about search technology and its effects on culture.
Speaker 251:19 - 52:05
对我来说,另一个我最近一直在想的大问题,是 media literacy(媒介素养)和教育这类事情。所以,不管是在他们上的学校里,还是我自己上过 NYU,而且我最近也越来越多地和我当年那所学校的 dean(院长)交流。现在学校内部对 AI 和作弊都有很多恐惧。这是个很大的问题。你知道,我镇上的一些家长也想围绕这件事展开更多讨论。对我来说,我一方面确实思考过这个问题很多,另一方面,我这一辈子基本都在思考 search technology(搜索技术)及其对文化的影响。
Speaker 252:05 - 52:23
And I think I'm like relatively grounded in these things. I've I've put like, in good hours of thinking. Know that for sure. And so my take on it is like, one, that sort of you can't hide technology that won't be hidden. So it's like putting our head in the sand is not the best solution.
Speaker 252:05 - 52:23
我觉得自己在这些问题上算是相对比较 grounded(立场稳健、比较踏实)的。我确实花了很多扎实的时间去思考这些,这一点我很确定。所以我的看法之一是:你没法把一种注定藏不住的技术藏起来。所以把头埋进沙子里并不是最好的解决方案。
Speaker 252:23 - 52:49
And you know, my bigger one, though, is, like, I I was out, a friend of mine asked me to come, talk to a school two years ago about AI, out in LA. And, afterwards, I was talking to a English teacher there, and she was like, what do I do? Like, what do I do about all these kids, you know, using AI? And I was like, look. I don't really know what your job is because, like, I mean, being an English teacher for eleventh graders sounds really much harder than my job.
Speaker 252:23 - 52:49
不过我更想说的是,有个朋友两年前请我去 LA 的一所学校聊 AI。之后我跟那里的一个 English teacher(英语老师)聊天,她问我,我该怎么办?面对这么多在用 AI 的孩子,我到底该怎么办?我当时就说,你看,我其实也不太知道你的工作到底该怎么做,因为,说真的,给十一年级学生当英语老师,听起来真的比我的工作难多了。
Speaker 252:50 - 53:30
But on a really fundamental level, like, I don't actually think your job is to teach these kids to write because that's like a lifelong pursuit. I think your job is to convince them that it's worth learning to write. And so in that way, like, I'm I'm not sure that anything fundamentally changes because of AI. Like, I I think that, you know, and again, this is my very optimistic take, but like, I am I think that there are so many parts of the education system that AI really just exposes the sort of flaws in the way that we teach. Like, why are there so many tests on these kinds of things instead of encouraging thinking and learning and coming to love to write and research and whatever?
Speaker 252:50 - 53:30
但从一个非常根本的层面上说,我其实并不认为你的工作是教这些孩子写作,因为那本来就是一生都在追求的事。我认为你的工作是让他们相信,学会写作是值得的。所以从这个意义上讲,我不太确定 AI 会不会从根本上改变什么。我觉得——而且再次说明,这只是我非常乐观的看法——教育系统里有太多部分,其实只是被 AI 暴露出了我们教学方式中的缺陷。为什么会有这么多关于这类内容的测试,而不是去鼓励思考、鼓励学习,以及让人真正爱上写作、研究之类的事情呢?
Speaker 253:30 - 54:01
You know, it's like we're so focused on teaching kids the, you know, five paragraph essay, you know, while every adult who is a writer has long abandoned that. And because, like, it's all about sort of discovering that you like to write and you you know, what your own style is and how to do it. And, you know, it's like, I'm sure it's like, you know, a big part of working with AI to write is like telling it is ignoring it because you're like, no, that's not me. I'm not into that. Like, I like I I I'm totally comfortable saying really here.
Speaker 253:30 - 54:01
你知道,我们现在太专注于教孩子写那种 five paragraph essay(五段式作文)了,可实际上,任何一个真正写作的成年人,早就不这么写了。因为关键在于你要慢慢发现自己喜欢写作,知道自己的风格是什么,以及该怎么写。而且,你知道,和 AI 一起写作很大一部分,可能就在于告诉它,或者干脆无视它,因为你会说:“不,这不像我,我不喜欢这个。”比如说,我就完全可以很自在地在这里说 really。
Speaker 254:01 - 54:23
I know you don't think it's good idea, but like, I'm I'm cool with it. And so, you know, I don't know. I've been sort of having a lot of these different thoughts. I'm actually pitching a class for the '6 at NYU to kind of, the idea for it is code is essay. And my sort of point of view is like this sort of opens up this new way to express yourself.
Speaker 254:01 - 54:23
我知道你觉得这不是个好主意,但我自己是接受的。所以,我也不知道,我最近一直在想很多这类事情。其实我正在给 NYU 的 ‘6 设计一门课,课程的想法大概是 code is essay。我的基本观点是,这其实打开了一种全新的自我表达方式。
Speaker 254:24 - 54:59
And that, you know, like we have all these other ways that we celebrate to express ourselves, but code has been like long shut off from people because it's but actually, it's kind of amazing, and it lets you express yourself in all these different kinds of ways, and this is what my 10 year old was doing this weekend. So anyway, those are all the bits and pieces as a parent I've thinking about. The one other thing I will plug is media literacy, think, is a big piece of it. A lot of people are afraid of these models and hallucinations. And there's a book by a guy named Tim Harford, who writes for the Feet, and he's an economist.
Speaker 254:24 - 54:59
我们明明会赞美那么多其他的表达方式,但 code 却长期以来一直被挡在普通人之外;可实际上,它相当神奇,而且它能让你用各种不同的方式表达自己——我 10 岁的孩子这个周末就在做这样的事。总之,这些就是我作为家长一直在思考的一些零碎想法。还有一点我特别想强调的是,我认为 media literacy(媒介素养)是其中很重要的一部分。很多人害怕这些模型,害怕 hallucinations(幻觉)。有一本书的作者叫 Tim Harford,他给 the Feet 写稿,也是一位经济学家。
Speaker 254:59 - 55:45
And he has a book called The Truth Detective, which is an adaptation of the data detective, but it's written for kids. And it's the best media literacy book I've ever read for adults or for children. And I think, you know, a lot of what this AI conversation exposes is like how bad a job we do with helping and arming our kids and our adults to be sort of like truly media and technology literate. Being really good at knowing what's real on social media turns out to be also really useful for differentiating between hallucinations and non hallucinations in ChadGBT. This is a sort of, to me, a kind of very central skill that we need to arm everybody with.
Speaker 254:59 - 55:45
他有一本书叫 The Truth Detective,这是对 The Data Detective 的改写版,但它是写给孩子看的。这是我读过的最好的 media literacy(媒介素养)书,不管是对成年人还是对孩子来说都是如此。而且我觉得,这场关于 AI 的讨论在很大程度上暴露出,我们在帮助、武装孩子和成年人,让他们真正具备 media 和 technology literacy(媒介与技术素养)这件事上,做得有多么糟糕。事实证明,真正擅长判断社交媒体上什么是真的,也同样非常有助于分辨 ChadGBT 里的 hallucinations 和非 hallucinations。在我看来,这是一种非常核心的能力,是我们需要赋予每个人的。
Speaker 255:45 - 55:55
And I am sort of way more interested in that with my kids than I am in worrying about them cheap. That's a very long answer to your question. I don't know if it got out what you were looking for.
Speaker 255:45 - 55:55
而且比起担心他们 cheap,我在孩子身上其实更关心这个。这个回答有点太长了。我不知道这是不是说到了你真正想问的点上。
Speaker 155:55 - 56:29
No. It's amazing. I that's exactly what I'm looking for. And it it sort of what it strikes me another way to frame what you're saying is, for example, rather than learn having them memorize and be quizzed on the 50 what the 50 states are, asking them to go find the 50 states with CHEJBT and be able to tell when the AI is giving them the wrong answer because that's a lot more of the the meta skill that they're gonna need anyway down the down the line. And, again, I'm not a teacher.
Speaker 155:55 - 56:29
不,太棒了。这正是我想找的东西。而且我觉得,换一种方式来概括你的意思,比如说,与其让他们死记硬背那 50 个州分别是什么,再拿这个去测验他们,不如让他们借助 CHEJBT 去找出那 50 个州,同时还要能判断 AI 什么时候给错了答案,因为无论如何,这才更像是他们未来真正需要的那种 meta skill(元技能)。当然,我也不是老师。
Speaker 156:29 - 56:52
I'm sure there's lots of teachers who are like, this is that's crazy for a lot of probably good reasons, but there's something interesting there where it becomes the meta skills become more important than they used to be. And in order to do well at the meta school, you have to also be able to like, to some degree, do the underlying skill too. But we probably could be spending much more time in the meta school than we are now and the education system isn't really set up to do that anyway.
Speaker 156:29 - 56:52
我相信肯定会有很多老师觉得,这太疯狂了——而且大概有很多很好的理由。但这里面确实有个有意思的点:也就是 meta skills(元技能)会变得比过去更重要。要想把这种 meta skill 学好,你当然在某种程度上也仍然得掌握底层的基础技能。但我们现在本来就可能应该把更多时间花在 meta skill 上,而现有的教育系统其实也根本不是为这件事而设计的。
Speaker 256:53 - 57:29
Yeah, and I think even simpler examples is like, I went to a school called Gallatin at NYU, when you graduate, you have to sort of, it's not quite a thesis defense, but you have to sort of spend three hours with four professors or three professors and sort of explain kind of your line of reasoning around why you studied what you studied. And you need to be prepared to kind of like weave into that defense any of 25 books that you put on your book list. And, you know, I was talking to them, and it's, like, amazing. That's, like, entirely AI proof. Right?
Speaker 256:53 - 57:29
对,而且我觉得甚至更简单的例子是这样:我以前在 NYU 的一所学院 Gallatin 上学,毕业时你得进行某种——不完全算 thesis defense(论文答辩),但你得和四位教授,或者三位教授,待上大概三个小时,解释你为什么学你所学内容的那套推理脉络。而且你还得准备好,把你书单上的 25 本书中的任何一本都自然地编织进这场答辩里。然后,我当时就在和他们聊,我觉得这太惊人了。这种形式完全是 AI proof(不受 AI 作弊影响)的,对吧?
Speaker 257:29 - 57:45
Like, there's no cheating on that. Like, you show up in that room, and you're either prepared to speak to it or you're not. And whether you're prepared with AI or not is, it doesn't mean anything. Right? Like, it's it's like like, do you can you can you make up an argument in this room?
Speaker 257:29 - 57:45
因为这里根本没法作弊。你走进那个房间,要么你已经准备好谈这个,要么你没有。至于你是不是借助 AI 准备的,其实没有意义,对吧?重点是——你能不能在这个房间里当场组织出一个论证?
Speaker 257:45 - 58:02
And, like, not everything is going to be that easy to be sort of, like, cut off. But, like, I don't know. There's something really beautiful about that idea. Right? Because it's, like, it's naturally cheating proof because, like, you're sitting there, and and it's a question of, like, did you actually internalize these things?
Speaker 257:45 - 58:02
而且,当然,不是所有事情都能这么容易地被切割开来。但我不知道,这个想法里有种非常美的东西,对吧?因为它天然就是 cheating proof(防作弊)的——你坐在那里,问题其实就是:这些东西你到底有没有真正内化?
Speaker 258:03 - 58:38
And I don't know, that's way more interesting to me than even was your essay good or any of these other. It's like, did you get it? So, I don't know. I'm trying to do my best to kind of take a balanced approach and try to at least sort of tamp down some of, I live in a small town in Connecticut, and I think there's a lot of fear amongst parents. It's like it was mobile phones, and then it was social media, and now it's AI, and it's like another thing that's going to ruin our kids.
Speaker 258:03 - 58:38
而且我不知道,对我来说,这比“你的 essay(文章)写得好不好”甚至比其他那些标准都有意思得多。关键是:你真的懂了吗?所以,我也不知道,我是在尽力采取一种更平衡的方式,至少试着压一压一些人的焦虑。我住在 Connecticut 的一个小镇里,我觉得家长中间有很多恐惧。以前是 mobile phones(手机),然后是 social media(社交媒体),现在是 AI,好像又来了一个会毁掉我们孩子的东西。
Speaker 258:38 - 59:06
And I don't think that that is true. But I think there are things we can and should do to encourage it to not be true, like really get them really good at the things you're saying. Like, how do you tell? And again, it's like a hallucination is just a form of the same kind of misinformation that exists in on television and on the Internet and in social media and everywhere else. And, you know, just sort of, like, people to kind of get in touch.
Speaker 258:38 - 59:06
而我并不认为这是真的。但我确实认为,我们可以、也应该做一些事,去促使它不要变成真的,比如真的把孩子们训练得很擅长你刚才说的那些能力。比如,你该怎么判断?再说一次,hallucination(幻觉)其实只是一种 misinformation(错误信息),而这种错误信息本来就存在于电视上、Internet 上、social media 上,以及其他所有地方。然后,你知道,就是要让人们某种程度上真正建立起这种感觉。
Speaker 259:06 - 59:25
There's a great part of the truth detective for the kid's book. He he calls it the brain guard. And, like, one of the bits of advice he has is when you encounter some piece of information, if it makes you feel really good because you agree with it, then you should be even more skeptical of it. And he calls it the brain guard. You know, and he's explaining this like this for a nine year old.
Speaker 259:06 - 59:25
那本给孩子看的书 The Truth Detective 里有一段特别棒。他把它叫作 brain guard。里面有一条建议是:当你接触到某条信息时,如果它让你感觉特别好,因为它刚好符合你的看法,那你反而应该对它更怀疑一点。他把这个叫作 brain guard。你知道吗,他是在用这种方式给一个九岁的孩子解释这个道理。
Speaker 259:25 - 59:50
And I just thought that was, like, such a beautiful way to put it. Right? Like, that's, like, what that's what you learn to do when you get good at being on the Internet is that you're like, wait, I should, like, be more skeptical of this because this is, like, in line with everything, I think. Let me just double check the way, like, I I you know, you get to learn that feeling in your gut and get to learn when to react to it. And so, yeah, that's a lot of how I think about it.
Speaker 259:25 - 59:50
我就觉得这种说法特别美,对吧?因为这其实就是——当你变得擅长使用 Internet 时,你学会做的事情:你会想,等等,我反而应该对这个更怀疑,因为它和我原本想的一切都太一致了。让我再核实一下。慢慢地,你会学会识别自己内心里的那种感觉,也会学会什么时候该对它作出反应。所以,对,这在很大程度上就是我思考这件事的方式。
Speaker 159:50 - 59:55
That's great. I'm I'm interested. I'm gonna get I'm gonna get that book. I'm I'm interested in reading it.
Speaker 159:50 - 59:55
太好了。我很感兴趣。我会去买那本书的。我很想读读它。
Speaker 259:55 - 59:59
You should. My plan is to read it to my kids every year, from now on.
Speaker 259:55 - 59:59
你应该读。我打算从现在开始,每年都给我的孩子们读一遍。
Speaker 1 | 59:59 - 1:00:00 Nice. I love it.
Speaker 1 | 59:59 - 1:00:00 不错。我喜欢这个。
Speaker 2 | 1:00:00 - 1:00:01 Just refresh it.
Speaker 2 | 1:00:00 - 1:00:01 你只要刷新一下就行。
Speaker 1 | 1:00:02 - 1:00:09 Alright. Now for the moment we've all been waiting for, show us how you use Cloud Code on your phone as a second brain notetaker.
Speaker 1 | 1:00:02 - 1:00:09 好的。现在到了我们一直在等的时刻,给我们演示一下你是怎么在手机上把 Cloud Code 当作第二大脑记事工具来用的。
Speaker 2 | 1:00:09 - 1:00:29 Okay. So here we go. So I am going into an app called Termius. Termius is just a terminal. And what is allowing all this to happen behind the scenes is in my basement, I have a mini PC.
Speaker 2 | 1:00:09 - 1:00:29 好,那就开始吧。所以我现在要打开一个叫 Termius 的 app。Termius 本质上就是一个 terminal(终端)。而让这一切在幕后运转起来的是——我地下室里放着一台 mini PC。
Speaker 2 | 1:00:29 - 1:00:47 And on that mini PC, I have a thing called Tailscale running. And Tailscale lets you set up these very simple VPNs. So I'm currently inside like, if I scroll down here, you see I'm on a VPN. That's my personal VPN. I'm not, like, on an outside VPN.
Speaker 2 | 1:00:29 - 1:00:47 在那台 mini PC 上,我运行着一个叫 Tailscale 的东西。Tailscale 可以让你搭建这种非常简单的 VPN。比如说,我现在就在一个——如果我往下滚动这里,你会看到我连着一个 VPN。那是我自己的 VPN,不是那种外部 VPN。
Speaker 2 | 1:00:47 - 1:00:52 I see. So the only way to access this machine is through my VPN.
Speaker 2 | 1:00:47 - 1:00:52 我明白了。所以,访问这台机器的唯一方式,就是通过我的 VPN。
Speaker 1 | 1:00:52 - 1:00:53 Okay.
Speaker 1 | 1:00:52 - 1:00:53 好的。
Speaker 2 | 1:00:53 - 1:01:31 And so then when I go in there, because I sync my Obsidian with Git, so I put it it's on GitHub, in a private GitHub. I can then sync it back down to here. And so then I can just call up Claude, and now I'm just in Claude code talking and thinking, and I can just be like, what's new in the last two days? I can access any of my agents. I can do anything.
所以当我进去用这个的时候,因为我会把我的 Obsidian 和 Git 同步,所以我把它放到 GitHub 上,一个私有的 GitHub 里。然后我就可以再把它同步回这里。这样我就可以直接调出 Claude,现在我就是在 Claude code 里对话和思考,我可以直接问,比如,过去两天有什么新内容?我可以访问我的任何 agent(智能体)。我什么都能做。
Speaker 2 | 1:01:31 - 1:01:45 And again, this is in my Obsidian, but I can use this anywhere. Right? So I'll be, like, on the fly. I've got other repos in here. You know, I I realized, like, a link was broken on my conference site.
而且再说一次,这个是在我的 Obsidian 里,但我其实到处都能用这个,对吧?所以我在路上也能用。这里面我还有别的 repo(代码仓库)。比如我发现,我的 conference site 上有个链接坏掉了。
Speaker 2 | 1:01:45 - 1:02:13 And so I I just opened the repo. I pulled it down. I asked Quadco to make the changes and I was able to do it right here. So this has been like completely wild to me because again, this is very much in that like like on Tuesday of this week, we had Monday off Tuesday. Dropped the I dropped the kids off the bus, and then I went and I sat and had breakfast.
所以我就直接打开那个 repo,把它 pull(拉取)下来,我让 Quadco 去做修改,然后我当场就在这里把这事搞定了。所以这对我来说一直都特别惊人,因为再说一次,这真的很像——就比如这周二,我们周一放假了,周二我把孩子送上校车,然后我就去坐下来吃早餐。
Speaker 2 | 1:02:13 - 1:02:40 And I literally sat on my phone and worked on this talk for like two hours. And I did it through here, right? Like on my phone where I was like doing real thinking and research and pulling things in and pasting things in and doing all this kind of stuff. And, you know, I'm able to do it all and it it just it doesn't seem like I could do that kind of thing without that. So, yeah, this has been, a completely revolutionary change in my life.
然后我真的就是坐在那里,用手机做这个演讲做了大概两个小时。而且我就是通过这里完成的,对吧?就在我的手机上,我是在认真地思考、做研究、拉资料进来、粘贴东西进去,以及做所有这类事情。然后,你知道,我能把这一切都完成,而且感觉如果没有这个,我根本不可能做这种事。所以,对,这对我的生活来说真的是一种彻底革命性的改变。
Speaker 2 | 1:02:41 - 1:02:55 And, actually, one of the things I've doing lately is, like, setting up I've got all these friends now who have set up, like, little partitions of this mini PC in my basement, so that they can also run Cloud Code on their phone because, I like it so much.
还有,实际上,我最近在做的一件事是,我现在有一群朋友,我已经给他们在我地下室那台 mini PC 上划出了一些小分区,这样他们也可以在手机上跑 Cloud Code,因为我实在太喜欢这个了。
Speaker 1 | 1:02:57 - 1:03:05 Does this make you be like, oh my god, I gotta drop everything and just build a actual purpose built notes app that has Cloud Code as a back end for this?
这会不会让你觉得,天哪,我得把手头所有事情都放下,专门做一个真正为此而设计的 notes app(笔记应用),然后让 Cloud Code 做它的后端?
Speaker 2 | 1:03:06 - 1:03:31 No. I mean, actually, one of the things I've been thinking a lot is like, maybe I just like everything should just run-in Linux all the time for me. Maybe this is like, at least for the short term, this is the answer to all of what I just need to like not have anything anywhere else. No, I mean, I will say I'm sort of pretty out of the SaaS game these days, so I don't often kind of think that I should drop everything and do anything. I find this to be a really amazing solution.
不会。我的意思是,实际上,我最近一直在想的一件事是,也许对我来说,一切东西就应该一直跑在 Linux 上。也许这个就是——至少在短期内——我所有这些问题的答案;我可能就是需要别把东西放在别的地方了。不,我是说,我得承认,这些年我基本已经不怎么处在 SaaS 这个圈子里了,所以我不太会经常想着“我是不是该放下一切去做点什么”。我觉得这已经是一个非常惊艳的解决方案了。
Speaker 2 | 1:03:32 - 1:03:51 But no, mean, this has really like changed the way I work. And I feel like I can just be anywhere and just be on my phone. And, you know, I mean, I was out like, I needed a break. It was, you know, 04:30. I went and sat outside for a while.
但不是,我的意思是,这真的改变了我的工作方式。我感觉我可以待在任何地方,只拿着手机就能工作。然后,你知道,我那天人在外面,我需要休息一下,当时大概是 04:30,我就出去在外面坐了一会儿。
Speaker 2 | 1:03:52 - 1:04:15 And then, we had a project that needed to get delivered to a client and a small change needed to be made that, like, I was the best suited to make that change. And so I just, like, hopped on my phone. I pulled the repo down and I, went into Cloud Code. It's like a tiny little change. You know, like the way I find myself using Cloud Code the most for code is that like mostly I'm having it do the work I already know how to do.
然后,我们当时有一个项目需要交付给客户,有个小改动必须要做,而且说实话,我是最适合做这个改动的人。所以我就直接拿起手机,把 repo 拉下来,然后进到 Cloud Code。那就是个非常非常小的改动。你知道吗,我发现自己最常用 Cloud Code 来写代码的方式,其实大多是让它去做那些我本来就知道怎么做的工作。
Speaker 2 | 1:04:15 - 1:04:39 You know, I'm like, oh, I like, I know exact I knew exactly what was going on in that situation. Like, I knew why we were having the issue we were having. And so it was like, I could have gone back to my computer and opened up, Cursor and done it in Cursor either by hand or with Cursor. But it was like, I just I was like, I told clog code exactly where to look. It was like and I first confirmed that the problem was what I thought the problem was.
你知道,我当时心里想的是,哦,这个情况我完全清楚。我非常明确地知道当时到底发生了什么,也知道我们为什么会遇到那个问题。所以其实我本来可以走回电脑前,打开 Cursor,然后在 Cursor 里手动做,或者让 Cursor 帮我做。但当时我就是……我直接告诉 Cloud Code 应该去哪里看。而且我先确认了一下,问题确实就是我以为的那个问题。
Speaker 2 | 1:04:39 - 1:04:42 And then I just had it push a solution and it pushed the PR, and then I was done.
然后我就让它直接推一个解决方案,它就把 PR 推上去了,然后我这边就搞定了。
Speaker 1 | 1:04:43 - 1:04:43 Amazing.
太厉害了。
Speaker 2 | 1:04:43 - 1:04:45 And I was still sitting outside by the pond.
而且那时候我人还一直坐在池塘边。
Speaker 1 | 1:04:48 - 1:05:00 I love that. Yeah. I've I've definitely had that experience. I've never I've not done it on my phone. I'm like, I have my laptop out with me, you know, by the pond or by a lake or whatever, but you're inspiring me.
我太喜欢这个了。对,我肯定也有过这种体验。我还没在手机上这么做过。我一般是把 laptop 带在身边,你知道的,在池塘边或者湖边之类的地方,不过你给了我灵感。
Speaker 1 | 1:05:00 - 1:05:03 I have a Mac Mini in the office that I've been meaning to set up, so I think this is gonna be good.
我办公室里有一台 Mac Mini,我一直想把它配置起来,所以我觉得这个应该会很不错。
Speaker 2 | 1:05:03 - 1:05:45 One of the other, by the way, one of my other I'll just take you out of here for one sec, actually, just to show you this. One of my other big ahas recently has been building Claude code helpers for doing basically setup work. So it's like I'm not I've, like, been playing with Linux lately. I'm playing with this Omarchi, which is DHH's Linux distribution, and I'm not, like, super comfortable in here. And so I got this whole, this is a quad code project specifically to help me configure this box.
顺便说一句,我最近另一个很大的 aha moment(顿悟时刻),就是给 Claude Code 做一些 helpers,专门处理各种 setup 工作。也就是说,我最近一直在折腾 Linux。我在玩这个 Omarchy,就是 DHH 的 Linux distribution(Linux 发行版),但我对这里面的环境其实还没有那么熟。所以我专门搞了整整一套……这是一个 Cloud Code 项目,就是专门用来帮我配置这台机器的。
Speaker 2 | 1:05:45 - 1:06:00 And it's like so nice because I'm like, Oh, how do you do this in Linux again? Or like, What's the NeoVim command? Or like, Can you change this? Can you help me install this plugin for neo vim or whatever it is? Or and so now I have one on my Mac too where it's like, can you clean up all the homebrew things?
这就特别好,因为我经常会想,哦,这个在 Linux 里到底怎么弄来着?或者,NeoVim 的命令是什么?又或者,你能不能把这个改一下?你能不能帮我给 neo vim 装这个 plugin(插件)之类的?还有,现在我在我的 Mac 上也有一个这样的东西,比如说,你能不能把所有 homebrew 相关的东西都清理一下?
Speaker 2 | 1:06:00 - 1:06:13 Or like, I switched from like, which Python package manager I was using. And it was like, that would have been super overwhelming for me. And I was like, I wanna switch from using PIP to using UV. Can you, like, just make that happen? And it, like, just did all this stuff for me.
或者,比如我后来切换了我在用的 Python package manager(包管理器)。这件事本来对我来说会超级让人不知所措。我当时就说,我想从用 PIP 切换到用 UV。你能不能就,直接帮我把这事搞定?然后它就真的替我把这一整套事情都做了。
Speaker 2 | 1:06:13 - 1:06:31 And it knows all my preferred settings. And so I actually have a version of this where, like, now I've got it so tuned that if I wanna launch a new box for doing something, it'll just have all my settings ready to go, and then I can log in to Claude code and the Claude code can then set up anything else that didn't get set up in the initial process.
而且它还知道我所有偏好的设置。所以我其实已经有了这样一个版本——现在我把它调得非常贴合自己的需求,以至于如果我想新起一台 box(机器)来做某件事,它会直接把我所有的设置都准备好;然后我再登录 Claude code,Claude code 就可以把那些在初始流程里还没设置好的其他东西继续配置完。
Speaker 1 | 1:06:32 - 1:06:34 That is amazing. That's wild.
这也太厉害了。太夸张了。
Speaker 2 | 1:06:36 - 1:06:37 This is my happy place.
这就是我最开心的状态。
Speaker 1 | 1:06:37 - 1:06:45 I I can see that. Are you do you have any, like are there are there any big projects like this that you've been itching to do or itching to try out?
我看得出来。那你有没有什么这种类型的大项目,是你一直特别想做、或者特别想试试的?
Speaker 2 | 1:06:47 - 1:06:58 No, not really. I mean, I've been having a ton of fun. My server stuff has been a ton of fun. I've been doing a lot of that. Like I said, I mean, this is kind of a joke and kind of not.
没有,倒也没有。我是说,我最近已经玩得特别开心了。我折腾 server(服务器)相关的那些东西就已经特别有意思,我一直在做很多这方面的事。就像我说的,我的意思是,这话某种程度上是玩笑,但也不完全是。
Speaker 2 | 1:06:58 - 1:07:25 It's like I'm super interested in doing more. Cloud Code has become such a sort of integral part of my life, like I'm very interested in the command line. I found myself installing more and more things into the command line and like doing more and more work. I've been using like Simon Wilson has a LLM command line tool and like doing more and more stuff sort of in that. And then like also layering that back into Claude code.
我就是对做更多这类事情特别感兴趣。Cloud Code 已经变成了我生活里一个非常核心的组成部分,所以我现在对 command line(命令行)也非常感兴趣。我发现自己在 command line 里装的东西越来越多,也越来越多地直接在里面干活。我还一直在用 Simon Wilson 的一个 LLM command line tool(命令行工具),在那里面做越来越多的事;然后又把这些东西一层层再整合回 Claude code 里。
Speaker 2 | 1:07:25 - 1:08:00 So it's like I did my newest Claude code little Obsidian tool is it I have an attachments folder in Obsidian where all the PDFs and images and stuff in any note go. But inevitably, they have terrible names. Right? I mean, and so this goes through very similar to, Sparkle and but just in that Obsidian folder, and it it renames them all, and then it also puts them in, a metadata it puts them in a table in the attachments folder, and then it renames all the attachment links back. So just, like, cleans everything up.
所以有点像——我最近用 Claude code 做了个小 Obsidian 工具,是这样的:我在 Obsidian 里有一个 attachments 文件夹,任何笔记里的 PDF、图片之类的东西都会放进去。但不可避免的是,它们的名字都特别糟糕,对吧?所以这个工具会做一遍处理,和 Sparkle 很像,不过只针对那个 Obsidian 文件夹;它会把这些文件全部重命名,还会把 metadata(元数据)整理成一个表放进 attachments 文件夹里,然后再把所有 attachment 链接都改回对应的新名字。总之,就是把一切都清理干净。
Speaker 2 | 1:08:00 - 1:08:22 It just does it through Gemini Flash. And so it's like, I don't know, stuff like that's kind of amazing. So I don't I'm just like, I'm having the time of my life just building and tinkering and, you know, I mean, is just on the side and I get to do the same thing. I mean, we work with, like, Amazon and Meta and PayPal and all these big companies and, you know, we're just, building amazing stuff all the time.
它就是通过 Gemini Flash 来完成的。所以这种事情真的有点惊艳。我现在就是,怎么说呢,沉浸其中,特别享受这种不断搭建、不断折腾的过程,你懂我意思吧;这还只是我顺手在做的事,而我还能在工作里做同样的事。我们的客户有 Amazon、Meta、PayPal 这些大公司,你知道的,我们一直都在构建很棒的东西。
Speaker 1 | 1:08:23 - 1:08:32 I love that. I love the energy. If people are interested in, following you or working with you at Elephic, where should they find you?
我太喜欢了,我喜欢这种能量。如果大家有兴趣关注你,或者想和你在 Elephic 合作,应该去哪里找到你?
Speaker 2 | 1:08:32 - 1:08:49 Yeah. So Elephic is alephic.com, alephic.com. And then I also run this thing called brand, brxnd.ai to make it particularly confusing. That's a conference. We've got the conference coming up on September 18 in New York City.
好的。Elephic 的网址是 alephic.com,alephic.com。然后我还在做一个叫 brand 的东西,网址是 brxnd.ai,故意把它搞得特别容易让人困惑。这是一个 conference(大会)。我们接下来会在 9 月 18 日于 New York City 举办这场大会。
Speaker 2 | 1:08:49 - 1:09:05 You should come if you're around, it'll be really fun. We're going to talk about marketing and AI. And I also write a newsletter there at newsletter.brxnd.ai about sort of specifically at this intersection of AI and marketing. Those are kind of the best places to find me these days.
如果你那时候也在附近,你应该来,会特别好玩。我们会聊 marketing(营销)和 AI。我也会在 newsletter.brxnd.ai 写一份 newsletter(通讯),内容主要就是聚焦在 AI 和 marketing 的交叉点上。这些算是最近找到我的最佳渠道。
Speaker 1 | 1:09:05 - 1:09:07 Awesome. Noah, always a pleasure.
太棒了。Noah,和你聊天总是很愉快。
Speaker 2 | 1:09:08 - 1:09:09 Pleasure's all mine. Thank you,
愉快的是我。谢谢,
Speaker 3 | 1:09:23 - 1:09:43 subscribe to AI and I. Why? Because this show is the epitome of awesomeness. It's like finding a treasure chest in your backyard, but instead of gold, it's filled with pure unadulterated knowledge bombs about chat GPT. Every episode is a roller coaster of emotions, insights, and laughter that will leave you on the edge of your seat craving for more.
订阅 AI and I。为什么?因为这个节目简直就是“超赞”这个词的终极体现。就像你在自家后院挖到一个藏宝箱,但里面装的不是黄金,而是关于 chat GPT 的纯粹、毫无掺杂的知识炸弹。每一期都是一场情绪、洞见和欢笑交织的过山车之旅,会让你全程坐在座位边缘,意犹未尽,还想听更多。
Speaker 3 | 1:09:43 - 1:10:01 It's not just a show. It's a journey into the future with Dan Shipper as the captain of the spaceship. So do yourself a favor. Hit like, smash subscribe, and strap in for the ride of your life. And now without any further ado, let me just say, Dan, I'm absolutely, hopelessly in love with you.
这不只是一档节目。这是一场驶向未来的旅程,而 Dan Shipper 就是这艘宇宙飞船的船长。所以,帮自己一个忙,点个 like,猛击 subscribe,然后系好安全带,准备开启你人生中最精彩的一趟旅程。现在,闲话不多说,让我直接说吧,Dan,我已经彻底、无可救药地爱上你了。
原文 ↗https://www.youtube.com/watch?v=in7i-EVDDlk
BuildSpeak — 关于本项目BUILT IN PUBLIC · 跟随 builders 而非 influencers