Claude Code Can Be Your Second Brain

Transcript

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 Node 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. If you want to 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_02] Thanks for having me. I'm excited to have you. It's really good to get to chat. This is our first interview in probably five years. You are 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. And I love the way that your brain works. You have this 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 Alephic, 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 they're working so well. And I know you have some pretty cool Claude code stuff to show us. So yeah, thanks for coming on. Thanks for having me. I'm super excited. That was a fun interview all those years back. It was really, really fun. So I want to just dive right into the thing that I think is so cool about what you're doing. So I know you have a whole vibe coding setup that you built for yourself. Can you talk us through that? Yeah, I'm not sure about the vibe coding part of it. I have a fairly heavy duty Claude code setup, but actually mostly not for code. So since those days of super organizers, many people have 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 folders. And they can then be synced with Git and you can do lots of other fun kinds of things. And so my number one Claude code use is using it as a tool to interact with my notes. 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 Claude code on my phone. [SPEAKER_00] This is incredible. I want to go through all of this. So where should we start? Should we do how you use Claude code as sort of this research assistant notes organizer note taker thing? Or should we start with how you use it on your phone? [SPEAKER_02] We can start with just the general part of it. That might be the easiest. The phone is really just an extension of that same thing. I would say generally, and this is something I feel not enough people talk about with AI, one of the things I find really extraordinary about it is the ability for me to work really productively on my phone. And that's been a huge change because so much of what I do is 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 my computer was a better place for it, which is why I've been such a note taker. And I have found whether it's Claude code and Obsidian or Claude code and code. Right. So the other piece of it is being able to, if you see something go wrong, 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, I use quite a bit of Grok voice mode. And I find that as an alternative way of working through problems. I have a Tesla. So now it's baked into the Tesla. And it's just. And obviously all the other ChatGPT and Claude and all these things of being able to go and do research and really think and explore things. In this device, it's always been useful, but the phone has not been the best place for deep work, I think is probably something most people would agree with. The phone has not been the best place to do deep coding and research work. And I feel it's really changed my ability to do that. [SPEAKER_00] Wait, I got to stop you. [SPEAKER_00] So you're using Grok voice mode. And is that specifically because it's built into your Tesla or using it in situations where you could also use, for example, ChatGPT voice mode? [SPEAKER_02] No, I'm using it because it's way better than any of the other voice modes. [SPEAKER_02] And I will fight anybody who says anything different. [SPEAKER_00] OK, tell me what do you like about it? [SPEAKER_00] Why is it better? [SPEAKER_02] To be fair, OpenAI launched their real time API, which may or may not be baked into ChatGPT voice now. [SPEAKER_02] It's not totally clear, but the old voice mode was based on 4.0 and I just found it to be completely unusable. And Gemini's voice mode, I just didn't find to be smart enough. And I just found Grok's voice mode to be significantly smarter than anybody else's. I'm using Grok. Two, three, four. I don't even remember what, or whatever the latest. [SPEAKER_00] Latest one. Yeah. Not the super, I don't have the most expensive account. Super heavy or whatever. [SPEAKER_02] I don't have super heavy. But I just find it to be much better. It does tool calling way better than any of the other ones. That's a major weakness of the voice models is that they don't do great tool calling and research. [SPEAKER_02] And Grok's team steps all 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 two hours researching and essentially working through a piece. [SPEAKER_00] Super heavy or whatever. I don't have super heavy. But I just find it to be much better. It does tool calling way better than any of the other ones. That's a major weakness of the voice models—they don't do great tool calling and research. Grok's team steps through all that. So, before it was loaded in my Tesla, I dropped my daughter off at summer camp this summer up in New Hampshire. I had a five hour drive on my own. I spent two hours researching and working through a piece. I did it by connecting it to Bluetooth and sitting there in the car. I found it to be by far the best of the voice modes. I hope these other models catch up there because I would love more really good voice modes. I had a mind blowing session this weekend, and I'm giving a talk with some ideas. I think it's generally going to be about transformers eating the world. So I was catching myself up on self-attention and exactly how it works. [SPEAKER_02] I did an hour session and it was by far the best explanation I've ever read or heard for it. [SPEAKER_02] Yeah, I've just found it to be a pretty extraordinary product. I do love voice mode for that. It's the—it's a podcast made specifically for you about whatever you're curious about. That's really cool. I drove upstate this weekend and I've been reading the Iliad. I had it on an audiobook and then I had some questions as I was driving. So I unfortunately used ChatGPT voice mode because I didn't know about Grok. I wish we'd had this conversation before then. But the thing about ChatGPT voice mode is, when it first came out, it was cool, but it just hasn't gotten as smart as the models are. They gave it this new personality that I had to get used to where every time you ask it a question, it goes, "Oh yeah. Uh huh. Well, you know." And it's just this weird Gen Z thing that feels like it has a little too much swagger or something. Like it doesn't actually care about you. I don't know what that is. So I had to get used to that. [SPEAKER_02] Grok has a stoner mode for what it's worth. [SPEAKER_02] The car version is very interesting to me. [SPEAKER_02] This was in the most recent Tesla release a couple of weeks ago. [SPEAKER_02] I had been doing that same thing you did where you plug your phone in and put it on Bluetooth and do your best to make it work. [SPEAKER_02] It's very interesting to just have a voice AI button and it syncs back to your regular Grok, but you can't rejoin old chats. It's just like, hey. But these things are significantly better than Siri and all these other things. Particularly, there's no comparison if you actually have something more than just a single question you want an answer to. If you actually want to have a conversation about the Iliad or about transformers and self-attention, it's pretty amazing to just hit this button and use that car time. I was on my way somewhere last week and I was having it research. I was going back to Walter Benjamin and I have this idea to write a piece about how the reactions to every new technology are essentially elitist critiques of it. It's always like, "Oh no, everybody's going to be able to do this thing that only we used to be able to do." So I was in the car thinking about this and I was like, okay, it's been years since I read the Walter Benjamin about mass production of images. [SPEAKER_00] One. Yeah, that one. So then I'm having a conversation about that and I'm like, who were Walter Benjamin's contemporaries? And then I'm into all these things. That's amazing. [SPEAKER_00] It's the best. It's the best. Yeah. [SPEAKER_00] Okay. So you're filling your brain with all these things from voice mode, which I love. [SPEAKER_00] Tell us about your second brain setup, or however you refer to it. I want to know how you're using Claude to take notes and do research and all that. Yeah. So I could just open it up. Maybe that's the easiest thing to walk you through. [SPEAKER_02] I'll start on my computer and then we can do the phone. The computer is a way easier share here. So this is what I was working on before. This is just Claude and it's sitting on top of my Obsidian. I'm following the PARA method. [SPEAKER_02] I've got everything organized in here and put in the places that they need to be. [SPEAKER_00] Let me stop you for people who are listening. [SPEAKER_00] So we're looking at Claude. It seems like you have Claude running in your Obsidian vault. [SPEAKER_00] It looks like it's adding something to an existing note. Is that what's going on? [SPEAKER_02] And I've just got everything organized in here and put in the places that they need to be. Well, let me just stop you for people who are listening. [SPEAKER_00] So, okay. [SPEAKER_00] So we're looking at cloud code. [SPEAKER_00] It sounds like you have cloud code running in your Obsidian vault. [SPEAKER_00] And there's some kind of, it's adding something to an existing note. [SPEAKER_00] Is that what's going on. [SPEAKER_00] That's what we're looking at. Yeah. So in this particular one, I'm working on this talk. I'm putting on my conference in two weeks. I'm giving this talk about marketing and AI and what's going on. If we jump back a second, I've been doing these conferences called brand brxnd.ai. [SPEAKER_02] And they're about marketing and AI and I did one in February in LA. [SPEAKER_02] And my talk in LA was about this, I'm sure you've seen it. [SPEAKER_02] It was the office of strategic services, which was the precursor to the CIA wrote this manual called the simple sabotage field manual. [SPEAKER_02] And it was essentially a manual to help citizens, saboteurs in Nazi occupied territories, quietly sabotage the Nazi occupation. [SPEAKER_02] And so there's a whole bunch of stuff for blue collar workers. [SPEAKER_02] That'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 it will. [SPEAKER_02] 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 if somebody is trying to make a decision, you should suggest that they don't act with too much haste. Less we'd be embarrassed. And so my talk was about how one hope I have is that AI can sidestep a lot of the bureaucracy that exists inside large organizations, because it has this goo like effect where it can fit into any crevice or crack because it can act as this fuzzy interface. And it doesn't really care about the sort of input output. And so the next part of that story is after the conference, I realized that manual was in the public domain. So I hired a designer and I printed 300 copies and I wrote a new foreword for it. And so we're giving this away at the conference. And so my talk is trying to tie all these ideas together. Right. 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 and the OSS was the precursor to both the CIA and special forces. And so 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 chats and articles and all these things. And then I'm constantly talking to the AI in here and giving it new ideas. So I'm like, oh, I need some conclusions. Here's my first thought on conclusions and I'm having it note down the conclusions. And then at the end of each day, I have the AI write up the changes, the things I learned that day that are going to help me push this talk along. And so that's what you're looking at right here is this work that I've been doing where I've been feeding it. I was working on what are some of the conclusions I want it to be. And so this is all sitting in my Obsidian inside of project specifically for that talk. [SPEAKER_00] Okay. [SPEAKER_00] So let me get a clearer sense of this. [SPEAKER_00] This is really interesting. [SPEAKER_00] So you have a project, when you have a new thing, you're giving a talk, you make a new folder. [SPEAKER_00] And then as you're thinking about stuff, you're working with cloud code inside of the folder and you're researching stuff and then saying like, I want you to take notes on it. [SPEAKER_00] In this particular case, you know that a component of your talk is the conclusions section. [SPEAKER_00] And so there's one particular markdown file that you're going back and forth with and having it add conclusions. [SPEAKER_00] But what else is in that folder? [SPEAKER_00] So is there a body note and then there's an intro note, or is it. 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 the cloud code, don't help me write anything right now. And I generally find this to be a big thing with all these models is they immediately jump to wanting to help you with the artifact. And when you're just in thinking mode, you have to be very explicit in like, hey, I just want you to help me think and ask me questions. [SPEAKER_02] And so what you can see here is there's a bunch of files in here. [SPEAKER_02] I've got chats. [SPEAKER_02] That's where I'm literally taking chats I'm having in other things. [SPEAKER_02] And I'm using the Obsidian web clipper to pull the whole chat in. [SPEAKER_02] I've got daily progress. [SPEAKER_02] That's where I'm having the AI actually look through all the notes that came out that day and help me think through the progress. [SPEAKER_02] And then I've got research. [SPEAKER_02] That's where I've got a bunch of articles and PDFs and stuff that I've pulled in so far and been reading about, and then there's a bunch of other random notes along here where I've been using it to help me think. [SPEAKER_02] And so I was in the midst of one, I've got this conclusion note. [SPEAKER_02] So I sort of felt like I had blocked out the big themes. [SPEAKER_02] That's where I'm having the AI actually look through all the notes that came out that day and help me think through the progress. [SPEAKER_02] And then I've got research. That's where I've got a bunch of articles and PDFs and stuff that I've pulled in so far and been reading about, and then there's a bunch of other random notes along here where I've been just using it to help me think. And so, yeah, I was in the midst of one. I've got this conclusion note. So I 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 to 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. And so I was starting to get to the conclusions. And so, yeah, I'm just trying. I'm really piecing all this stuff together right now. That's what's happening. And give me a sense of when this folder was empty, what did you start with? [SPEAKER_02] So I think I started with 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 a brand to give you a sense of the style that I have. And here's the kind of general idea and the big points I want to make, right? Like I'm giving away this book. So I want to talk about simple sabotage field manual. And I have this notion—it's just a title. It's like "transformers are eating the world." Yes. This idea that one of the very interesting things happening with these models is they're displacing a whole bunch of specialized code in places. And so I want to talk about that and then I've got these conclusions. And so the first thing I said was like, hey, just go look through all the rest of my—probably 1500 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 pull those into the research folder at the beginning to jumpstart this process. [SPEAKER_00] 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? No, so I'm starting it in the full obsidian vault. So like if we step out of here, right, we're in the root directory. All this stuff is in the root directory. My obsidian, and my obsidian setup is also a little more intense for what it's worth because I've realized you can add a package.json to add a bunch of 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 there are a bunch of other moving pieces in here, but generally it's fairly straightforward. I mean, I'm trying to use PARA and some other bits and pieces. [SPEAKER_00] So for people who are listening or watching, we just went through a bunch of stuff really fast. So the basic gist is obsidian is a note-taking app that runs locally. And so everything—all the notes you take—they exist in essentially text files on your computer organized by folder. And when you're starting Codeium, one way to do it would be to start Codeium in the folder for the particular project that you have. But it sounds like what you're doing is instead you're starting in the root directory where all of your obsidian notes live. And the advantage of that is Codeium has some sandboxing things where 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.json, which lets it run custom software commands, basically. That's really interesting. Okay. And do you find—cause I've had this as a twinkle in my eye to 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, this random thing is relevant because X, Y, Z," 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 what I think is interesting, it definitely would not have. Do you find that that's the case or have you figured out a way to make it relevant? I think by and large, yes, I agree with you. I think in this case, relevance is a little simpler since ultimately this talk is the things I was asking it 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 want to talk about the simple sabotage field manual. It can literally just do a find for all the times, all the articles and things I've got in my obsidian about that. And so relevance is a loaded term, right? And I agree with what you're saying. I think what I'm asking it to do is much more simple, which 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_00] Got it. I want to talk about the simple sabotage field manual. It can literally just do a find for all the times, all the articles and things I've got in my Obsidian about that. And so it relevance is, yeah, it's a loaded term, right? And I agree with what you're saying. I think this is what I'm asking it to do is much more simple, which is amongst this set of things, go find all the notes that I've already researched that brought me to be thinking about these things to begin with. [SPEAKER_00] Got it. [SPEAKER_00] And then once you had to do all that research, did you have it do any sort of summary to let you stimulate you to be like, okay, here are some jumping off points based on what you've done before. What was your next step? So my next step is I actually have an agent in here. So if we go to, I'll do continue for now. [SPEAKER_00] Um, and so for people who are listening, you're just starting up Claude, you're using the continue flag. So you're starting Claude by continuing the last session that you were in. And now you've got Claude Code gives us ability to do sub agents. So those are little mini Claudes that you can spawn and you have a thinking partner, one thinking partner, sub agent. Okay. How does that work? 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 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. 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 not just happening here. I was also having a whole conversation. Sorry, I'm just backing out. So if we go into chats, these are a whole bunch of the chats that I had. [SPEAKER_00] Like with the interviewer. No, these are chats I was having with ChatGPT and Claude and Grok 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, like 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. And, you know, the 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 outperform some specialized time series modeling models with transformers. And, 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 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 thread in ChatGPT or Claude, and I'll then save that somewhere. And then I'll just 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 idea initially came into my head, maybe when I saw the research about time series modeling or something. [SPEAKER_00] Really interesting. [SPEAKER_00] Okay. [SPEAKER_00] So let's keep going. [SPEAKER_00] So you've got the sub agent and I actually want to 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 agent ghostwriter. And I think we found the same thing when I was thinking about, okay, how does a good ghostwriter work? They don't just, you don't say, hey, I want you to write a blog post, and they're just like, cool, I made it, here it is. A good ghostwriter is going to get to know you and really understand. You're going to work together to figure out what's in your head about it, but also shape what's in your head. It's not just, oh, I can see it. They need to get it out of you. 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've found that too. And I think that's 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 let it ask to understand you first. One of the things I say to a lot of people is just, 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. You know, and its ability to read is incredible. Right. And I think, you know, arguably much more useful on a day to day basis. We produce artifacts far less frequently than we just think about things. And so yeah, I do this a lot. This is definitely a complaint I have about all the models is, you know, even when you very specifically tell it not to try to do your work, it's still often tries to do your work. And so you have to really be like, no, I said no. And it's its ability to read is incredible. Right. And I think, arguably, much more useful on a day to day basis. Like we produce artifacts far less frequently than we just think about things. And so yeah, I do this a lot. [SPEAKER_02] This is definitely a complaint I have about all the models is that even when you very specifically tell it not to try to do your work, it's still often tries to do your work. And so you have to really, really be like, no, I said no. Like, I think actually, if we look at, so here 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_00] It's so good. [SPEAKER_00] I love it. Yeah, but yeah, I think we all experience that. And I do hope over time that gets baked into the models. I think it's a very interesting tension that exists with the model companies. Because obviously, the economic input output is measured in the artifacts that it produces. And so I think it's very oriented and I suspect that part of it is just that the helpful assistant thing has become a sort of meme that is probably self ingested. But yeah, it's, I think for those of us who are trying to do more interesting things with these models, it becomes a real barrier to work. [SPEAKER_00] Totally. [SPEAKER_00] Um, okay. [SPEAKER_00] So I want to think about when you're using the thinking agent, did you say it's outputting some sort of summary of what you've come to in a particular place or? Yeah. So that thinking agent is sort of told to, as it asks me questions, make notes about the questions that it's asking me and keep a running log of what I'm uncovering and how I'm thinking about it and all those sorts of things. [SPEAKER_00] Got it. [SPEAKER_00] And then, you know, you come back the next day and you're like, oh, I just want to go down this rabbit hole on X, Y, Z thing about, you know, this Wild Bill guy. [SPEAKER_00] And that you started a new chat, maybe with it, maybe with the sub vision, maybe not. And that becomes its own new file on that topic. [SPEAKER_02] Yeah, exactly. [SPEAKER_02] So the Wild Bill stuff started as deep research in ChatGPT. And I'm reading the Wild Bill book right now. There's one sort of particularly famous biography of him. And I'm thinking about the bits and pieces and trying to make connections. I think I made a kind of interesting connection in there. A big part of what he seems to have been after with the OSS and the inspiration for the special forces was empowering individuals. That's the theme of that manual was empowering citizen saboteurs, but also, I think a big part of the special forces is having incredible operators at the edge who obviously operate within a sort of command and control hierarchy, but have a ton of autonomy to move and execute independently because they have all the things that they need. And in all of that Wild Bill research, I went back to this and I was like, is this an interesting way to connect all these ideas that maybe there's something here. And again, I'm still early. I have not solidified these conclusions. This is the regular kind of writing process. Right. But it's like, well, I think there's this idea that fundamentally, one of the big things with transformers is it moved us from sequential based models to models that can act in parallel and process their work better. [SPEAKER_02] 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. [SPEAKER_02] And what we both do for a living. [SPEAKER_02] And so I think there's this kind of interesting connection. [SPEAKER_02] And so that was what I was playing with. [SPEAKER_02] I think here was like, oh, maybe there's this connection between sequential processing to this kind of parallel. [SPEAKER_02] And then there's this connection to bureaucracy. [SPEAKER_02] And then there's this connection to Wild Bill who seems to have been very much about working within a system, but having autonomy at the edges. [SPEAKER_02] And so that's what I was playing with and just taking notes. [SPEAKER_02] And then, yeah, I would jump out and be like, oh, well, actually, I haven't figured out a conclusion yet. [SPEAKER_02] Let me start the conclusion section and I'll just get that going on the side. [SPEAKER_02] And then, I have a job, so I can't be doing this all the time. [SPEAKER_02] So it's also like you interrupt yourself and it's really nice to be able to come back and be like, can you catch me up on the last three days of research? Ooh, I love that question. That's so cool. [SPEAKER_02] And so, yeah, you can just go in and be like, can you catch me up on the last few days of the research? [SPEAKER_02] And it's just going to go read all this stuff. [SPEAKER_02] Right. [SPEAKER_02] And again, it's like I think the point you made earlier about go find relevant sources. [SPEAKER_02] It's like I find that the difference between the people getting a lot of this right now is part of it is just that you have a good feel for where the edges of the capabilities of these models are and you sort of encourage them to work within those capabilities. [SPEAKER_02] Like this is an incredibly easy task, right? [SPEAKER_02] Like I know what it's going to do here. [SPEAKER_02] Like I could write all these Unix commands. [SPEAKER_02] And it's just gonna go read all this stuff. [SPEAKER_02] Right. [SPEAKER_02] And again, I think the point you made earlier about go find relevant sources. I find a lot that the difference between the people getting a lot of this right now is part of it is just that you have a good feel for where the edges of the capabilities of these models are and you encourage them to work within those capabilities. Like this is an incredibly easy task. We know what it's gonna do here, right? Like I 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 however long, and we know it's gonna be able to do that. And so it's saying 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. But it's just amazing also to be able to revisit deep work like this, right? Where you're gonna break your flow. And it's often that I find whether it's code or writing, the hardest part is just picking it up again because you're out of it. And so to kickstart that process is amazing. I think what I was playing with here is this idea that bureaucracy was actually an innovation, right? We look at bureaucracy as a negative and generally we talk about it as a negative. And I think often it is a negative. But bureaucracy was a huge innovation for how companies operate, right? And ultimately it represents hierarchy and structure and a whole bunch of things that are actually pretty positive for operating at a large scale. And so my whole thesis on AI around all this bureaucracy stuff is that what's interesting about it is that as opposed to past technologies, which forced you to make a decision about whether you wanted to use your existing structure and build that technology into your existing structure or adopt the new structure. And most of the time, the new software required you to adopt the new structure. And that's why so many software projects failed for so long, at least that's part of what I think. And I think part of what's interesting about AI, what I find so interesting is that you can keep letting everybody work in whatever way they want. It's a classic problem inside large companies where one team wants to use Asana and one wants to use Jira and one wants to use Linear, right? And so then at some point there's a huge project and they bring in some big consulting firm and they decide they're going to all centralize on this one thing. And now two thirds of the company is unhappy. And they've all made sacrifices and you're in this very non-ideal state. And I think what's really interesting about AI, and this is a little more theoretical because we're so early in this, is that I think it's very possible you could just say, well, everybody just keep doing what you're doing. We're going to stick some models in the middle. They don't care what you use because it's all just data structures to them. And so we can have this central thing. And when we talked about Percolate at the beginning, Percolate was a content marketing platform that worked with very large companies. So it was an enterprise software product. And at the end of the day, this is the fundamental challenge of enterprise software: adoption and change management. And I just think, I hope, and this is the optimist in me, that AI lets us not worry so much about these things. And rather than trying to make everybody change the ways that they work, let them work in these ways and let AI sort of get into the nooks and crannies. I call it my Thomas's English muffin theory of AI. And so yeah, 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. I think the point you just made is totally right. And it's actually not theoretical. I've been seeing this too inside Every, and I've been meaning to write about it. We have inside Every we run six different products and we have 15 people. So it's a crazy product to head count ratio. And what's interesting is I really like doing things in a bottom up way. So everyone, each of the products has its own stack. We're not centralized into a particular stack. Each GM that runs a product just 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. So an easy example is we have one product called Sparkle, which is a finder replacement or Spotlight replacement. So it organizes your files and then it implements really fast Spotlight search. I'm a user. I like it. Okay. So then you know. And so that's really cool. And agentic search coming soon, check it out. And we're just building a new product, new GM, new stack, called Para, which is essentially an in-house counsel. So it's short for paralegal, not para like Tiago Forte para. And the whole job for Para is just take all of your legal files and whenever I have a question and be like, okay, 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 a Cloud Code sitting on top of a directory. and so that's really cool. And agentic search coming soon, check it out. And we're just building a new product, new GM, new stack called para, which is essentially an in-house counsel. So it's short for paralegal, not para like Tiago Forte para. And the whole job for para is to take all of your legal files. And whenever I have a question and be like, okay, do we ever sign this contract or what's the employee agreement template or whatever, it just gives you the answer. And it's a cloud code sitting on top of a directory. And a thing that we needed to implement for that is this fast file search. And what's really interesting is historically, if we wanted to reuse the stuff that we learned from implementing Sparkles 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 all those things. Right. And what we did instead is we just added a pre, who's the developer for para right now. We just added her to the Sparkle repo. And I was just like, just ask cloud code to figure out how it works and just do your own version. And so you get this tacit code sharing where we all get better, but without having to do the work of abstracting and modularizing everything, because the percentage of things that you can do that for are pretty low, because it's a heavy lift. And I'm seeing that happen all the time where just having a bunch of repos that are all solving some of our problems, but in different environments in different ways, everyone gets more productive because AI can translate. I've, one thing we've done there, we also at Alephic, 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've got lots 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 you're just in Cursor or Cloud Code or whatever, and you're like, Hey, can you go 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. So it's got some CRM stuff and it's been a fun place to build the things that we need to run our company. But it's also a good place to experiment and explore and figure out solutions to interesting problems. And so I'll frequently be like, Oh, can you go look at the Intelligence repo and you know, look at how I implemented that thing there and take those best practices and just pull them over. And yeah, I think that stuff, that's where I really do believe in this idea. I, one of my, whenever we have a client meeting or something, my first question, the icebreaker I always use is what was your aha moment with AI. And mine was, I mean, it was probably not the very first, but it's the one that was most impactful. I got access to build a ChatGPT plugin room and plugins came out, two and a half years ago or something now, you mean 50 years ago, 50 years ago. And you know, I, I've written a lot of software in my life and you know what you do when you get access to something new. It's I've got to go read the API docs and figure it out. And you know, there's going to be a contract and as long as you follow that contract, it works. And I go read the plugin spec and it basically is like, Oh, you just stick a manifest.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 to send it back to us and then we'll deal with the rest. And I was just like, that's amazing. It's how the world should work. I wish everything worked that way. I wish I didn't always have to adhere to the big companies contract for how to send and receive data. But also the thing that really struck me in that moment, and it's been my rallying cry around all this stuff is that it's fundamentally counterintuitive. I literally have a career's worth of intuition for how to integrate software systems. And it flipped it on its head, 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 thing for everybody, like, this is just not intuitive for now. And that's not a bad thing. It just means you need to build intuition and that's what we're all just out there trying to do with it. Right. And so when I don't know, I mean, part of what I like about what you're doing and you know, even just hearing the things you're saying, but generally what you do with the podcast and what you do with every is so much of it is like, we're all just figuring stuff out for the first time. Right. And you know, we're like, oh, will this work? And then 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 what we're all doing all the time. And that's why it's so fun. I think that's why I love this moment. Because you just have a weird idea and you're like, has anyone done this before? And it's like, no, and it's not a complicated idea. It's just a whole new territory, you know? [SPEAKER_02] I, yes, I think about that all the time. And I think actually one of the really damaging 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 I think particularly the people who are scared, you know, we run, we work with Fortune 50 companies. And so when we're out there and we're talking to people inside the organization, a lot of people feel like they've already been left behind and it's like, no, you can literally go sign into ChatGPT I think about that all the time. And I think one of the really damaging 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 I think particularly the people who are scared, we work with Fortune 50 companies. And when we're out there and we're talking to people inside the organization, a lot of people feel like they've already been left behind. It's like, no, you can literally go sign into ChatGPT and 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 totally new trick. And I don't know, that's just, and to be fair to some people, that's 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. I think people go on there and ask it to write you a poem, and then it writes you a poem and you're like, okay, it wrote me a poem. But I don't know that feeling of being on the frontier. Right. Totally. And I think your point about intuitions and getting intuitions is the big thing. And I think people don't realize is when you're dealing with something fundamentally new, you can't trust 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 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 I think that's why when you first see ChatGPT, you'd be like, oh my God, it can do everything. We're not going to have jobs in a year. And now we're three years in and we're like, yeah, it's awesome. And jobs are complicated. And there's a lot of complex stuff that we do. And I love that in order to build the intuition, all you have to do is use it. And just by using it, you're already on the edge for now. And that's the best. There's apparently a German word called Fingerspitzengefühl. Of course there is. Building fingertip feeling. And that's been my approach. Also, I'm in that hole in the realm that you're discussing. I've been trying to do a lot of analogizing. And that's really hard. But my two that have stuck the most, one is that I watch a lot of YouTube with my kids and we watch this channel called Veritasium. It's a science channel and I love Veritasium. 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. They just have to get on it and feel it. And I really think about that a lot. And then the other one is a deeper cut. 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. We have very good understanding of it. We wouldn't be talking right now. We wouldn't be on computers. We wouldn't have phones if we didn't have a very good grasp of the mechanics that exist underneath it. And his thesis in the book is essentially that what's really lacking is the vocabulary because we all exist in a Newtonian world, not in a quantum one. And we all have words that reflect the deterministic processes of that macro universe. And I think a lot about that. I have not fully been able to pull that string all the way to AI, but I feel like there's a real connection there because I think there's just something really weird about using probabilistic computers. We're not used to using things where you ask them the same question twice and they have different answers. That's very strange. We're 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. These are not normal things that any of us have lived with in our lifetimes. And of course it takes some time for us to adjust. 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, non-deterministic things like other humans. We've just grown up in a world where because of the Enlightenment and the Scientific Revolution and the tools that came out of that are very much deterministic. We've associated that with how we see it. That's how we see the world because of those tools and that language. [SPEAKER_00] And there's a whole other part of the way that we see the world, which is much more squishy and more vibes-based that has been, I think, deeply deprioritized, especially in Western culture. Now that we have a tool that works that way, I think we'll be able to start seeing that again. And that's one of the beautiful things to me about language models is it opens up that whole world again. [SPEAKER_00] Yes, I love it. I do want to go back to cloud code and we should do the phone unless there's other things that you want to share on the computer. But the thing I want to do before we get there, that's on my mind right now, is like you said, you watch this with your kids and I'm curious how, what do your kids think about this? And how are you dealing with it with your kids? Yeah. I love that question. [SPEAKER_00] And that's one of the beautiful things to me about language models is it opens up that whole world again. [SPEAKER_00] Yes, I love it. I do want to go back to cloud code and we should do the phone unless there's, unless there are other things that you want to share on the computer. But the thing I want to do before we get there, that's just on my mind right now is you said, you said you watch this with your kids and I'm curious how, what do your kids think about this? And how are you dealing with it with your kids? Yeah. I love that question. So, I've got a seven and a 10 year old, and obviously I'm pretty deeply embedded in this stuff. And so I've exposed them quite a bit to it. They don't occasionally use the 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. This weekend actually for 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, 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 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 in app to do it. And so I just gave her my phone and V zero. And honestly, that was so amazing to watch, not just because it was so cool to see her do that and build it. And she went through, she was having so much fun. She did 75 revs on V zero. So she really got it going polished and app. She also started to get into really interesting computer science ideas without knowing it. So 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 rather than having adults and kids, you need to call them groups. Right. And so she's getting into data modeling and all of this, I'm watching this conversation happen. And I just thought that was so awesome. And also just a real pet peeve of mine right now. I've gotten this argument with a bunch of people is there seems to be a big conversation that there's a bubble in vibe coding. And because one company or another might have too high of a valuation. And my take on that is I just could not care less what the valuations of these companies are. I think fundamentally, if there's a tool that can allow a 10 year old to build an app, that can't be a bubble. I just can't see a possibility where that is. So, anyway, that's one side of it. The other big one for me that I've been thinking a lot about is media literacy and education stuff. So, both at the schools they go to, and then also I went to NYU and I've 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 and there's a big thing. Some parents in my town wanted to have more of a conversation about it. And as someone who I've thought about this a lot, and I've spent my entire life thinking about technology and its effects on culture. I think I'm relatively grounded in these things. I've put in good hours of thinking. I mean, I know that for sure. And so my take on it is one that you can't hide technology that won't be hidden. Right. So putting our head in the sand is not the best solution. And then my bigger one though is 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 an English teacher there and she was like, what do I do? What do I do about all these kids using AI? And I was like, look, I don't really know what your job is because being an English teacher for 11th grader sounds much harder than my job. But on a really fundamental level, I don't actually think your job is to teach these kids to write. That's a lifelong pursuit. I think your job is to convince them that it's worth learning to write. And so in that way, I'm not sure that anything fundamentally changes because of AI. I think that there are so many parts of the education system that AI really exposes the flaws in the way that we teach. 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. It's like we're so focused on teaching kids the five paragraph essay, while every adult who is a writer has long abandoned that. Because it's all about discovering that you like to write and you know what your own style is and how to do it. It's a big part of working with AI to write is telling it, ignoring it. You're like, no, that's not me. I'm not into that. I'm totally comfortable saying really here. I know you don't think it's a good idea, but I'm cool with it. And so I don't know, I've been having a lot of these different thoughts. I'm actually pitching a class for the fall of 26 at NYU to kind of, the idea for it is, code is essay. And my point of view is this opens up a new way to express yourself. And that, we have all these other ways that we celebrate to express ourselves, but code has been long shut off from people because it is, but actually it's amazing. And it lets you express I know you don't think it's a good idea, but I'm cool with it. And so I don't know, I've been having a lot of these different thoughts. I'm actually pitching a class for the fall of 26 at NYU. The idea for it is code is essay. And my point of view is this opens up a new way to express yourself. And that we have all these other ways that we celebrate to express ourselves, but code has been long shut off from people because it's, but actually it's 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 been thinking about the one other thing I will plug is media literacy. I think it's 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 FT and he's an economist. 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 a lot of what this AI conversation exposes is how bad a job we do with helping and arming our kids and our adults to be truly media and technology literate. And 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 ChatGPT, right? This is a very central skill that we need to arm everybody with. And I am way more interested in that with my kids than I am in worrying about them cheating. That was a very long answer to your question. I don't know if it got at what you were looking for. No, it's amazing. That's exactly what I'm looking for. And it strikes me. Oh, another way to frame what you're saying is for example, rather than having them memorize and be quizzed on the 50 states, asking them to go find the 50 states with ChatGPT and be able to tell when the AI is giving them the wrong answer, because that's a lot more of the meta skill that they're going to need anyway, down the line. And again, I'm not a teacher. I'm sure there's lots of teachers who were like, this is crazy for a lot of probably good reasons, but there's something interesting there where the meta skills become more important than they used to be. And in order to do well at the meta skill, you have to also be able to, to some degree, do the underlying skill too. But we probably could be spending much more time in the meta skill than we are now. The education system isn't really set up to do that anyway. Yeah. And I even think simpler examples is like, I went to a school called Gallatin at NYU and when you graduate, you have to sort of spend three hours with four professors, or three professors, and sort of explain your line of reasoning around why you studied what you studied and you need to be prepared to weave into that defense any of 25 books that you put on your book list. And I was talking to them and it's amazing. That's entirely AI proof, right? Like there's no cheating on that. 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 doesn't mean anything, right? It's like, do you, can you make an argument in this room? And not everything is going to be that easy to be cut off, but there's something really beautiful about that idea. Right. Because it's naturally cheating proof because you're sitting there and it's a question of did you actually internalize these things? And that's way more interesting to me than even whether your essay was good or any of these other things. It's like, did you get it? So yeah, I'm trying to do my best to take a balanced approach and try to at least tamp down some of the fear. I live in a small town in Connecticut and I think there's a lot of fear amongst parents. It was mobile phones and then it was social media and now it's AI and it's another thing that's going to ruin our kids. And I don't think 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 good at the things you're saying, like how do you tell? And a hallucination is just a form of the same kind of misinformation that exists on television and on the internet and in social media and everywhere else. And just sort of encouraging people to get in touch, there's a great part of the truth detective, the kids book. He calls it the brain guard. And 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, explaining this for a nine year old. And I just thought that was such a beautiful way to put it, right? That's what you learn to do when you get good at being on the internet. Is that you're like, wait, I should be more skeptical of this because this is in line with everything I think. Let me just double check. The way 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. That's great. I'm interested. I'm going to get that book. I'm interested in reading it. You should. My plan is to read it to my kids every year from now on. Nice. I love it. Just refresh it. of this because this is in line with everything. I think, let me just double check [SPEAKER_02] the way, I 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. That's great. I'm interested. I'm going to get that book. I'm interested in reading it. [SPEAKER_02] You should. My plan is to read it to my kids every year from now on. [SPEAKER_02] Nice. I love it. [SPEAKER_02] Just refresh it. [SPEAKER_02] All right. Now for the moment we've all been waiting for, show us how you use Claude code on your phone as a second brain note taker. 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 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 on an outside VPN. So the only way to access this machine is through my VPN. Okay. And so then when I go in there, because I sync my Obsidian with Git, so I put it 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. And again, this is in my Obsidian, but I can use this anywhere. Right. So I'll be on the fly. I've got other repos in here. I realized a link was broken on my conference site. And so I opened the repo. I pulled it down. I asked Claude Code to make the changes and I was able to do it right here. So this has been completely wild to me because again, this is very much in that, on Tuesday of this week, we had Monday off. Tuesday I dropped the kids off the bus. And then I went and I sat and had breakfast and I literally sat on my phone and worked on this talk for two hours. And I did it through here, right? On my phone where I was doing real thinking and research and pulling things in and pasting things in and doing all kinds of stuff. And I'm able to do it all. And it just doesn't seem like I could do that kind of thing without that. So yeah, this has been completely revolutionary in my life. And actually one of the things I've been doing lately is setting up. I've got all these friends now who I've set up little partitions of this mini PC in my basement so that they can also run Claude Code on their phone because I like it so much. [SPEAKER_02] Does this make you be like, oh my God, I got to drop everything and just build an actual purpose-built notes app that has Claude Code as a backend for this? [SPEAKER_02] No, I mean, actually, one of the things I've been thinking a lot is, maybe everything should just run in Linux all the time for me. Maybe this is, at least for the short term, this is the answer to all of what I need—to not have anything anywhere else. No, I mean, I'm pretty out of the SaaS game these days. So I don't often think that I should drop everything and do anything. I find this to be a really amazing solution. But this has really changed the way I work and I feel like I can just be anywhere and be on my phone. And I was out, I needed a break. It was 4:30, I went and sat outside for a while and then we had a project that needed to get delivered to a client and a small change needed to be made that I was the best suited to make. And so I just hopped on my phone, I pulled the repo down and I went into Claude Code. It's a tiny little change. The way I find myself using Claude Code the most for code is that mostly I'm having it do the work I already know how to do. I knew exactly what was going on in that situation. I knew why we were having the issue we were having. And so it was, I could have gone back to my computer and opened up a cursor and done it in Cursor either by hand or with Cursor, but I just told Claude Code exactly where to look. I first confirmed that the problem was what I thought the problem was. And then I just had it push a solution and it pushed the PR and then I was done. [SPEAKER_02] Amazing. And I was still sitting outside by the pond. [SPEAKER_02] I love that. Yeah, I've definitely had that experience. I've not done it on my phone. I have my laptop out with me, you know, by the pond or by a lake or whatever, but you're inspiring me. I have a Mac mini in the office that I've been meaning to set up. So I think this is going to be getting one of the other, by the way, one of my other big ahas recently has been building Claude Code helpers for doing setup work. So I'm not been playing with Linux lately. I'm playing with this Omarchie, which is DHH's Linux distribution. And I'm not super comfortable in here. And so I got this whole, this is a Claude Code project specifically to help me configure this box. And it's so nice because I'm like, oh, how do you do this in Linux again? Or what's the Neovim command? Or can you change this? Can you help me install this plugin for Neovim or whatever it is? And so now I have one on my Mac too, where it's like, can you clean up all the Homebrew things? Or I switched from which Python package manager I was using. And it was like, that would have [SPEAKER_02] DHH's Linux distribution. And I'm not super comfortable in here. And so I got this whole Claude code project specifically to help me configure this box. And it's so nice. Because I'm like, oh, how do you do this in Linux again? Or what's the Neo Vim command? Or can you change this? Can you help me install this plugin for Neo Vim or whatever it is? And so now I have one on my Mac too, where it's like, can you clean up all the homebrew things? Or I switched from which Python package manager I was using. And that would have been super overwhelming for me. And I was like, I want to switch from using PIP to using UV. Can you just make that happen? And it did all this stuff for me and it knows all my preferred settings. And so I actually have a version of this where now I've got it so tuned that if I want to launch a new box for doing something, it'll just have all my settings ready to go. And then I can log into Claude code and the Claude code can then set up anything else that didn't get set up in the initial process. That is amazing. That's wild. This is my happy place. [SPEAKER_02] I can see that. Do you have any big projects like this that you've been itching to do or itching to try out? [SPEAKER_02] 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. I mean, this is a joke and not a joke, it's like, I'm super interested in doing more because Claude code has become such an integral part of my life. I'm very interested in the command line. I found myself installing more and more things into the command line and doing more and more work. So I've been using Simon Wilson's LLM command line tool and doing more and more stuff in that. And then layering that back into Claude code. So 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. And so this goes through, similar to, but just in that Obsidian folder and it renames them all. And then it puts them in a metadata table in the attachments folder. And then it renames all the attachment links back. So it just cleans everything up. It does it through Gemini Flash. And so stuff like that's amazing. I'm just having the time of my life just building and tinkering. This is just on the side and I get to do the same thing. We work with Amazon and Meta and PayPal and all these big companies and we're building amazing stuff all the time. I love that. I love the energy. If people are interested in following you or working with you at Alephic, where should they find you? Yeah, so Alephic is Alephic.com. A L E P H I C dot com. And then I also run this thing called Brand, B R X N D dot AI to make it particularly confusing. That's a conference. We've got the conference coming up on September 18th in New York City. 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 dot BRXND dot AI about the intersection of AI and marketing. Those are the best places to find me these days. Awesome. Noah, always a pleasure. Pleasure is all mine. Thank you, Dan. Oh my gosh, folks. You absolutely positively have to smash that like button and 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. 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. How are you feeling? Um, 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. Ask me the kinds of questions, help me think through it. Um, 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, um, uh, sorry, I'm just backing out. So like, if we go into, um, if we go into chats, like these are a whole bunch of the chats that I had, um, like with the interviewer. No, these are chats I was having with chat GPT and Claude and Grock and all of these different things that I went and just grabbed the full transcript of. Um, so, you know, I was also having all these other conversations and then, you know, I'm specifically telling the interviewer, like review all these other things. So actually, you know, I think the first one, there's a, one of these conversations is I originally had this idea about transformers are eating the world. And, you know, the sort of notion there is like, um, you know, there was some research that came out, I think a few months ago that, um, uh, they had found, uh, um, they were able to sort of outperform some specialized, uh, time series modeling, um, uh, 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, uh, a thread in chat, GBT or Claude, and I'll then save that somewhere. 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. Really interesting. Okay. Um, okay. So let's, let's keep going. So, uh, you've got, you've got the sub agent and I actually, I want to like, just actually, I want to 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, uh, one of the apps that we've incubated called spiral, which is a agent to 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. And they're just like, cool, I made it. Here it is. Like a good ghostwriter is going to get to know you and really under you're going to, you're going to 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 can see it. And like, I'm, they need to get it out of you. Like you're, you're actually making it together. And in order to do that, you have to have a really good, um, inter basic interview process to uncover things. And that sounds like you've 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. 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. You know, and it's like its ability to read is incredible. Right. And, and I think, you know, 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. And, um, uh, so yeah, I, I, 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's 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, um, uh, so here 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. It's so good. I love it. Um, yeah, this is like, uh, 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. Cause like, obviously, you know, like the sort of a lot of the economic input, output is sort of measured in the artifacts that it produces. Um, 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. Um, but yeah, it's, it's, um, 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. Totally. Um, okay. So I want to 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 or? Yeah. So that thinking agent is sort of told to, as it asks me questions, kind of 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. Got it. And then, you know, you come back the next day and you're like, oh, I just want to go down this rabbit hole on X, Y, Z thing about the, you know, this wild bill guy. Um, and that you started a new chat, maybe with it, maybe with the sub vision, maybe, maybe not. And that becomes its own new file on that topic. Yeah, exactly. So like I, I, there's the, um, the wild bill stuff started as like deep research and chat GPT. Um, and I, you know, how 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. And, uh, um, you know, I'm kind of thinking about the bits and pieces and trying to make, and I, I think I made a kind of interesting connection in there. Um, uh, 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. Um, 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, um, so, you know, in all of that wild bill 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, I'm, this is still early. I have not like solidified these conclusions. This is like, you know, the regular kind of writing process. Right. Um, 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, you know, sort of paralyze their work better. And that obviously allowed us to have much more powerful and, you know, interesting models and has, you know, arguably kicked off this entire sort of revolution of what's going on. Um, and you know, what we both do for a living. Uh, and so, you know, I think there's this kind of interesting connection. And 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. 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 like 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, I 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. But, um, 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, um, can you catch me up on the last three days of research? Ooh, I love that question. That's so cool. And so, yeah, you can just kind of go in and be like, can you catch me up on the last few days of the research? And, um, it's just gonna 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, right? Like I 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, um, 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. Um, 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. Um, you're not, and it's like, it's often, you know, I find whether it's code or writing, the hardest part is like just picking it up again. Cause you're, you're out of it. And so just to kind of like kickstart that process is sort of amazing. Um, I think what I was playing with here is this idea that, um, bureaucracy was actually like an innovation, right? Um, 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. Um, but you know, um, 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. Um, and so, um, you know, again, my, my kind of whole thesis on AI around all this bureaucracy stuff is that what's interesting about it is that, um, 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. 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 sort of part of what I think. And, um, 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. 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 going to all centralize on this one thing. And now two thirds of the company is unhappy. Um, and like, they've all made sacrifices and, you know, you're sort of in this like, um, 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, you know, 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. They don't care what you use because like, it's all just data structures to them. And so we can then have this sort of central thing. And if, you know, I, when my, you, 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, you know, at the end of the day, this is sort of the fundamental challenge of enterprise software is about like, you know, adoption and change management. And I just think, I think, and I hope, and again, this is sort of the, the optimist in me that like 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 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 is positional encoding means yet. I'm hoping I figure it out in the next two weeks before I have to give this talk. I think, no, but 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. 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, um, a lot of the different products are running into similar things they want to solve for. So an easy example is, um, we have one product called sparkle, which is a little bit like a, um, uh, a finder replacement or spotlight replacement. So it, it, it organizes your files and then it implements really fast spotlight search. I'm a user. I like it. Okay. So then you, you know, um, and, uh, so that's really cool. And, uh, agentic search coming soon, uh, check it out. And, uh, and we're just building a new product, new GM, new stack, uh, called para, which is essentially an in-house counsel. So it's short for paralegal, not para, like, you know, Tiago Forte para. Um, and, uh, 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 we ever sign this contract or what's the employee agreement template or whatever, it just gives you the answer. And it's just a cloud code sitting on top of a directory. Um, and, and a thing that we needed to implement for that is, uh, 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 sparkles 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 that, all those things. Right. And what we did instead is we just added a pre D who's the developer for, for, for para right now. We just added her to the sparkle repo. And I was just like, just ask cloud code to figure out how it works and just do your own version. Um, and so you get this, like sort of tacit code sharing where we all get better, but without having to do the work of, uh, abstracting and modularizing everything, because the, the percentage of things that you can do that for are pretty low, cause it's a, it's a heavy lift. And I'm seeing that happen all the time where just having a bunch of repos that are all solving some of our problems, but in different environments in different ways, you, everyone gets more productive because AI can kind of translate. I've, uh, one thing we've done there, uh, we also, we, so at Alephic, we do a whole bunch of building for, uh, very large brands. Um, and so we sort of build all kinds of AI things and, um, 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, um, a few times for that same purpose, which is just like, um, you know, you're just in cursor or cloud code or whatever, and you're like, Hey, can you go like, look up, uh, we run, we've got an internal tool, um, called intelligence that just sort of is a wrapper around a whole bunch of like stuff that we use. Right. So it's like got some CRM stuff and it's just like been a fun place to build the things that we need to run our company. Um, 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, um, you know, look at how I implemented that thing there and take those sort of best practices and just pull them over. Um, and yeah, I think that stuff again, that's where I really do believe in this idea. I, 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 aha moment with AI. And, um, uh, mine was, uh, 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, uh, I got access to build a chat GPT plugin room and plugins came out and like, uh, two and a half years ago or something now, you mean 50 years ago, 50 years ago. Um, uh, and you know, I, 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, like there's a going to be a contract and you know, as long as you follow that contract, it works. And I go read the plugin spec and it basically is like, Oh, you just stick a manifest.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 to 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. Like I wish everything worked that way. I wish I didn't always have to adhere to the big companies contract for how to send and receive data. Um, 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, um, 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. 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, I 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. And like, um, 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, um, 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 that's why I love this moment. Cause 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? I, yes, 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, um, 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 and it's like, no, you can like literally go sign into chat GPT and like had do something like nobody's thought about doing with this thing yet, because there's just so much white space to explore and, and you might discover some totally new way of using it and, or like totally new trick. And, um, I don't know, that's just, 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, you know, it's like, you ask it to write you a poem, and then it writes you a poem and you're like, okay, it wrote me a poem. Um, but, uh, I don't know that feeling of like that feeling of, yeah, it's like being on the frontier. Right. Totally. And yeah, I think that, um, your point about intuitions and getting intuitions is the big thing. And I think people, 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 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, um, and I think that's why, like when you first see, maybe when you first saw chat, you'd be like, oh my God, it can do everything. Like we're not going to 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. And there's a lot of complex stuff that we do, you know? Um, 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, uh, for now. And yeah, I think that's the best. There's apparently there's a German word called finger Spitz and fuel. Of course there is building fingertip feeling. And that's been my, um, uh, just because I can't resist. Also, um, I, I, I'm in that hole in, in sort of the realm that you're discussing, like, uh, 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, um, uh, you know, but my two that have sort of stuck the most one is just, um, I watch a lot of YouTube with my kids and, um, uh, we watch this channel called Veritasium. It's a science channel and I love Veritasium. Yeah, it's great. Um, 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. Um, 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. Um, they just have to get on it and feel it. And, um, and so, you know, I really, that video is amazing and, um, uh, it's, that channel is amazing. And, and, but I, I've thought a lot about that. And then the other one, which is a sort of deeper cut is, um, uh, there's an amazing book about quantum physics called beyond weird, um, by Philip Ball. And, um, the thesis of the book is basically that like, there's nothing particularly strange about quantum physics that we like, we have 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. 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 asked them the same question twice and they have different answers. Like that's very strange. 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. 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, non-deterministic things like other humans. We've just grown up in a world where because of, you know, the enlightenment and the scientific revolution and the tools that came out of that are very much like deterministic. We've associated that with how we see it. Like that's how we see the world because of those tools in 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 like vibes based that has been, I think, deep, deep prioritized, 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. And that's one of the beautiful things to me about language models is it opens up that whole world again. Yes, I love it. I do want to go back to cloud code and we should do the phone unless there's, unless there are other things that you, that you want to share on the computer. But the, the thing I want to do before we get there, that's just on my mind right now is like you said, you said, you know, 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? Um, yeah. Um, I love that question. Uh, so, uh, I've got a seven and a 10 year old, um, 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. Um, uh, you know, they don't, uh, 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. Um, this weekend actually for the first time, my 10 year old, um, uh, she was really eager to be every year. Um, uh, my wife and her sister and brother and mom and, and all the cousins that 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. Um, and, uh, I encouraged her to, uh, vibe code in app to do it. Um, and so I just gave her my phone and V zero. And, um, honestly, that was like so amazing to watch, like, not just cause it was so cool to see her do that and build it. And she went through, she was having so much fun. She did 75 revs on V zero. Um, uh, so she like really got it going polished and app, uh, 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 presence to adults and the kids give presence 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 to happen. And, um, I just thought that was so awesome. Um, and, you know, also just like a real pet beam 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 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 just like, can't see a possibility where that is that. So, um, anyway, that's sort of one side of it. The other big one for me that I've been thinking a lot about is, um, uh, is sort of media literacy and education, um, stuff. So, um, you know, both at the sort of schools they go to, um, and then also I went to NYU and I've sort of, um, been having more and more conversations with the Dean of the school I went to there. Um, and, uh, um, there's a lot of fear inside schools right now about AI and about cheating and, um, there's a big thing, you know, so some parents in my town, they, you know, they wanted to have more of a conversation about it. And, um, you know, as someone who I, I've thought about this a lot, but I've also just like been, I've spent my entire life thinking about sort of technology and its effects on culture. And I, I think I'm like relatively grounded in these things. I've, of like, I've put in good hours of thinking. I mean, I know that for sure. Um, and so, you know, my, my take on it is like one that sort of, you can't hide technology that won't be hidden. Right. So it's like, you know, putting our head in the sand is not the best solution. And then, you know, my bigger one though, is like, I was out, um, a friend of mine asked me to come, um, talk to a school two years ago about AI, um, uh, out in LA. And, um, 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 11th grader sounds really much harder than my job. Um, but on a really fundamental level, like, I don't actually think your job is to teach these kids to write. Cause 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, 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, 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. Cause 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. I know you don't think it's a good idea, but like I'm, I'm cool with it. Um, and so, you know, I don't know, I, I've been sort of having a lot of these different thoughts. I'm actually pitching a class for the fall of 26 at NYU to kind of, um, the idea for it is, uh, code is essay. And my, my sort of point of view is like this sort of opens up this new way to express yourself. Um, 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 like, you know, 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 been thinking about the one other thing I will plug is, um, media literacy. I think it's a big piece of it. A lot of people are afraid of these models and hallucinations. And, um, there's a book, um, by a guy named Tim Harford who writes for, uh, the FT and he's an economist. Um, 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. Um, 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. And, you know, like being really good at knowing what's real on social media turns out to be also really useful for like differentiated between hallucinations and non hallucinations in chat GBD, right? Like this is a sort of, to me, a kind of very central skill that like we need to arm everybody with. And, um, I am sort of way more interested in that with my kids than I am in worrying about them cheap. That was a very long answer to your question. I don't know if it got at what you were looking for. No, it's amazing. That's exactly what I'm looking for. And it's sort of what it strikes me. Oh, 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, uh, asking them to go find the 50 states with chat GBD 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 going to need anyway, down the, down the line. And again, I'm not a teacher. I'm sure there's lots of teachers who were 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, um, we probably could be spending much more time in the meta school than we are now in the education system, like isn't really set up to do that anyway. Yeah. And I, I, you know, even, I think even simpler examples is like, I went to a school called Gallatin at NYU and, and, um, 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 and, and, 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, um, uh, any of 25 books that you put on your book list. Um, and, you know, I was talking to them and it's like amazing. That's like entirely AI proof, right? 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, uh, it doesn't mean anything, right? Like it's, it's like, like, do you, can you, can you make a, an argument in this room? 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? Um, and I don't know, that's way more interesting to me than even like, was your essay good or any of these other, it's like, did you, did you get it? Like, um, and, uh, uh, so yeah, I, I don't know. Um, I'm, I'm, I, I'm trying to do my best to kind of like, um, take a balanced approach and, um, try to at least sort of like tamp down some of, I live in a small town in Connecticut and, you know, I think there's a lot of fear amongst parents, you know, 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. And, um, I don't think that that is true. Um, uh, 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, um, you know, just sort of like encouraging people to kind of get in touch. There's a great part of the truth detective, um, uh, for the kids book, he could, 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 is for a nine year old. 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. Um, 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. That's great. I'm, I'm interested. I'm going to get, I'm going to get that book. I'm, I'm interested in reading it. You should. My plan is to read it to my kids every year, uh, from now on. Nice. I love it. Just refresh it. Um, all right. Now for the moment we've all been waiting for, show us how you use Claude code on your phone as a second brain note taker. Okay. So here we go. So I am going into an app called termious term is just a terminal. Um, and, uh, what is allowing all this to happen behind the scenes is in my basement. I have a mini PC and on that mini PC, I have a thing called tail scale running and tail scale 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. Um, so the only way to access this machine is through my VPN. Okay. Um, and so then when I go in there, um, because I sync my obsidian, um, um, with, uh, Git, so I put it, it's on GitHub, uh, in a private GitHub. Um, 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, um, what's new in the last two days. Um, I can access any of my agents. Um, I can do anything. 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. Um, you know, I, I realized like a link was broken on my conference site. And so I, uh, um, I just, uh, opened the repo. I pulled it down. I asked Claude code to make the changes and I was able to do it right here. Um, so this has been like completely wild to me because again, this is very much in that, like, like on Tuesday of this week, um, we had Monday off Tuesday. I dropped the, I dropped the kids off of the bus. And then I, uh, I went and I sat and had breakfast and I literally sat on my phone and worked on this talk for like two hours. Um, 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 kinds of stuff. And, you know, I'm able to do it all. And it just, it doesn't seem like I could do that kind of thing without that. So yeah, this has been like a completely revolutionary change in my life. Um, and, uh, actually one of the things I've been doing lately is like setting up, I've got all these friends now who I've set up, um, like little partitions of this mini PC in my basement, um, so that they can also run Claude code on their phone because, um, I like it so much. Does this make you be like, oh my God, I got to drop everything and just build a actual purpose-built notes app that has cloud code as a backend for this? 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. Um, no, I mean, I'm, I'm, I will say I'm, 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. Um, and, uh, um, but no, I mean, I, this, but this has really, 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, um, you know, I mean, I was out like, uh, I needed a break. Uh, it was, you know, 4 30, I went and sat outside for awhile and then, um, we had a project that needed to get delivered to a client and a small change needs to be made that like, I was the best suited to make that change. Um, and so I just like hopped on my phone, I pulled the repo down and I, um, 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, you know, I'm like, Oh, I like, I know exactly, I knew exactly what was going on in that situation. Um, 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 a cursor and done it in cursor either by hand or with cursor, but it was like, I just, I was like, I told cloud code exactly where to look. It was like, and I first confirmed that the problem was what I thought the problem was. And then I just had it push a solution and it pushed the PR and then I was done. Amazing. And I was still sitting outside by the pond. I love that. Um, 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. I have a Mac mini in the office that I've been meaning to set up. So I think this is going to be getting one of the other, by the way, um, one of my other, uh, I'll just take you out of here for one sec, actually, just to show you this. One of my other big ahas, um, recently has been, um, uh, building, um, Claude code helpers for, um, doing, uh, uh, basically like, uh, setup work. So it's like, I'm not, I'm like been playing with Linux lately. I'm playing with this Omarchie, which is DHH's Linux distribution. And I'm not like super comfortable in here. And so I got this whole, this is a Claude code project specifically to help me configure this box. And it's like, so nice. Cause I'm like, oh, how do you do this in Linux again? Or like, what's the Neo Vim 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, um, can you clean up all the homebrew things? 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 want to switch from using PIP to using UV. Can you like, just make that happen? And like, just did all this stuff for me and it knows all my preferred settings. And so, um, I actually have a version of this where like, now I've got it so tuned that, um, if I want to launch a new box for doing something, it'll just have all my settings ready to go. And then I can log into Claude code and the Claude code can then set up anything else that didn't get set up in the initial process. That is amazing. That's wild. Um, this is my happy place. I can see that. Are you, do you have any, like, um, uh, are there, are there any big projects like this that you've been itching to do or itching to try out? Uh, no, not really. I mean, I've been having a ton of fun. My, my server stuff has been a ton of fun. I've been doing a lot of that. Um, I'm, uh, I'm, I'm, I'm like I said, I mean, this is kind of a joke and kind of not, it's like, I'm super interested in, um, like doing more, I, because Claude 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, um, and like doing more and more work. So I've been using like, uh, um, 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. 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, um, and so this goes through very similar to, um, uh, sparkle and, but just in that obsidian folder and it, it renames them all. And then it also puts them in like 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. It just does it through Gemini flash. Um, and so it's like, I don't know, stuff like that's kind of amazing. Um, 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, this 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 like building amazing stuff all the time. I love that. I love the energy. If people are interested in, uh, following you or working with you at Alephic, uh, where should they find you? Yeah. Um, so Alephic is Alephic.com. A L E P H I C.com. Um, and then I also run this thing called brand B R X N D dot AI to make it particularly confusing. Um, that's a conference. We've got the conference coming up on September 18th in New York city. You should come if you're around, it'll be really fun. We're going to talk about marketing and AI. Um, and I also write a newsletter there at newsletter dot BRX and D dot AI, uh, about sort of specifically at this intersection of AI and marketing. Um, those are kind of the best places to find me these days. Awesome. Noah, always a pleasure. Pleasure is all mine. Thank you, Dan. Oh my gosh, folks. You absolutely positively have to smash that like button and 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. 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. How are you feeling? How are you feeling? How are you feeling? How are you feeling