How Nat Eliason Made $200,000 in a Week Teaching AI - Ep. 48

[00:00] I mean, I've never seen anything like this. The way the course starts out is I show people, you know, you get cursor open up and running and then you hop into this agent tab and you can say something like, can you build me a simple Pomodoro timer in HTML, CSS and JavaScript? Keep it as simple as possible. [00:19] And you hit go and it'll think for a moment and then it'll just start making the files. So there's nothing in this folder. And so right now it's generating the HTML. And, you know, I didn't have to create this file. I didn't have to copy anything over. It just automatically plugged it in. This is like the simplest version of how you could build a website or build a web app, right? Just an HTML, a CSS and a JavaScript, like those three files. And what I want to underscore here, if you did one prompt and then it's like it's doing these multi-turn edits, [00:49] plan, it creates a file, it writes the file, and then it checks to make sure that the file is working in the linter. What I think is so crazy about this is like, we're just watching this happen, right? Like literally two years ago to do this, we would have had to type every single character into every single one of those files. That is wild. It feels like the dark ages to like hand type your code. There are 700 students in the course. There have only been two instances [01:19] needed to help somebody troubleshoot something that they couldn't resolve using cursor. I thought I was ever going to do a course again. I put up a page where people could buy and it did $200,000 of sales in a week.

[01:43] Matt, welcome to the show. [01:45] Thanks for having me on, Dan. Again, right? Yes, this is your back. I'm back. You were here in the earliest phase of the show. You took a bet on me, on us, when we were nothing, and now we're here. [01:59] We've been taking bets on each other for a long time. We have been. And you're one of my favorite people in the online writer space, or really just in general, but let's say in the online writer space. [02:15] And you have this ability to go really deep into something right before it gets hot and know everything about it and then succeed at it and then move on to the next thing. And I think people get so caught up in what am I going to be and who am I going to be? And you've had all these different topics that you're just the master of. [02:32] And, and you just like, you throw yourself into it with wild abandon. And you, you know, when we first started working together, you were, you were into SEO, then you moved into crypto, you, you. [02:44] wrote a book, which you released recently that I love, I think is amazing. And you sort of transitioned from online writer to author. And then most recently, you've been in the AI coding game and you launched this new course teaching people how to build with AI. And you have this really fun, I'm going to shut up in a second, but you have this really fun course arc where

[03:14] Rome, you made Rome hot and launched a course and like bought a house with the money and then disappeared from from the game. And now you're back. And it's really fun to see. Tell us about that. Well, yeah, I mean, I owe some credit to that to you guys, because I don't know if you remember how this started, but Adam Kiesling. [03:35] Adam Kiesling, our first, Every's first employee. Yes. Yeah. He had a tweet in October of 2019, I think. October or November. [03:47] where he said, wow, I just tried this thing called Rome Research, and it's really cool. And nobody really knew about it. [03:53] back then. [03:56] And [03:56] I was... [03:58] I was still running my marketing agency growth machine, but was looking for, you know, [04:03] interesting things to explore. And so I dived into it and was just kind of blown away by the tool and started tweeting about it and talking about it. And that made other people really interested. [04:14] And I... [04:15] You know, just said like, hey, does anybody want me to do a course on teaching how to use Rome? And a lot of people on Twitter responded positively. And I just put up a PayPal link. And I think I got... [04:27] $10,000 or something worth of pre-orders. [04:31] Off of those tweets before I'd written any or written anything for the course is like, well, I better go do this now. Pretty good validation. Good validation. And then launched the course and it did something like 600 grand in sales over the next year, which was bananas.

[04:47] Yeah. And I owe a lot of that to the Roam team because they didn't really want to build onboarding for their product. They were focused on other stuff. And so they said, if you take Nat's course, which was $100, we'll give you $100 in... [05:01] credit. [05:02] for signing up because it was like $15 a month. And so that was what, six months of free usage. And they said, yeah, you know, take that course and you'll basically get it for free because you'll get the product for six months. And so obviously that drove a ton of sales. [05:15] And we had a really good thing going. And then I... [05:20] I ended up being like, okay, I kind of feel like I don't want to keep doing this. I didn't want to keep doing the cohort model, and that ended up [05:28] Being, I think, a pretty good decision on accident just because Rome's development fell off quite a bit. Competitors popped up like Obsidian. And I think an easy way you can kill a good course business is by hiring a ton of employees and building a huge apparatus around it. [05:47] only for the interest in it to fall off, you know, two, three years later. And now suddenly you have all of these liabilities that you've accumulated and you lose the huge upside that you had when it was, [05:57] maybe just you are really small team and crazy cash flows. So, um, and, and yeah, as you alluded to, I used a lot of the profits to buy a Airbnb property outside of Austin in like, [06:11] June of 2020, so absolute... [06:15] Pitt. [06:16] of the real estate, like, you know, local pit for the real estate market.

[06:19] We got a really good deal on it. Turned it into an Airbnb. Tried doing the Airbnb thing for a bit. That turned into a miserable experience that peaked with a frat party throwing a rager at the house. Somebody, I kid you not, pooping in the bathtub. Oh, my God. And leaving it for our cleaner to find. And she was wonderful. She was like a Rottweiler. She was so pissed at the people. She wasn't pissed at us. [06:49] can't believe these people. They disrespected your beautiful... She was amazing. She handled it so well. But they did that. They broke off an outdoor water faucet that flooded the whole yard and caused all this damage. And then [07:04] Literally two weeks later, Austin had this terrible freeze that blew out the shower pipes upstairs and flooded the second floor. And it was like a $15,000 repair. And after those two things happened, we said, okay, this sucks. This is not worth it. Anything we think we're making, we're losing in repairs. [07:20] And so we sold it in May 22, which was the peak of the Austin real estate market. It was like literally just two happy accidents in a row. And it ended up being like a 6x cash on cash return in a year and a half on a real estate investment, which just [07:41] Doesn't. [07:41] happen ever. You just have great timing. So I just want to fast follow all your trades. Sometimes. I also opened a cafe in January 2020. So it's not always the best timing.

[07:55] Crypto Confidential coming out in the middle of last summer when nobody was talking about crypto, that could have been timed, I think, a little bit better. It picked up when the market picked up in the fall. But yeah, those timings were pretty great. So [08:09] Fast forward to today, you and I have been talking about [08:13] some of the cool potential with this AI stuff. I remember when GPT-3 launched, you and I were playing around. You were doing it a lot more than I was. We were texting about this, about, okay, you [08:22] train these models? Can we use them in our writing and things like that? Do metaphors and all this kind of stuff? Yeah, yeah. I was trying to build a stoic bot. I was calling it stoic therapy, so I was training it on Marcus Aurelius and Seneca, so you could have a conversation with it like you would a therapist, but it would respond the way [08:42] a stoic wood and it wasn't great back then and so i kind of put it on the shelf and you you kept going with it to your credit you [08:50] It went a lot harder than I did. I put it on a shelf for a while and then I [08:55] last winter, [08:57] So December 23 into January 24, over my holiday break, I started playing with it again because these AI augmented software tools, Cursor, predominantly were just coming out. And I had this question of like, OK, could I use this to actually build a mobile app? [09:15] because I'm primarily a writer. I've been doing all of my writing, tracking in a spreadsheet. I thought it would be cool to have a Strava-like app [09:23] for tracking writing. And it seemed like you could maybe build that without a ton of knowledge using cursor. And so I tried and it worked. I got a basic version of the app working pretty quickly. I think I still pay for that, by the way. Oh, do you? Okay. Well, I won't be hurt if you cancel. I mean, it turned out that nobody really wanted that tool, which was fine. You know, that's good for me. Yeah, I know. Like I even I kind of stopped using it after a while. I was like,

[09:53] can kind of be replaced by Excel at a certain, it has to reach a certain level of pain to graduate from Excel. And that level of pain just wasn't there. But, [10:02] That got me started using... [10:05] these tools to write software for my life. But back then it was, it was okay. You still had to have a pretty good grasp of programming to get anywhere with it. And then it feels like four months ago, maybe so fall of 24. [10:21] the agents started coming out. [10:24] So you had the replet agent, you had stuff that came out more recently, like Bolt and Lovable. [10:31] And cursor added its own agent. And this was this really new step function in [10:38] how much programming you could do without knowing any programming. Because [10:44] If you had a rough idea of what you wanted, a basic understanding of programming, you could kind of just prompt it and it would start... [10:52] writing full apps for you. [10:54] And so after Crypto Confidential came out, I've been working on the sci-fi novel and I've been [11:01] going really hard on that the last six months. And I finished a draft of it in December and was letting it sit in the drawer. And I said, okay, you know, while this is sitting, let's go play with these tools because maybe there's a way I can actually use them. [11:13] for my work. [11:15] And so the first thing I thought about was... [11:19] you know, I'm sure you have this too. Maybe you don't anymore since you have, um,

[11:23] spiral. But a lot of people who do writing have a bunch of saved prompts somewhere. And they're kind of copy and pasting those into Claude to get similar results. And my good friend, Nathan Baugh, he's also a fiction writer. We write together every week. We were trading prompts back and forth. But it was kind of this complicated process of, okay, we've got to like paste it into Claude and then get the output. Maybe we have to make a new chat. And you kind of have to jump through [11:53] Yeah. [11:55] And the other benefit of doing that is, you know, with some models, you run into a [12:00] text limit issues, right? [12:03] The 01 context window is actually... [12:07] 200,000 tokens or whatever, but per chat, it's only 40,000. So if you want to put in a full manuscript of your book, you have to break it into three or four messages, which is super messy. [12:17] And so I was like, well, let's just [12:19] use these new cursor agents and let's just try building an app to help me edit my book. [12:25] And I started hacking on it. And literally within a day, I had something that was better. [12:30] than what I could do on the Claude front end. And that was pretty awesome because one, I was still getting Claude Sonnet responses, but I had all of my prompts saved and it was slowly turning into this editing tool. I can show it to you in a minute. I want to see it, yeah. Yeah, yeah. [12:51] Unfortunately, it's not done. It's not nearly to the point that I thought it would be at this point because I started tweeting about it. I was like, yeah, I built this thing. This was so easy. And then Nathan and I started a podcast called Between Drafts where we're talking about the journey of being an author and growing your audience and selling books and writing and editing.

[13:14] And... [13:14] I mean, you know, a podcast requires a decent amount of work on the back end. You've got to get the show notes and the timestamps and you've got to format it for YouTube and Spotify and you've got to make social media. And like that takes a decent amount of work. And I've hired people to help with that in the past. [13:28] But my thinking was, okay, well, I can probably create an app to do this too. And so I started hacking on that. And a day later, I had an app where I could just upload an audio file, and it would make a nice description, timestamps, you know, so it would handle all the show notes, it would format it in different ways. So I could just copy and paste into YouTube and Spotify and my blog. And I was like, [13:48] This is sick because this is now saving me a few hours a week and is just like very useful for running a podcast. And so, you know, that was useful. And then I was tweeting about that. And then it literally was just like history repeated itself. I thought I was ever going to do a course again. I didn't really want to get back into that business. But somebody tweeted at me and said, like, hey, I really want to learn how to do some of this stuff. [14:12] you're doing, it looks really cool. So I put up the bat signal again, was like, Hey, does anybody want me to do a course on this? Just like building your own apps with AI. I got a hundred plus responses to that tweet saying, yes, please do it. I put up a, [14:26] a page where people could buy and it did $200,000 of sales in a week. That's crazy.

[14:34] I mean, I've never seen anything like this. I, I don't know if, [14:42] I, I've never heard another story like that of a course launch. Like obviously people have done much bigger course launches. There have been, except for your own last course you did. I mean, but it didn't blew that out of the water because it didn't really start selling until the course was done. I mean, the, [14:58] You know, it was just like the pre-sales. [15:01] And so that's literally all I've been doing the last three weeks is recording videos and getting that built out. And it's been really, dude, it's been so cool to see people go through the course and to see them posting all this stuff that they've built that they didn't know how to build beforehand and not stuff that I'm directly teaching them. They're just like, OK, I've learned how to do this. Now I can go build this other thing that I want. [15:31] his site. Kat Lavery built a journaling tool that's like forced warning pages where it deletes everything you wrote if you stop writing for more than five seconds. It's just like cool stuff people are making. And yeah, [15:44] I literally just finished the last video of the last unit this morning. So I'm hopefully going to get all that edited and get it plugged in and I can, [15:55] I'm still bug fixing, so I can't do a full demo right now. But literally, the thing that I did for the course is I [16:04] like got a fresh computer, right?

[16:07] to start recording from. So I could show like, here's a computer that's never done any development. And like, let's get the development environment set up. The way the course works is it kind of like walks you through building these basic apps and then [16:22] In the end, I sort of build this whole... [16:25] AI content studio, like landing page and Stripe payments. So for people who are listening, basically you're on this website. It looks like pod buddy.ai. And this is pod buddy.ai.com. Somebody had the dot AI. Very frustrating. Pod buddy.ai.com, which I guess is the, is, is what students who are in the course are going to end up with when, when they're done. [16:55] a second. [16:57] So, yeah, so it looks like it's a podcast studio. So it does transcriptions, content generation, social media. I can't believe you're competing with me here. We got to, we're going to. [17:08] Wait, did you build an app for this? Well, I mean, Spiral. Spiral is kind of like this. Yeah, yeah, yeah. This is sort of like Spiral, but it's okay. This is very cool. Yeah. And I think like what's most interesting to me about this is how complete it looks. Like there's a lot of things that people are building and... [17:27] I did a course like this a year ago, and it was not as popular as this, but it was a big deal back then. It was like how to build an AI chatbot with like... Yeah, yeah, I remember. And that feels so archaic now. But what's interesting is I had a lot of concerns about like, okay, people who are non-technical are taking this. Is it going to be possible for them to actually do the course? And it turned out that it kind of was, but it was a big pain.

[17:57] And the amount that we could do is sort of limited. And I had to provide a lot of sample code and all this kinds of stuff to make it work. And we're just in a completely new era right now where English is just... You can just build with English way better. And if you have enough gumption and stick-to-itiveness to copy-paste back and forth between 0101 and your cursor instance, you can get through any bugs you find. It's crazy. Dude, that was my big concern with doing the course. [18:27] this is popular, am I going to have... [18:30] dozens of people messaging me every day with the bugs that they're running into and the problems that they're having that I'm going to have to try to troubleshoot remotely. Because if that happens, this is not going to be sustainable and it's going to be miserable. But the first lesson started going up two and a half weeks ago. There are 700 students in the course. There have only been... [18:51] two instances. [18:53] where I needed to help somebody troubleshoot something that they couldn't resolve using cursor. [18:59] That's wild. And it's, yeah, absolutely insane. Because it's sort of like the course starts by showing you how to use cursor and how to troubleshoot things and how to get errors fixed. And I, I, [19:12] I err on the side of playing dumb through the course too, where even if I know how to fix something, I'll still kind of like let cursor do it to show that it can handle stuff. And yeah, like people can just, [19:24] figure it out. It's pretty wild. And, you know, there is a common problem of as the code base gets bigger, as the app gets more complex, it starts hitting more issues and you start having to get a little more intelligent with your prompting. But, you know,

[19:39] People are kind of figuring that out too. And it's really neat to see just how much you can build now without having that much of a programming background. And... [19:50] I've noticed too, like it's making me a better coder, because I'll go look at how it's doing things, you can ask questions about why it did things certain ways, it'll explain it. And it's kind of a neat new way to learn programming. I think this is just how people are going to learn programming now. [20:03] I agree. Totally. Can, can, cause I think that for some people listening and watching, like they're, [20:09] Maybe they know about AI, but they haven't used Cursor yet. Or maybe they used Cursor a year ago, and they're like, I kind of get it. But I think the whole agentic experience, which I actually first used WindSurf, and I was like, holy shit. WindSurf, I think, was the first one to really have the full agentic thing, and then Cursor now has it. Can you just show us a little sample of making something with Cursor, and then we can talk about it from there. I do want to get into your more advanced Cursor tips, just honestly selfishly. [20:39] table for people who don't yet know what's possible. [20:43] Yeah, yeah. So let's just sue. [20:48] Cursor, if you've used it before, it just had this chat feature where you could... For people who are listening, basically, you have Cursor open. And Cursor is a development environment, right? So it's like you've got your file system on the left, you've got your files in the center, and then you have a chat window on the right. And Cursor always had this sort of like... Not always, but like... Yeah, I guess always has had this chat. But chat was like, you know, you couldn't... It wouldn't go autonomously.

[21:18] edits for you. You had to select the edits and say apply, and it was just kind of a mess. Yeah. Yeah. So now it has this Composer tab next to chat, and Composer is basically their agent. So it has these options, normal and agent. If you select agent, it will... [21:35] basically do everything for you. So the way the course starts out is I show people, you know, you get cursor open up and running and then you hop into this agent tab and you can say something like, can you build me a simple... [21:49] Pomodoro timer in HTML, CSS, and [21:53] JavaScript, keep it as simple as possible. And you hit go. [22:00] And it'll think for a moment and then it'll just start making the files. [22:05] So there's nothing in this folder. And so right now it's generating the HTML. [22:10] And I didn't have to create this file. I didn't have to copy anything over. It just automatically plugged it in. Now it's going to say, let me create the CSS file with some basic styling. Okay. [22:21] And this is like the most, this is like the simplest version of how you could [22:25] build a website or build a web app, right? Just an HTML, a CSS, and a JavaScript, like those three files. And what I want to underscore here for people who are listening or watching is like, you did one prompt, and then it's like, it's doing these multi-turn edits, where it's like, it has a plan, it creates a file, it writes the file, and then it checks to make sure that the file is working in the linter, and then it just does the next one and the next one

[22:55] crazy about this is like, we're just watching this happen. Literally two years ago, to do this, [23:04] Even if you knew how to do it, which we both would have been able to do this, we would have had to type every single character into every single one of those files. That is wild. It feels like the dark ages to hand type your code. And it was inconceivable that this would be possible. And now it is. [23:22] Yeah, I mean, this is so it's 20 lines in the HTML, 40 lines in the JavaScript, 46 in the CSS. I mean, if we were typing this out manually, like we would have had to two years ago, it's probably like 20, 30 minutes of work. [23:34] Right. Like it's going to take a little bit, but. [23:37] It did all of that in 30 seconds. We can hit accept all. And then I should be able to reveal the index HTML in the finder. And then I'll double click on it. And we have a Pomodoro timer. Oh, my God. I could just hit start and it's... [23:56] gonna start the timer. This is running, right? We're watching it live. It's working. And this is such an incredible moment. You know, I had all these people texting me being like, "Oh my God, this is magic." I mean, it's just so cool. And, you know, we can say like, you know, we can just go back to cursor and we can say, you know, I'll start a new chat and I'll say, "This is working great, but the design is a little boring." [24:22] Can you spruce it up to make it look like a modern...

[24:27] web app, maybe use Blue as a [24:32] base or primary color. And then I'll just hit enter again. While it's working, this is a specific cursor composer tactic that I'm kind of curious about is when do you start a new composer window? So I start a new window whenever I don't want the previous context in the conversation. Right, but how do you know that you don't want the previous context? Like why did you do it just then? [24:55] The way I think about it is if I'm working on a new feature or some new part of the app, I'll start a new window. [25:03] Or if it's getting stuck fixing a bug and it can't seem to figure it out, I'll start a new window. Got it. This is, again, another little interruption. But are you ever using O1 or O1 Pro for this? And how are you incorporating that, if so? I'll use them in two situations. So one, if I'm running into an issue that Sonnet's having trouble fixing, then I might go to O1 in the chat and have that try. [25:33] I'll use O1. So, for example, in the course for the capstone with the PodBuddy tool, once it was close to being ready to deploy to web, I went to the chat. I selected O1 and I said, can you please do a deep review of all of this and see if there's anything that we need to fix before we push it live? That's cool. [25:55] security, think about [25:57] user experience, you know, every let's and then create a checklist of everything we need to do before we go live. And it actually made a markdown file, I can go find it here.

[26:09] Show it to you. [26:10] Thank you. [26:11] Yeah, so it created this whole deployment.md file. Interesting. And then did you have the agent go through the deployment file or the markdown file? I had it do some of it, yeah. I started pasting a couple of these one by one into the composer and had it start executing them. And that was really helpful. But while we're talking, it went ahead and it did this redesign of the Pomodoro timer. If we go back to our browser and refresh, look, we have our nice new design. I love that. [26:41] For people watching, it's now blue. It's now blue. It's not like people listening, it's now blue. But it changed fonts too. That's good. It followed the instructions. That's good. I love tracking the new norms that come about. And I think that a shift that's starting to happen, it's happened for me. I see that it's happening for you just watching you use this. And I think it's happening for other people. When we first started using AI, we started to... [27:08] look line by line of the changes it was making and like making sure that the changes were okay, except one by one. And then now everyone just presses except all. Yep. Just brain off. And I just want like a t-shirt that just says except all. [27:25] You should make that. Because I think it's so of the moment that like, that's just a totally new thing that we never would have done before. And I think what it speaks to is, [27:35] Um, [27:37] Thank you. [27:37] There definitely are still cases where the underlying code and underlying code quality matters. But especially for this stuff, like this early stuff, it doesn't matter.

[27:50] And we don't need to care how it's being done. It does a really good job. And that's totally different. And it's a totally different way to learn programming, as you said, because like... [28:00] When I learned to program, and I think when you learned to program too, like, so I learned to program from reading books. [28:06] when I was in middle school. [28:08] I literally would go to a bookstore and buy a book on basic or C++ or whatever. [28:15] The first six months of learning to code, you just learn all the abstractions. You just learn if statements and for loops and you have no idea how it levels up into anything that you want to make. And you have to be willing to get through that hump to actually make anything. And... [28:32] Um, [28:33] And students today, you just type a thing and then it's like, [28:37] There it is. And even saying this, I sound like my dad. I sound like I used to have to walk, hike up to school uphill in the snow both ways or whatever. He doesn't really sound like that, but he does sort of totalize. And I just think it's so different and so much better because how many people were not able to build things because they couldn't get through that six months [29:07] things now that wouldn't have been able to before. And I just think that that's such a good thing. [29:11] Oh, yeah. I mean, those are the two most common testimonials that I've gotten. One is that I've wanted to be able to do this for years and have never taken the time to sit down to figure it out. And now it's just so easy to build these things. And the other one is that people have tried to use these like online all in one builders, right? Like Bolt is a common one that people mention or lovable as well. And it eventually runs into errors that it has problems debugging.

[29:41] you often have to like bring it locally and start working on an incursor to get through them. [29:45] And that can be a sticking point for people, but... [29:48] Those two barriers are... [29:51] so much lower now. [29:52] Like if you if you learn how to I mean, really, what you have to learn is troubleshooting. You don't have to learn syntax anymore. You know, once you get to a point where it really starts struggling, then you have to start thinking about code organization and, you know, being dry and all those things. But it takes a while to get to that point. And by the time you get there, you already have a decently functioning app. So you're a lot more motivated to figure out how to push through. [30:18] those challenging issues. Yeah. What I, what I think I really want to talk to you about is, um, [30:25] How this changes how you think about your career and what you want to do with your life and how you want to spend your time. Because I think the thing that... [30:33] one of the reasons why we like each other is we're both like generalists that just love like new things and like, and, and have all these different skills that we love putting together to like make a product or a company or a book or like whatever. And that's the thing that's drawn me a lot to AI is like, I now have all these powers and all these domains that like, I maybe know a little bit, but now I can do a lot more. You're doing this course, now you're building little apps, but you're also like, have made this like very big decision to like be a writer and [31:03] I just want to know how all of these things are like currently bubbling together in your brain and your sort of like plan for what's next. [31:10] Yeah, I mean, the thing that has me really excited about...

[31:15] being able to build these tools with AI is that I love the idea of the, [31:22] kind of like hyper prolific solo creator business, because I've done building a business, I've done hiring employees. It's not something that I'm really aspiring to get back into. What I really want to be able to do is to predominantly write and do and talk about things that I'm interested in, but have a pretty robust perspective. [31:42] business around that with as few people to manage as possible. And the ability to do that has just increased dramatically now, right? Like, [31:53] having this podcast tool for me and Nathan's podcasts, like I don't need to hire someone to do [31:59] a good chunk of this like editing and management anymore because it's so fast for me to just use my tool to do it. And I think I'm going to be able to use it for creating shorts and things like that in a relatively near future as well. And so that. [32:13] that whole level of additional management that I need is just kind of like gone while still being able to tap into these, [32:19] marketing channels and on the writing side too, you know, so much of writing is in the editing. [32:27] And having the patience to... [32:32] fully edit your work, being able to get good feedback on your work, being able to parse that feedback. And so a lot of the writing tools that I've been working on have been around editing more than writing because the... [32:44] The writing that it generates is getting good. It's getting better.

[32:48] but it's still like not really your writing. But the feedback it can give you as an editor is getting excellent. And especially in the... [33:10] It's three to four weeks minimum before you get it back. I didn't even think about that, but that makes so much sense. Yeah, totally. Yeah, yeah. Three or four weeks minimum before you get it back. Or if you need to wait in somebody's queue, right? So Nathan hired an editor to review his draft because he's on query and trying to find an agent. And getting somebody to professionally review will be really helpful. And he found some great people. [33:33] But the soonest they can look at it is in three or four months. [33:37] And then it's going to take them a month to read it and get it back to him. So that adds like a four or five month delay. That, that kind of sucks. Right. It's a lot. Yeah. Yeah. [33:44] But if you can... [33:47] build a really excellent editing tool that's [33:51] even 80% as good as these professional editors that can give you that feedback instantly, [33:56] That's incredibly powerful. [33:58] And that lets you move through so much faster. And it lets you do things that you couldn't do before. So one of the features I built into my editing tool is it has a task manager. [34:09] So it has everything that I know needs to be fixed about the book. And every time I do an editing prompt, it also sends in the tasks that I already know about so that the editor only points out things that I'm not already planning on changing. That's interesting. I definitely want to see this. You said so many things I want to talk about. So like so one, just to respond to your like.

[34:30] Basically, you want to live a sort of solo creator life, but like have a business. Yeah. And, and that is like, I wrote this article like two years ago called, um, AI in the age of the individual. Um, and, and that's like, that was the promise that was like originally like so excited to me is at every, for example, like. [34:49] Thank you. [34:49] We've got 10 people now, 10 full-time people and a bunch of contractors, right? But I have to pay a lot of people to do that. And so I have to be at a certain level of income and success and money raised or whatever in order to do that. And you see that with a lot of writers who are way, way, way more successful than me. Like Ryan Holiday, he has a whole team and that's how he does all the stuff that he does, right? Right. [35:13] And to some degree, any solo writer can get the leverage of having a big team with this stuff. And I think that that is so... [35:23] amazing. It's so valuable. [35:25] Um, and, and the editing thing is like, I feel that pain so much right now because, um, it's a bottleneck for us, right? Like we have so many different surfaces we've got, we publish an essay every single day. Then we have like three different products that we run all internally that send emails and like have product copy and whatever. We want everything to have this sort of like same every feel to it. And, um, and then we've got new writers and like, and, and so I'm, I feel like I'm repeating myself all the time. [35:55] And I'm not even the main editor. And so I just want a tool to make this better. So I'm curious to see the tool you've made. Yeah, yeah. Well, here, I'll show you. So, I mean, like I said, it, one second, let me bring it up here.

[36:10] It's unfortunately not where I hoped it would be by this point, since I got sidetracked by doing the course and everything, but it is still exceptionally useful. So let me share my screen. Are you using, and by the way, before you dive into it, are you using 01 for this? Because I found that 01 is the best at giving editing feedback. And the reason is because... [36:32] Um, it's good at finding all instances of something in a, um, in a, uh, in a piece of text, whereas like Claude will only like find two. Um, I'm curious if that's what, what you did. The, the getting a one properly integrated is like the next step that I have on the to do's it's using Sonnet right now. Uh, and the only reason that it's not integrated yet is because my API isn't at the level where I can access the full one. [37:02] if you want. Honestly, all I have to do is pre-fund it with $1,000 and then I'll have access. So it's, it's literally just like, I need to do that. Um, you just need to pipe your course sales right into your, uh, into your opening high account. Yeah. My, my, my guilty admission is that I like haven't done any book work in the last month because I've been so focused on the course. Bad, bad, bad, bad. I know. I know. Um, okay. So, so you're, you're bringing up this tool. [37:32] which I guess is for L. Ron Hubbard. And it has basically like the screen you're on, it looks like a dashboard where you can have like tasks, characters, locations, and technologies. And you've selected characters, the character view, where you have like a list of all your characters. So it kind of looks a little bit like Scrivener, but like maybe an AI native Scrivener.

[37:52] Yeah, yeah. Or there's another tool that I like called Novel Crafter. Yeah, I think you turned me on to that at some point. [37:59] Yeah, yeah. But this kind of came from some frustrations with Novel Crafter for some of its, it didn't have some of the world building things that I wanted, and it didn't have the editing aspects that I wanted. So the... [38:12] The editing aspects of this are broken right now, so I gotta fix those after. But basically the way [38:20] that part of it worked is you could paste in your entire manuscript and then you could pick reader personas like [38:27] master editor, casual reader, um... [38:32] angry, [38:34] adversary, [38:37] romanticity reader, you know, things like that. And it would read your draft and then give you very detailed feedback based on those personas. That's really cool. We have something like that internally here where it's called Rally. It's built by one of our writers, Michael Taylor, and it does that. But it's like you can spin up an audience of like a thousand people that are like hacker news commenters or like every readers or whatever. And then you can ask it a question, [39:07] the crowd thinks. It's really cool. Yeah. Yeah. That's, that's kind of the next level that I want to build in is basically have each of those personas do three or five passes and then have a like master editor, probably using a one pro aggregating the feedback from all of those people into like one kind of like master guide. That's very cool. And then the way I had it set up was

[39:37] that you wanted to create as tasks for your next edit for the book. [39:41] And then those all pop up here. Right. So when you're going to work on the book, you can. And you're looking at basically a task manager that looks sort of like Trello where it has sort of like Trello. Different tasks organized by like description, relationships, world, plot, all that kind of stuff. [39:58] Exactly. And these get passed into the editing prompt too. So when you're trying to get feedback on your draft, it already knows all the things that you're aware of and doesn't mention those. So you can run it a few times to make sure this is good to go before you get to work. But the other thing that I really wanted was I have a, I'm decently able to come up with like plot type stuff, but I have a hard time flushing out characters. So I built this whole character editor. [40:28] where you could take a character in the book and you could start filling things out for them. So their age, a celebrity lookalike, a character inspiration... [40:39] Physical characteristics, um, you know, their, their background, things about their personality, aspects of their health and relationships, um, [40:50] and then built in chat with it. So the chat can work in two ways. One, it can role play, right? Or you can say, if Isaac came back to camp with a broken leg, [41:04] How would... [41:06] Grant React, right? And it'll use these descriptions of him to reply as that character in the book.

[41:14] And [41:16] This can actually be really helpful because sometimes it's hard to get out of your head and write in the way your characters speak. And you might not want to like, you know, you probably don't want to use this verbatim, but it starts giving you some good ideas so that your dialogue is being more varied. That's really cool. You know what I kind of want? And it seems like you're on this track. And so if you decide to do it, I wish you do it so I can just use it. Is like I have a couple of writers who I just think are fantastic at things like this. [41:46] Tolstoy. He's incredible at like using characters behavior and some, some of their inner monologue to tell you about like who they are and to kind of like paint this like very vivid picture. And I just want some agent to like take apart Tolstoy and like, [42:04] turn it into like a vector database that like when I want to describe a particular character, it like selects a few sections of Tolstoy that are relevant and then like recombines them into something interesting to kind of like push my brain into that territory. I really want that. [42:18] Yeah, or even if there's a way to extract a methodology, right? Yeah, like how would Tolstoy think about writing a character? Yeah. [42:27] Yeah, yeah, it's a good idea. [42:30] So it's got this roleplay, and then it also has this assistant for talking about the character. So we can look and we can say... [42:39] you know, what might, what could be important to fill out here, right? Or we could even just ask that, you know, based on what you know about grant, right?

[42:50] how might you flush out these things? [42:54] other details and this can give us some ideas especially for like secondary or minor characters where you want a couple of uh distinct things like this will start to give you some ideas right and it takes this back pretty quickly i'm just using haiku for it so you can do this all day and it's not really going to cost anything uh and then you can start filling out more character details from this that's really cool the the thing that's on my mind is like [43:22] as both of us are sort of like, [43:25] um recovering or like you know maybe not even recovering just like still are like productivity note-taking bros and there's always a thing in like in the note-taking world which is like [43:38] how much time do you spend on your system? And how much time do you spend actually doing the work that you are building the system in order to do? And I think in the previous era of the Rome research or the notions or whatever, people would create these elaborate database structures and tagging systems and blah, blah, blah, blah. And you always look at that and you're like, okay, cool, but... [43:59] what did you actually make? And a lot of times, the note-taking system is the coolest part of what they made. [44:07] And something occurs to me, which is like a trap here, is this could be, or things like this, I'm not saying this specific thing, it could be that. [44:18] on steroids, it's like, yeah, I can actually make an entire Scrivener or novel crafter or whatever. And I'm curious how you're navigating that for yourself, the trade-off between, okay, making something really custom for myself that really fits what I want versus like, okay, maybe there's an off-the-shelf tool that has some of this stuff and I can use that and just make more progress in my novel. Yeah.

[44:43] Yeah, the way I think about it is it's probably worth building a [44:49] Assuming you're competent enough to build it, it's worth building a personalized tool for the thing that's most important for you. So for me, it's like, OK, I'm very focused on the husk and the subsequent books. And the better this tool gets, the better, like all of those books are going to be potentially, you know, definitely three, maybe six or more books. Right. It's just like it it's going to be useful for years and years, the better it gets. And I do think that. [45:17] you're just not going to be able to compete [45:19] nearly as well as a novelist in the next few years. If you aren't learning how to use these tools to either make your work better, produce your work faster, extend your work into other mediums, it's going to be a lot of like, [45:31] ways it could be useful, but it's worth investing and figuring it out now so that you aren't playing catch up in a year or two, but it wouldn't be worth me making like, you know, [45:43] a super robust tool for, you know, [45:47] YouTube thumbnails or something. Right. Because like the stuff I can make on Canva is good enough. I'm not like a full time YouTuber. I make YouTube videos, but it's not my core thing. And so there it doesn't make as much sense. And so the other end of it is where can you make a tool really quickly? [46:06] that maybe saves you some time and money that [46:09] you know, is also worth it. Like I earlier today, I wrote a, or I had cursor write a script for compressing videos and audio files, because sometimes I get like a huge WAV file back from my editor. And I just want like a more compressed MP3. And I could pay for a tool for that. But it took three minutes for cursor to make one for me. And now I can just do it on the command line. So that's kind of worthwhile as well. I think that makes sense. I think that's a good line. Um,

[46:38] I want to talk to you, though, about the future of writing, because I've been kind of thinking about this, too, because, you know, I want to do a lot of writing like the best. You named your app prolific, right? Like the best way to be a great writer is to be prolific. And there's no tool that has been better for making writers prolific than AI ever, in my view. [46:56] I think an interesting difference, though, between the cursor thing, you already sort of mentioned, but between cursor where you can just press accept all and writing is when you're writing and you're writing under your name, the point is to stand behind everything that gets written. And code is different. Code is a little bit more outcome oriented, where it's like you want to stand behind whether it does the job, but the way it does the job is less important. [47:26] And so, [47:28] Having something that like generates an entire novel and a prompt is like, is not useful for writer. Cause you want it to be your novel, not a novel. And, and so I'm curious about like, [47:41] This question is not like, oh, how do we avoid AI slop? Or how do we... It's more like... [47:48] What do you think the at the limit, like in a couple of years when a super dialed in writer is writing with AI, like what is being done for you and how is it assisting you in getting all that stuff out as quickly as possible and still having it be yours? I think I mean, one of the things that I am probably going to try to hack on next is something a little closer to cursor for writing. I love that. It's so necessary.

[48:13] Yeah, yeah, where you've got, like, the main doc in the center, and then you've got, like, a chat and composer next to it. Because, and... [48:23] Figuring out how you really train it on your style. So it's not putting in generic stuff. It's going, you know, it's writing like you write and proposing things. [48:37] that you can accept and reject that are again in your style. Because, you know, when I think about planning a novel, it's like, I've got an idea for the, the, the high level arc. And then I might break that down into like a seven point story structure, you know, hero's journey, one of those. And then from that, I can probably figure out, okay, these are the core 50 to 80 scenes. And then within those scenes, these are going to be the main beats. And then within those beats, [49:07] see how a really good assistant can help you each step of the way where it becomes very collaborative. And it's very similar to how some of these prolific authors write their books. You know, like James Patterson doesn't really write most of his books. He has assistants and he has ghost writers who are trained on his style, who know how to write like him. And he's, as I understand it, doing as much approving of things as he is putting actual pen on paper. I think it's sort of how we're [49:37] going to be doing it. And you'll totally be able to just raw dog it if you want to, the way you can go like shoot film photography. Right. But for most people, you're going to be using an assistant kind of like this.

[49:51] And to some degree, your competitive advantage will be [49:56] will still be the strength of your voice and your ideas and your creativity, but you'll have an assistant helping you get them onto the paper much faster and probably closer to like the best of your ability. Because every writer has had this experience when you're in the flow, [50:11] And what you're making is just like awesome. And it's top 1% of what you're able to do. You're going to be able to do that top 1% of you all the time. And I think that's what the assistants are really going to help bring out. I like that. I also think like. [50:25] Part of being a writer... [50:27] is like the way that your brain works is it's this network of people, [50:33] things that are totally unformed, like ideas and quotes. And there's a whole network going on in your brain of things that are interesting to you. And an essay starts out as a network. [50:45] it's this interconnected set of things. And then writing is making that linear, is translating the network into a linear structure. And obviously, the process of transforming a network into a step-by-step linear thing, it changes what the network is, and it changes the linear thing, and it's this feedback process. But there's a lot of that translation work that's really hard to do. [51:09] to do that I think AI makes much faster and much easier. [51:14] I think for me, for example, I've been writing this long-form essay for six months, basically. It's called Seeing Like a Language Model, which I think I've sent you some stuff. Yeah, yeah. And I'm probably 10,000 words in, and I didn't publish this month on every, except for actually today, but on every I haven't published it in a month because I'm trying to just focus on this long-form thing. And I have this notes file that is like, I've been keeping it for six months or nine months or something like that, and it's like,

[51:44] It's just a notes app note and it's, I don't know, 20 or 30,000 words or something like that. And I know that the section of the thing that I'm in right now, there's a bunch of stuff that would be super useful in that file. But it's too hard to get stuff out of it, even if I throw it into Claude. Because Claude is going to go through... The attention mechanism is not good enough to really understand where I am in my piece, what would be useful. [52:14] individual and be like, is this useful and why? Claude will kind of give me like, oh yeah, just generally like, okay, yeah, this thing could be kind of cool or whatever. And it's just never good. But I think like a cursor composer type thing, but for writing would totally, totally do that well. And I just want someone to build it because it would accelerate my process in like an incredible amount. Yeah. And to the point of it having a hard time with like... [52:41] finding important small details in a large context. You know, you can kind of hack together an agent system where it's looking at each chapter individually, [52:53] And, you know, scoring certain aspects of it, but then also tracking like individual threads across all the chapters and like each of these kind of running as their own little process so that you're not overwhelming it with too many things at once. And I think we can kind of build that now. It would take a decent amount of work, but it would be worth it. It would be totally worth it. Yeah, especially with novels. Like, it's just so easy to miss stuff in editing, in self-reading.

[53:23] Yeah. [53:35] I think that I'm always torn between for some of this stuff. I mean, obviously, like we incubate stuff. So like we built a lot of stuff and whatever. But I'm always also torn between like, okay, do I want to spend time doing this now? Or do I want to just wait six months and it'll be like so much easier or someone else will do it? Yeah, that part's really true. It's sort of like it's deflation. It's like the deflation phenomenon. You know, it's like you don't want to spend the money because it'd be more valuable in a year. Yeah, yeah. Yeah. It's like we're rapidly approaching intelligence that's too cheap to meter. [54:05] It's time deflation. Your time is going to be more valuable the longer you wait. So you might as well. It's useless for us to be podcasting right now. We should all just be off on a beach waiting because podcasts would be way more valuable in a year or whatever. I know. And that is a tough thing. And I'm sure it's going to be a problem with the course too, because in three to six months, all the videos are going to be outdated because the tools are going to be so much better. I mean, that's the thing about courses is we've done courses. We [54:35] are, I think, incredible businesses, but they degrade so quickly. And that's why it's so hard to actually build a long-term sustainable business. I think what you do is the opportunistic... I have something that I can teach that people want, and I'm going to do a course. And then in three months, I won't be around anymore. But I haven't hired a whole team. It's like,

[54:57] I think the way to do courses. I think so. For us, like, that's also sort of how we do it, except... [55:03] It's just like the base of the business is subscriptions. And then when a writer at every me or Evan or anybody else is like, I have something to teach, then we do a course like we have this how to write with AI course that's that's launching again. And we're doing a second cohort in February. And it's great. Like people love it. You can make really successful products like like it's a really successful cash flow thing. But it's just hard to make it sustainable unless you're like Harvard or something like that. And no one has succeeded in doing the Harvard thing because it just takes so long. [55:33] masterclass and the courses like... [55:37] don't actually teach that much? Teach you, yeah. It's just infotainment. Yeah. It's entertainment. Yeah, yeah. [55:45] It's really interesting. There's so many little things about being a long-term creator on the internet that like this course thing that you just... [55:54] because I think there's so much stuff about being a startup founder and the lessons don't really translate in the same way. Um, and, uh, but, but I think the, uh, [56:06] the game has changed now that like all internet creators can like make software now like it's just just a whole different it's a whole different layer of the business now that that wasn't available before yeah and potentially be able to extend yourself in beneficial directions even if [56:21] those directions aren't going to be as long-term sustainable as the, [56:25] a startup might be, right? It's like, yeah, you can

[56:29] you know, I can probably do this course while it's relevant. I think I've got a good year or two of this topic before the tools are so good that you don't need somebody to show you how to use them anymore. And so it's like, yeah, I'm going to teach this while it's relevant. And then when it's not relevant, I'll be able to stop. And it'll be easy to stop because I won't have to like, [56:48] fire 10 people. Yeah. Yeah. The thing that I somewhat disagree with you on is like, I still think even the models are even better. [56:59] it will still people will still need courses just like the place where you need to teach is going to be different. It's not going to be at this particular level. There's endless amounts of meta levels like as execution gets cheaper, like you can just move up the layer of abstraction. And I think there's tons of opportunities even in years from now. Yeah, because really what I'm what this really is, is a programming course. Yeah. [57:21] And, you know, it's just it's a whole new way of teaching programming that's prompt first instead of, you know, hello world first. [57:29] Or, you know, back in the day, yeah, it's like, hello world. It's like, we went from assembly to like C, to scripting languages to English. [57:39] Yeah, yeah. Well, and even now too, you can just use one of the good audio to text models and you can just talk to Cursor. You don't even have to type anything. Honestly, that's how, so Kieran, who runs Quora, our email app, that's how he codes. He just talks to it.

[57:59] Speech to text is like a really important input that I think a lot of kids use, but adults don't really use right now. But I think it'll be way more important in like five years. [58:10] Yeah, yeah. I got to use it more because I'm still old school using my fingers. Yeah, just typing away like an old man. [58:20] Nat, this is awesome. I always love talking to you. Thanks for coming on. Yeah, thanks for having me on, man. And best of luck with the course. I can't wait to see where it goes from here. Thanks, dude. We'll talk soon. [58:40] 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. [59:03] 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. [59:16] And now, without any further ado, let me just say, Dan, I'm absolutely hopelessly in love with you.