How a Writer Uses AI Without Losing His Voice

I wake up and I don't touch the internet. I won't look at my phone. I won't go online until long after lunch. As soon as I touch my phone, I feel the chemicals shift and I can't go into any kind of deep thinking place or deep attention place or deep focus place. Because there's something about working with AI that feels very dopamine driven. And I believe strongly you can use it to do incredible work and also it's sort of a slot machine. And now I have a laptop just for writing that blocks everything. I can't do anything interesting on it. If I don't create these barriers, I will lose connection with this other part of me that I think is the most valuable part of me. There aren't that many people who are going to think about or write the weird books that I feel like I'm drawn to write. And as a human, that feels like the valuable thing for me to put my effort in. Every is the only subscription you need to stay at the edge of AI. If you care about being on top of the latest models and using the latest tools, you have to subscribe to Every to separate out the signal from the noise. Go to every.to slash subscribe today. Craig, welcome to the show. Hey, thanks for having me. So you are a writer, a walker, a player with technology, a photographer. Sure. And I think you have a life and career that I have looked up to for a long time. So it's really fun to have you here. And I think one of the things that we were just talking about is the thoughtfulness and the spirit with which you do your work. And I admire that spirit. I try to bring it into the stuff that we do here. And also, I've been trying to think about how does AI fit in with it? Because there's something about working with AI that feels very dopamine driven. And I believe strongly you can use it to do incredible work and also like it's sort of a slot machine. So I know that you're like deep into the vibe coding right now. So tell us, tell us what you're doing with it. And then let's talk about how it fits into your work. Yeah, I mean, look, I just think if you're not touching it, if you're not using it, if you're not building with it, you can't really comment on it, you know? And I think part of what when people go, it doesn't really work, it's so unpredictable. It's like, okay, just try, just use it. It's like, if you're using it, you go, okay, this is ridiculous. And why is this technology public slash like shouldn't this, I mean, I kind of agree with a lot of what Dario says. Like, there should probably be more regulation around this. Like, I don't know if everyone in the world should just have this immediately. Certainly, you know, as we're working out the kinks of what this is in public. I mean, it just feels strange. It feels like we are in this aberrational moment where technology like this normally isn't just given to everybody, you know, for free, essentially. So, look, I think you really have to be engaging with it, especially if you can. You know, it's like Fable came out. I played with it for four days. I had it like refactor code bases. I had to do, you know, these other little projects. I was like, great, this is cool. And then it went away and I was like, wow. Yeah, that kind of makes sense that this would go away. But also Opus 4.8 is sort of like good enough to do anything. Like if you told me you only have Opus 4.8 for the rest of your life, I'd be like, great. I could build anything with this. There's a lot I can do. Yeah. So it is this weird moment. Okay. So you're actually, you're actually saying, I'm, I'm, it makes sense to me that Fable is not here anymore. Do you, I like, I miss her. Like, do you, do you miss her or? I don't know. Like I, I honestly don't really feel qualitatively that maybe I'm not using it enough, but like the differences between these models like that explicitly. I just know that, oh, it feels a little more rigorous and it eats my tokens like crazy. So it must be better, right? So I just hacked into the, into Fort Knox and like stole all the gold. Yeah, I know. It must be better. Yeah. Yeah. I've got all the Bitcoin now. It's all me. I've become Satoshi. But the, the, look, I think you have to be using it. So that's one of the main reasons I have been using it. And also I just, I've always loved technology. I mean, it's been a big part of my life since I was, I have memory, you know, always curious about, let me take this thing apart or build this, or use this piece of software or whatever. Like I, it's always been just part of who I am. It turns out that's also part of who my birth mother is. She's a computer scientist. This one was out programmer, weirdly. She never went to college, but she's a, yeah, I met my birth mom. I was like, what do you do? She's like, Oh, I'm a programmer. I was like, Oh my God. Okay. Yeah. Nature. There is no, there is no nurture. It's all, it's all nature. It turns out nurture is just your pathologies. Like all, like all the things that you hate about yourself is probably like nature or about nurture. And then all the stuff that you're like intuitively is confusing to you is, is just nature. Holy shit. That is fascinating. When did you find that out? Just like a little under two years ago. Wow. Yeah. So it's been interesting. So anyway, technology is important to me because I'm just curious in that way. And I think it's the most interesting thing in the universe right now. Genetically predisposed. A little bit genetically predisposed. So I've been building stuff around my membership program. Um, well, I rebuilt Quicken, um, which I'm the tax software. Yeah. Tax software. Cause I needed, you can watch my interview with Paul Ford and, and Rich over on a board about that. So I re I rebuilt Quicken. Um, and then I rebuilt campaign monitor, which is a newsletter software, um, because SaaS CEOs are losing in this interview. I know. Well, well, well, okay. And why are they losing? They're losing because, uh, well, first of all, campaign monitor has not done anything in a decade. That's just been sitting there taking people's money for a decade plus with no innovation whatsoever. Zero. Nothing with like a really abusive, uh, pricing policy. How much were they charging you? So I was spending like, what was it? Like six, $7,000 a year. I mean, it was like one of the most expensive things I, I paid for. Um, but the real annoying thing was that they didn't count unique email addresses. They counted total, even if you had overlap between lists. So it was, it's just, it's like things like that where it's like, you don't just, I'm, I'm going away. Squeezing like a, like you're squeezing too much out of it. Yeah. And my bill now with like SES, Amazon SES, I set up all the DKIM and SPF and all that, all that email crap. Uh, so I think I'm getting pretty good deliverability, like on par with what campaign monitor gave me. But now my like yearly bill is probably going to be like, I don't know, like $150 or something. Like it's just a ridiculous difference. And how much in Fable tokens? Well, thankfully, yeah, this is all Opus. So, um, but that's the other weird thing is like, I, well, I was on the $200 a month plan and then I realized I wasn't hitting my limits. So I dropped to 100 and like for $1,000 a year, $1,200 a year. Like that is the easiest trade. Like that's the best, that's the deal of the century, um, in terms of what you can build. So I built newsletter software and then I've been, I've been adding to my membership program software. So actually one of the things I had Fable do was do a, like a full, uh, just security check on my membership, um, uh, Flask Python app, which I built by myself before any of this existed. And, uh, so it went through, I was like, Oh, you have a trillion security holes. Shall I fix them? And I was like, yes, please. So I think it's a little safer. I mean, the stakes are very low for my membership software, but. Then the FBI knocked at your door. Yeah. You got to stop using this. So, you know, I've been doing that and then I rebuilt, uh, Twitter, um, for my members. Uh, we call it the good place. Oh yeah. You were showing me that. Tell, tell me about that. Yeah. I mean, look, like social media sucks. It just, it's terrible now. There was this moment, 2010 to 20, like 14, where um, it wasn't algorithmic. Stuff just appeared. Links were favored. I mean, there were just normal, they didn't, they weren't a hit against you if you posted a link. Um, and everyone was on Twitter. It was like the, the great media watering hole. And like if you were active then and slightly interesting, you could like, you know, a hundred X your network just by being an What is your experience now day-to-day in your work life? Are you like, oh shit, now I'm a sysadmin for like four different pieces of software that I have to like send agents to go fix? Or is your work life still fairly similar to what it used to be? No, I mean, my membership software just works. You know, it's so simple, like when you break it down. I mean, this is why I'm using Python. I'm not using, there's no, like, what's it called? There's no react, there's no next, there's no none of that stuff. It's just, it's very simple. And the point is, is because I don't want to be systemming anything. And even with the newsletter software, that piece is only touched when I send newsletters. You know what I mean? So the sign-ups are happening and that has to be working and it seems to be working. I can check every couple of days. But the only critical thing is like when I hit send, make sure that goes out. And that only happens once a week or twice a week or something like that. So I don't feel like I'm maintaining anything. And actually, I get a high off of building things that allow me to write. Like, so software that helps me write or that helps me publish in a new way inspires me to do more writing. So it feeds back into it in a positive way. How is that? Do you have a specific example or not? Well, like Josh Miller and I kind of put together this weird SMS publishing tool. Like Browser Company, Josh Miller? Yeah, yeah, yeah. So before he did all that, um, we did this like little experiment where he built his like, he had like a little team experimenting with publishing stuff and we built this like SMS tool so I could do a newsletter over SMS, which just felt like, oh, what is it like to have a message appear, you know, like end to, you know, many, like one to, one to end sort of publishing. Um, and uh, that was kind of fun, you know, and it inspired me to like during this walk to think about what I wanted to be blasting out to everybody and you know, you had to, you had to keep it concise so it fit into, you know, one message. It wasn't broken across different messages. Um, so, you know, that's, that's like an extreme example of it. But just in general, like building my, building out the campaign monitor, um, clone, you know, which also, by the way, does a bunch of stuff. So like I have members only or I have pop-up newsletters that are like only for a week or for a month and I have those archived on my member's website. And I was able to um use Claude to, to build this newsletter software. So when I publish to the pop-up, it does the whole archiving process in Git, commits, pushes to the server. So it's archived perfectly for me, whereas I had to do that all manually before. Um, so that, like, that's a good example of like, wow, okay, now I want to make more pop-up newsletters because the archiving process is set up or I built a tool. I do board meetings with, for my members. I built a tool to build transcripts from them all. Like board meetings of your own, like life life. Yeah. Yeah, yeah. So we do every six, every six months, we do a board meeting where I just talk about what I did for the last six months and what I'm going to do for the next six months. And then I have a Q&A and the Q&As are actually always really good. And I wanted, I've done, how many have I done? Like 15 of them or something? I've done quite a few. So we have like, you know, almost like 20 hours cause I'll do two, two each. So actually maybe even like 20 or 30 of them. Anyway, we've got dozens of hours of Q&A and they're often great. And so I built uh this archive of the Q&As where you can, it's archived by like, you can, you can search by uh keywords or you can like view by keywords and then you can search for anything and it'll pull up all the videos where I say that word or talk about that topic and you can click the link and it opens the video to that point. So it's like building things like that makes me want to do more board meetings. I'm like, great, this is amazing. Like I want to do, how can I do more of this? So I, for me, that building software has to feed back into the greater purpose, which is to make, not to just like spin my wheels and build things for the sake of building things. Did you see Tim Ferriss recently posted on X, like the sales of the four-hour workweek are down like 80% or something like that because he thinks because of AI and there's this larger conversation happening about the value of nonfiction that's specifically like advice-based nonfiction. Yeah. What do you think of that? Well, it's funny. We had lunch like three days before he posted that and he was, he was telling me about that. He was telling me about it. I was like, really? Wow, that seems like, that seems excessive. I mean, look, there's still a lot of books, like self-help books, nonfiction books selling insane copies. I mean, Tim hasn't put out a book in a long time. I think that's part of it. I think maybe the long tail is getting shorter. Well, also, it's like there's a big difference between what you would say pre-AI and post-AI. So if you think about the four-hour work week, which came out when I was in middle school or something like that. It's like 20 years old now. Yeah, at least. Or 18 years old, something like that. I think it was like end of 2000s that it came out. Yeah, I mean, you would, um, also it's just, yeah, it's a different era of writing. Um, you know, I'd be really curious to see what Tim puts out next. If he did the four-hour workweek agent edition, I think it would sell like gangbusters. For sure. Yeah, yeah. I'll update it. You can actually do that now. Well, I mean, this is, well, what's crazy is now, it's so easy to do the four-hour work week, uh, style building, which probably makes it impossible to, to achieve now. I mean, part of it was the friction of like, it was a little hard to do, so not everyone could do it. So like if you put in that little bit of effort, you know, and now it's sort of like, well, everyone, I had a friend who built 10 companies in a year, or like 12. He did like uh a company a month. And this was like maybe 10 years ago. You know, and you, you know, he, he knew he had his frameworks and you could, you know, he had his like tool, he's building, you know, designing it and creating the mascots and all this stuff. And uh, he had a couple that did well, like decently well, you know, he's got his recurring revenue, but I feel like doing that today would just be, no one would care. It's, it's just fascinating to think about how that's changed so quickly. I think you can, you can one shot a company or an app, but the, I think the, the metric of quality or substantiality has gone from, can you build it at all to, are you maintaining it? Yeah. And it, like, have you maintained it over time for a longer period of time? Yeah. And that's a really, that's interesting. And I think that's harder actually to. Yeah. It's still, that's still hard. Yeah. Well, he was one-shotting them in a month, you know, like basically, like he was self one-shotting. It was just, it's just like the, the, you know, I feel like, you know, LLMs, it's, they just exist on a different timescale than us, you know? And so it's like, he was sort of doing, but, but the, the thing that was interesting about him doing that was that you knew he was building these things himself, you know? Right. And so, I think that's fascinating now. You can, you can, in a weekend, you can essentially spin up a company and everyone can go, can kind of just shrug and go, okay, well, end, you know? I think that's great because it means like we have to bring value to the table in a way that, um, you kind of get over the, you know, Kevin Kelly does this thing where if he has a book he wants to write, he'll make the cover for it. And he says that often like removes the desire to make the book, to write the book. And uh, it's just like a good forcing function. It's like, is the thing, is the thing actually doing the thing or just having the veneer of having done the thing? And I think LLMs kind of speed that up. That is honestly true. Yeah. Yeah. I've definitely done that. It's like, it's also buying the domain or, you know. Yeah. Oh yeah. Oh God. Yeah. Yeah. I had to, I like, I had to like tie my hands behind my back about domains. I still pay like a couple hundred dollars a year for all this garbage that I'm like. We'll never use but. Yeah. And I don't even know why I don't give it up. I try to give it up. I like turn it off You know, for like six months. That's how potent it all feels right now, and if I don't create these barriers, um, I will lose connection with this other part of me that I think is the most, to me, most valuable part of me. Like, there's a bunch of people playing around with this crap, and they're gonna do what they're gonna do, but there aren't that many people who are gonna think about or write the weird books that I feel like I'm drawn to write. And as a human, that feels like the valuable thing for me to put my effort in. You know, it was like when I was in Silicon Valley, and I realized all anyone's doing is building ad software. Like that was like such a big part of like early 2010s Silicon Valley. You know, it was just everything was ad software. I was like, oh, okay, I don't need to be doing this. It was like very easy to step away. Like it's a little reductive, but also it isn't. Like that's sort of when you break everything down. I love that. Tell me about that word weird. You're also using the word dorky a lot. And it feels like an interesting aesthetic to be pushing on right now because language models let everyone's sort of, everyone and everything look and feel a little bit similar. Yeah. Yeah, well, what do you mean, like when am I using dorky? You've been using it in some of your recent newsletters. Okay. Yeah, dorkiness. Yeah. Yeah, I mean, because, well, this, LLMs are fundamentally, like, it's still super dorky. Like, okay, 99.99% of people using it are like, hey, do you wanna be my girlfriend? Like, will you have sex with me? Like, I'd really think if we saw the chats of most people, like, it'd be quite mortifying. Like it's just weird. It's like, okay, now I'm going down on you. Like, what are you doing? Like, I think people are just having sex with these things, like, for the most part. Like, look, like, this is what we do. We're just like sex machines. To be confirmed later. Yeah, we're fundamentally just like disgusting sex machines. Like, look at Anthony Weiner, that guy couldn't like just stop taking pictures of his dick. You know, it's like, the stakes were so high. He just couldn't stop doing dick pics. Anthony Weiner, the representative technology user. So look, I think like, look, if you look at, like, book sales, like, most books are softcore porn about like angels and fairies having sex that women buy. Like, this is like, this is the fundamental human condition. It's just like dirty, like secret sex stuff, right? So I think that is mostly what is happening with LLMs. And so like folks like us who are actually building software with these things, we are like so, so in the minority. And so that's why I'm like constantly hammering out how like dorky we are because we are just mega dorks. Like we're not having fairy sex with our LLMs. Speak for yourself. Yeah, I mean, I'm not, at least not, I didn't this morning. I don't, I don't do that before lunch. The fairy sex is only after 3 p.m. But no, I'm just like, like talk to any bookstore owner. They're like, yeah, we sell so much, like, like elf sex books. It's crazy. But, but the, this software building part of LLM use is mega dorky. And you have to be a dork to understand all this crap. Spin up a like Digital Ocean server or whatever, like use a Cloudflare worker, like all this. It's so hard to use because you have to, there's no, the thing is they're so opaque. You have to know what to ask it for it to do any of these things. It's not like, here's a, here's a smorgasbord. Like, here's a menu of all the things you can do with the LLM. Like, that's weird that that doesn't exist. These interfaces right now are so terrible. And so I think we are going to maybe see better interfaces. Maybe it'll just be in Figma or in Claude design or whatever the hell, you know, you build software with. Like talking or thinking about infrastructure is going to completely disappear. In the same way we don't think about like what registers we're writing to, you know, or like, like what, you know, think registers we're pushing and pulling. And like, how do you do an XOR on this bit or it's like, we're not thinking about that, you know, that's all abstracted. So I think it's going to continue to be more abstracted and it'll become slightly less dorky, but we are in the deep dork version of all of this right now. Deep dark dork version. Yeah. Well, it depends on what your fairies are doing. Um, okay. And I think the thing about being weird, let's, let's, let's move away, like from the specific, I'm, I'm a dork for building, building LLM software because to some extent it is dorky, but then you have to also look at it relative to where you are, right? Like one of the, a weird choice to make currently is if you're a somewhat techie type of person is to be like, I could be in a room with like 10 other people mainlining AI, but I choose not to. And that's like a kind of an uncomfortable choice. Tell me about, like, about that and how you make that choice and why. Yeah. I mean, I don't know. I struggle with this because I, I, I, I feel like I'm using it in a way that illuminates the power of it, but I also feel like there's so much more I could be doing. And it's not even about, there's no like financial element. It's like, oh, if I do this, then I can make, you know, X amount of money or whatever. It's like, that is absolutely not even on the radar. It's more, I want to know what the edges of this thing are. And I think that was the same feeling I had when I first discovered the web. I saw the web and it was just immediately, I need to be engaging with this. I want to build, I want to learn HTML. I want to, you know, like all the, oh, and CSS got released. Oh, cool. How do I use that? Because I want to know the edges of these pieces of software and these technologies. I feel, I feel like for LLMs, you know, the, the rabbit hole goes so deep that if you, that six months, 10 hours a day with like a group of like fellow mega dorks is actually what you need to do to feel the edges of it. And then if you do that, I think you would just come away with a profound understanding that few other people would have. And that to me is the interesting part. Just that understanding. I mean, that's sort of what I'm, I think our project here is a little bit like that. Sure, yeah, yeah, yeah. More than 10 mega dorks at this point. But yeah, no, that's good. I mean, I think, yeah, that's, that's one of the, the most exciting things as a writer being in this time is if you're just willing to experiment, you're so far ahead of, of everybody else. And you get to understand this like corner of the world that people desperately need to understand because it's very scary to, to most people. Yeah. And it's new. And for me, like new things are just the coolest, you know. Yeah, it's just fun. I mean, there is, there's, and well, and you realize we're in this, you know, not to get like all like fucking hyperbolic, but like, we are in this epochal moment. Like this is weirdly special. This is like, this is genuinely strange. Like a generational shift in how technology is used and built. I mean, we kind of see it manifesting in these ridiculous evaluations and all this stuff. Like, it's going to bring with it incredible, like income disparity and like the people who are using it or aren't using it or who have access to it and don't have access to it. The weird, the strange thing about it though is the open source models seem to be not that far behind. And so, like, if, again, if you took away everything today and we're like, oh, you only get whatever deep seek open source, blah, blah, blah. I'm not really paying attention to the open source ones, so I don't know how they're doing. I just kind of hear inklings of it. But it feels like you could almost take one of those and still be so far ahead of the game. Like you would never want to program again without having that. You know, that co-pilot with you. So that also feels interesting about this is that it's both seemingly creating these disparities, but also weirdly egalitarian because you'll be able to run it on like pretty much any machine you have. That's that's that's a strange, you know, dissonance. Also, this idea of like you download this thing that's like 50 gigs or whatever and you've essentially got a JPEG of all of human knowledge distilled. It's the best. It's so weird. This is truly one of the weirdest, like pieces of magic I think that humans have, you know, and whatever Dario talks about the atomic power and all this stuff. But like, I feel like there are many parallels to that. You one of the big, I think, philosophical divides right now You know, and I think when you feel that, as I think most adopted kids feel this in some way, and it creates a bunch of like, bad psychological pathologies and all this stuff. Like, when you feel like your existence was a mistake, it kind of feels like the whole thing is like a bonus game in a weird way. And so you're like, wow, like, I'm really not supposed to be here. I mean, the fact of the matter is that this is true for everybody. Like, like the odds, the chances of you being you is infinitesimally small. It's like, if, if your dad, like, you know, ate an extra taco on Tuesday, you're not gonna be alive now, right? It's like, it's gonna be a different version of whatever that you are. But when you're adopted, it's like kind of hammered into you that you weren't meant to be created, and you were given away, and like, you know, all this stuff. And so I think, maybe I feel like, I've come to grips with the fact that our existence is so tenuous and so arbitrary, because I feel like my existence is like that. And it's not, it doesn't fill me with this like, ennui of like, sadness or whatever. I'm like, this is really interesting. It's a miracle. It's a miracle. And I am happy, I'm happy to participate in this weird little bit of time I have that I wasn't supposed to be here, and I'm grateful for that. And I extrapolate that to all of humanity. Like, I think I can do that easily. And I'm not made sad by that. I'm like, wow, what a gift that we had, like, a 50,000-year run or whatever. You know, whatever it was. And really, like, a 200-year run. You know, Victorian, like, you know, innovation, you know, the Industrial Revolution. Like, we've really had this incredible run, asymptotic, like, mega run, right? Like, and we get to witness this. That's so cool. And maybe after this, we're done. That's okay. I, I love, I honestly, I love this. I think this is, this is an amazing perspective. I think, I think we can leave it there. Like, that's, that's the, that's the... How are we gonna top that part of the interview? Yeah, no, I mean, yeah. It's, it doesn't, it fills me with like a weird hope, actually, that we've, we've managed to get this far. Because we've dodged so many, I think, apocalyptic, sort of, disasters along the way. That's, that's what I think, too, is, is, there's this moment where you contact, I, I, the thing I say a lot is, like, never make any major life decisions within 30 days of meditation retreat, a psychedelic experience, or your first experience with a frontier AI model. Um, well, I, I sort of think that you, you contact them and you're like, holy shit, this is crazy, maybe it'll end the whole species. And there's this process of unfolding and getting to know it that it then, you, it integrates into your life in a way where you're like, we, we're gonna dodge, to me, I'm like, we're gonna dodge a bullet. Maybe we won't. Maybe we won't. That's so interesting. Yeah. Yeah, no, we're all dead as soon as they're conscious. Instantly. That's the title of the interview. Instantly. Hey, man, and like, and like, with that, whatever, when that thing comes at like the, the, like the, the ejection into the food chain where everyone's like, whatever, like, uh, you know, I'll be taking the last bite of a, of a vegan burrito and going, oh yeah, I feel you, man. I feel you guys. Yeah, you were right. Goodbye. Thank you. You know, just go to sleep. I think it'll be a, a very, a very, um, gentle death. Like, I don't think it'll be a, a violent death, but we'll just disappear. On that note, Craig, thank you for joining us. This is fantastic. Thanks for having me. Yeah.