How to Supercharge Your Writing With AI Tools - Ep. 33 with Evan Armstrong

[00:00] We've split up the segments or the things we're going to talk about into four sort of distinct areas. One is like taste. So like, how do you know what good is? Two is topic. Like, how do you pick what you're going to write about? Three is craft. So that's actually how do you do the writing? It's everything from outlining to writing to editing. And then four is audience. How do you reach people? So why don't we start with taste? My line about this is that taste is not whatever people in Brooklyn are doing. No, I think taste is the ability to articulate why something is good. [00:30] copied this into Claude. And I was like, hey, here are a list of writers I like. Can you tell me the vibes of these writers in detail? For me right now, because I've seen this before, it's not like a mind blow moment. But when I first did it, it was like looking in the mirror for the first time. And I was like, holy shit, this is what I look like. And I like it. [01:00] Thank you. [01:03] Evan, welcome to the show. Thanks for having me. Long time coming.

[01:33] I think you're just you have that sort of like rare combination of you're really smart. You know a ton about business. You're funny as hell. And you actually want to be a writer. [01:44] Um, and it's just been like such a pleasure to get to watch you go from being a, I guess, professional professional. [01:53] a marketer, SaaS, investor, you know, a bunch of different things that you were doing, and now being a pro writer. So welcome. Well, thank you. I'm really excited to do this mostly because I'm going to chop up what you just said and just like my performance review at the end of the year, just play you back to you. That was the only reason. This is just to make sure that I hit my bonus for the year. That's the only reason I'm here today. I'm costing myself money. Yeah, exactly. This is a very expensive podcast. [02:23] to do is like, uh, do a little bit of a non-traditional episode. That's a, that's a little bit less like me just interviewing you and more like us together talking about writing. Cause I, we're both huge writing nerds. We love to write. We're both professional writers. Um, and talking about running us, particularly in the context of AI, like how are we using in each part of the writing process? How are we each using it? Um, and to what effect, where is it good? Where is it not good? All that kind of stuff. Um, [02:50] And you're actually teaching a course on this called How to Write with AI. So it's a good time for us to kind of explore together. And my hope is we both just come out of this [03:00] I mean, nerding out about writing, which is like probably both of our favorite things to do, but also like learning stuff from each other that we can apply to our process.

[03:09] Yeah, I think when people picture every, I think they vision it more editorially cohesive than it is. Where like we're all, I would say it's more contentious than people would think. Like we're debating this stuff a lot. We're arguing over sentence structure. And I'm going to guess that today we're going to find out we use AI very, very differently in our writing process. Let's hope. I think that would make a more interesting episode. It would make it more interesting. I think we're going to find where you use it pretty differently. Okay, cool. [03:39] So we've split up the segments or the things we're going to talk about into four sort of distinct areas. One is taste. So how do you know what good is? Two is topic. How do you pick what you're going to write about? What do you write about? All that kind of stuff. Three is craft. So that's actually how do you do the writing? It's everything from outlining to writing to editing. And then four is audience. How do you reach people? And we did it that way because that's how your course is structured. [04:09] Um, [04:10] And that sort of allows us to get the whole breadth of all the things you might use AI for in writing as a creative intellectual pursuit. So why don't we start with taste? Can you like teed up? Like talk about why taste? Why is it important? And yeah, we'll start from there. [04:28] Yeah, I think taste is a buzzy word and it's also a word that means nothing and everything.

[04:40] about this is that taste is not whatever people in Brooklyn are doing. [04:44] I'm in Brooklyn. I don't mean that as an attack against Dan, but more against the Brooklyn industrial complex. [04:51] They made our coffee too expensive, and it's all their... Anyways, I think taste is the ability to articulate why something is good. Like, [05:01] You know, you may say that you loved Dune 2 or you loved, you know, whatever latest article either Dan or I wrote, but being able to accurately understand. [05:10] describe why you liked a thing besides awesome loved it you know like that's actually really hard it's a discernible skill and i couldn't really do it for myself until i started using ai more and so i think it's an exercise that everyone who wants to write something good has to be able to say what good is [05:29] And what does that mean to you? Like, what is good to you? How do you articulate it for yourself? [05:33] This is complicated. So I think when we're talking about taste, you have to be taste in what context? So like in the capitalist context of taste, you're like, is my taste overlining with the problems that my product is solving? [05:49] So Lenny, who is a friend of ours, he writes Lenny's newsletter, does a great job. He has like these four jobs to be done. And you got to help me here if I'm missing some of them. But it's like, you know, make me smarter, make me money, entertain me.

[06:03] be taste that goes next to those jobs. [06:07] I have found that I am very bad as a writer of like, I got to make a product. I'm just not good at it. I get bored. The writing is crappy. So instead what I have found that like what good taste is, is basically things that I enjoy. So I only write things that I would have a good time reading. And that usually ends up anytime I deviate from that, the product doesn't, you know, the audience doesn't like it. I don't like it. No one enjoys it. So good taste is things that I [06:37] The peak of writing is the more boring the topic and the more entertaining it is, the more skill that's presented. So you and I, Dan, we write about, on one level, very boring things. You mostly do tokens. I'm talking about the next token, right? And I spend a lot of time on accounting. Here's how finance works. No one cares. No one likes that. No one enjoys that. It's not fun at all. [06:59] But being able to crack jokes, to be able to make it accessible and have an energy to it, it's really hard. It's really, really hard to be accurate and enjoyable. And so for me, that's what I shoot for in my own taste. I'm like, is it something boring that I know I should know, but I don't and I have a good time while reading about it? Very hard bar, but that's what I typically go for. Entertaining reads about boring topics is how I think about it. I'm curious, Dan, for you. [07:29] Like, how do you articulate your taste? Where do you find your taste being fulfilled?

[07:34] That's a really good question. And I will say also for me, like this was one of my big unlock moments for AI is I wrote this piece called What I Do When I Can't Sleep, which is about using AI to discover my taste. And it sort of came at this particular time in Evry's history where we were kind of going through a little bit of like a identity crisis. [08:04] Like, who am I? And both Chachapiti and Claude were like incredibly good for identifying that. And I think the things that came out of it for me, you know, going through the exercises, using those things to think about who I am and what I like. [08:20] I really like writing that is like really like it's, [08:26] Intellectually stimulating. It's analytical. It's philosophical. But I really also like it when it's like emotionally resonant. It's like psychological or it pulls on your emotions in a certain way. I also like writing that's very... [08:44] very like poetic and lyrical. Um, so like an Annie Dillard type type person with the running joke at every, is that everything, I relate everything back to any, any Dillard. I'm laughing because like literally I think for most of your pieces, I have to edit, I have to like hold you back. Like you do not need to mention any, nothing to do with her. Like you need to cut the section. I'm a broken record on any Dillard, but, um, the, the Annie Dillard will continue until morale improves. Um, so I like that. I really like, um,

[09:12] writing that is like really accessible, even if it's dealing with a hard topic. So like Robert Sapolsky is like a really good example of someone who I think does that incredibly well. I also really, really love writing that is just like [09:25] practical. It's like, you can actually like apply this or like, you know how it relates to you. Um, even if it's like somewhat esoteric, um, [09:34] And I think generally the things that I'm drawn to are... [09:39] very kind of like interdisciplinary looks at the human experience, um, the relationship between humans and technology, um, the relationships between technology and creativity and psychology, like, um, and then sort of like philosophy, like all bundled into that. And like maybe, and then business all bundled into that are like the, the kinds of stuff that like really, really get me going. And it's kind of interesting cause it's, um, I, [10:04] It's one of those things that I... [10:07] If I look back on my life, I can totally see that as a pattern and stuff I've loved for a long time, but I was never able to say it until... [10:18] Claude and ChattyPT told me like, hey, this is what's going on for you. And like you said, like saying it, articulating it, it's so powerful because once it's articulated, it becomes something that you can aim at. You can aim yourself at. You can aim other people at. And you can start to refine how you write and what you're doing based on that. And I think that's like sort of just this key underlying component to getting better.

[10:47] I think it's interesting because for both of our answers there, like if I had the stopwatch, I bet we both went on for like two minutes of like, this is what I like. And it's kind of just an amorphous blob of things and emotions. And so when I think about like taste, particularly when I saw you, because I was thinking about when you wrote that piece, that was June 23rd of 2023. [11:13] Yeah. [11:13] After you wrote that, it wasn't that you could suddenly be like, I like Annie Dillard and like, because she's lyrical. And so my writing is going to be more lyrical. Like you were before that your writing was lyrical. It wasn't like there was some huge shift in your writing necessarily. It improved, of course. But the thing that I noticed is after you published that piece was like you hit like a new emotional plane where you were like, ah, like I am comfortable writing the way I want to write. [11:43] Peace. [11:44] I love that. I think that's so true. Um, yeah, I think part of it, it sort of relates to that piece I wrote, um, I don't know, maybe three or four months ago called admitting what is obvious, which is like admitting that I wanted to write as like a core thing. Um, and I think you're, I think you're totally right. Like, um, [11:59] articulating it gives you something to aim at and also, [12:04] allows you to incorporate it as part of your identity, which requires like [12:10] admitting who you are, which is like a, it's actually like very scary to do, um, because it feels like it's, um, cutting off different other avenues that you can take. You know, like I like things that are not any of the things I mentioned, you know, I, I've, I like,

[12:25] you know, dumb, funny movies or whatever, but that's not in my taste. Um, and so, um, [12:32] And that's scary to do. And it's also scary to feel like maybe you'll be ridiculed. People won't like you if you say that you like this thing that no one else really – I don't know anyone that likes Andy Dillard except for me. They're out there, but I don't associate with them. The Dillard heads unite. [13:02] then you're like much more comfortable just like owning it and being like, this is, this is what I want to do. And that I think you're totally right is like such an important part of doing any kind of good creative work. [13:12] Um, I'm curious, maybe we should talk about like what you actually did in the article. Um, for those who have it for the every heads, uh, beyond our, like our deep cut fans, like what was the AI exercise that you did to like develop your taste? I'm, I'm curious, like, can we do it live? This is the AI and I show. We'll do it live. So basically the way this worked and I did this like, [13:37] a long time ago. So we'll see how, we'll see how, how well it does. Um, yeah, [13:42] you know, today. I'm sure it'll be good, actually, but it'll be interesting to see how it updates. Basically, like, I just had this, like, note in my Notion doc. [13:51] Um, [13:53] And, um, I was just like thinking for a little while, like, who do I actually just like,

[14:00] as a writer. So I started adding names. And this was not just a one-time thing. It was a continual process because there's all these different contexts in which you're like, oh, I really like that person, even though you forgot. Yeah. [14:12] So for a while I was kind of doing just updating this and I have like Robert Sapolsky, Robert Persig. Sapolsky obviously does the like really accessible like deep science stuff. Persig is like really accessible philosophy blended with fiction. Ursula K. Le Guin is like really interesting, like psychological fiction. We've got Mary Oliver, like that, that resonant like prose. Bill Simmons, who's like a very bloggy, funny, like clear, simple kind of writer. [14:42] And I have words for these people that I can say all the words right now, but I could never say that before this exercise. So what I did was I just copied this into Claude and I was like, hey, here are a list of writers I like. Can you tell me the vibes of these writers in detail? And then I just pasted my list and I... [15:08] went for it. And I kind of like the, like asking for vibes from a language model, like language models tend to do well with vibes. And it sort of gives me this like really, really, [15:19] big list of things like Robert's Polsky, scientific, engaging, um, accessible. See, that's a word that I used. Um, [15:27] Thank you. [15:28] Persig philosophical introspective

[15:30] Le Guin, imaginative, thought-provoking, feminist. Mary Oliver, nature-focused, contemplative. William James, philosophical, psychological, pragmatic. And it sort of goes on. And one of the really interesting things here is you can even start to now pick out things that – [15:47] words that resonate with you. Like, I don't know if you, you see any words here that you're like, ah, like that is actually something I hope to be. [15:54] I mean, I have the highest of standards for myself. Like, I should be all of these all at once. I don't know if you ever get that, where I'm like, I should just be the best of every best writer and do it all in my 1,500-word blog post. [16:10] I... [16:10] kind of the most. I'm curious. One thing we should do is you actually did not do this in Claude last time. You did this in ChatGPT. I did it in both. Oh, you did in both? It was both Claude and ChatGPT. So listeners, you should know that Dan is a liar because in his post that I was reading this morning, he says ChatGPT. No, it says Claude and ChatGPT. You didn't read the post carefully. [16:40] okay, no, this is different. Don't come at me unless you've got receipts, man. No, no, no, no, no. Now you're changing the truth. You used Claude to do the notes part of the exercise. You didn't use Claude for the writer part of the exercise. Or maybe you did both and you just didn't include those details. I did both, but I just used the one from Chagiputine and one from Claude. The key to internet success is nitpicking needless details and starting a beef over it. So this is what I'm trying to do here today. This is where it starts.

[17:10] of 2024 starts. Okay. So let's, let's keep going with this. So basically, um, so we've got this big list and you can start to pick out things that you think are interesting, but like, it's also, to me, it's like overwhelming. It's like, wow, like, um, how am I going to try to be all those things? It's impossible. So one of the things you can do, which is really cool. Um, well first, before I even get to the things you can do, I would press retry a few times just to like, see how it does it in different, in different ways. Like it will, you'll kind of explore the [17:40] come up with different ways of describing things that might be better or worse. Like, I don't think that one was like particularly better. Um, [17:53] I think this is like slightly better because it's not necessarily citing their like most [17:59] uh, important work, which I think is kind of irrelevant to this exercise. So I'm going to go with this one and I'll say something like, um, [18:05] Can you synthesize the vibes down into something more compact? I want a summary that can help me express my taste. Do it in five sentences. [18:22] And we'll see what it does. What's really interesting about this is ChatGPT, when it does summaries like this, it's [18:28] like the sort of like, tell me the vibes and it gives you a big long list. At the end, it usually has a summary graph that just like tells you what it just said. And that graph is usually like really good. Cloud doesn't do that. So it might be interesting to try this and try GPT after this, but...

[18:44] Okay, it says, your literary taste gravitates towards thinkers who blend scientific rigor with philosophical depth, often exploring the intricacies of human nature and consciousness. You appreciate writers who can make complex ideas accessible, whether delving into neuroscience, psychology, or the cosmos. There's a strong current of introspection and mindfulness in your preferences balanced by a dash of humor and pop culture savvy. So aside from the fact that it's like really complimenting me and gassing me up, like, [19:08] This is actually like really good. And for me right now, like, because I've seen this before, it's not like a mind blow moment. But, um, but when I first did it, it was like looking in the mirror for the first time. And I was like, holy shit, this is what I look like. Um, and I like it. [19:27] You were gassed up successfully. [19:31] And so, um, so, so that's the, that's like the basic gist of the exercise is like find people you like, throw it into chat GBT and have it synthesize something. [19:39] So when you're, so you have this list and you've had, you sat on it for a little over a year now, like when you're editing a piece or writing a piece, do you ever find yourself like mentally going through this checklist of attributes or is it like, I'm curious how much this actually comes into play during your day-to-day process. It's not a checklist of attributes, but, um, when I, when someone gives me a piece and they're like, what do you think of this? Or should we publish this in every, like, I am kind of like explicitly being like, if, if I don't like it, [20:09] vibe that I don't like it. And then I can be like, well, it's just not... [20:12] Uh, it, it doesn't have, uh, it's not accessible enough or it, um, it doesn't have like that sense of like a little bit of like curious optimism or it doesn't have the depth or the thoughtfulness or whatever. Um, so in that sense, I, I totally do. And then another way that this works is like when I'm editing myself, I do have some of those words in mind and I'm often.

[20:34] either thinking about those words or I'm going back and being like, I feel dry. I don't have the vibe anymore. I know that Robert Spolsky's got the vibe I'm going for. I'm just going to reread him. Yeah. So I'm curious for you. I know that you've done these exercises too. How are you doing taste? How are you thinking about it? And how are you identifying it with AI? [21:01] So I think I did, because you read this article, or you wrote this article last year, and I was like, ooh, I should do that. So all credit to you for this exercise for myself. I didn't come up with this idea. I just copied you. [21:16] The place that I took it differently is... [21:20] I think I'm more multimedia than you are when it comes to tastemaking. Like I love cinema. Like I love exploring different forms of artwork and, um, [21:34] I find that informs what I write just as much as anything else. And so a lot of times... [21:43] I will find the taste notes of what I'm looking for by talking with [21:49] uh, [21:50] Well, talking first with Morgan, my wife, who's a humanities PhD, and so she has a much better articulation of all these things than either of us. But if she's busy by talking to ChatGPT about it and getting a better sense of...

[22:05] Like if I liked a couple of movies, like why did I like these movies? Or if I liked a couple of posts, what artwork is related to these posts? Because I find that it's able to draw things that I haven't heard of or I haven't been interested in. And it makes me more well-rounded. I worry when writers are like, I only read because I think you can get in a little bit of a rut. Personally, I get into a little bit of a rut. [22:35] and so ChappasheepBee helps me do that. I'd be curious like how you how you do that. So read out to me like five of the writers that you love right now and make sure they're ones I can spell. [22:48] Okay, cool. I'll give you a little bit of a list. And actually, before we do that, can you just introduce the exercise that you're going to do? Tell us what you're going to show me. [22:59] Okay. [23:00] So basically my goal is – [23:03] those taste elements that you pulled out in your exercise, where it was, you know, philosophical or lyrical, um, [23:13] I think it's really interesting when you say, I like a lyrical prose. How does that apply in other mediums? [23:21] Lyrical is obvious in, say, a poem or in a song, but is there lyrical paintings? Is that a thing? [23:31] My big thesis when it comes to taste is that it's a blob of emotional permission to like what you want to like. And it's not constricted to certain types of medium. So it's not just writing. Being a great writer and having great taste as a writer does not mean you only read the best books. It means you partake in the best movies, the best music, whatever it may be. Yeah.

[23:54] Okay, so what I want to do is take the list of writers that you have and then try to convince you to watch a movie. Because I've known you for years. I've given you like 20 movie recommendations. I think you've watched zero. So today we're going to fix that. We're going to fix it, Dan. If ChatGPT tells you, you'll do it. If I tell you, you ignore it. So you're going to have ChatGPT do it for me. I love that. I also would like to do that with you, too, just to see what we get. Because I really want to explore your taste, too. But let's start with... [24:23] I'll start with what you want to do. So, um, [24:26] Yes, let's pull up ChatGPT and we can see what it says. Okay. So, Dan, who should I put in? Just give me like five. Okay. So, I mean, we've already talked about Annie Dillard. I have to have her on any list. [24:39] I would say Robert Persig. A new one, like a more recent one is this guy, HDF Kiddo. He's like a he's like a classicist. He writes about Brees. He's amazing. Is it Kiddo? K-I-T-E-O. K-I-T-E-O? T-T-O. [24:56] I like kiddo K-I-D-D-O. [25:00] That's his nickname, kiddo. [25:03] Also, Ian McGilchrist. Sorry, his name is I-A-I-N. He's got an I in the middle. Oh, man. And then M-C-G-I-L-C-H-R-I-S-T. So what I'm going to do is I took those lists of, say, here's a list of my friend's favorite authors.

[25:26] and then recommend five movies that have similar vibes. [25:29] Be specific in why they are similar. [25:31] I do like it. So the response from chat GPT is kind of funny because they put vibes in quotation marks. It's like it's not a real word, which they may be right about. And this. Oh, so and it listed out the five vibes for each of them. It kind of gave three for each of the five authors and they gave five movie recommendations. [25:55] I'm curious in the five movie recommendations for the tree of life, my dinner with Andre, the seventh seal, uh, 2001, a space odyssey and wings of desire. Have you seen or heard of any of these? So I've seen the tree of life and I hated it. I did not understand it at all. Um, good. We're doing good. But like, I know why it's recommending it and I have been recommended that before by other people. And it could be a, [26:24] It just wasn't contextualized for me appropriately. The description of it sounds amazing. I want to watch it, but the actual... [26:31] like reality of it. I was like, this sucks. Um, um, my dinner with Andre. Um, another one that I've, that's, I've heard of that. I've never watched it, but I, I know that it, uh, I probably would like it. So that's a good, that's a good recommendation. The seventh seal, Ingmar Bergman. I, [26:48] I've definitely seen Ingmar Bergman. [26:50] I think I maybe watched that one, but it was a long time ago. Basically, I went through a phase where I really liked Woody Allen movies, which I really obviously don't want to say.

[27:03] The art is different than the artist. If you're going to reject film based off of the moral actions, you're just going to have to reject the genre. Okay, well, I will say when I was in college, I really liked Annie Hall in Manhattan. And Ingmar Bergman is one of his big influences. And so I started watching Ingmar Bergman films. [27:20] I can't say that I immediately loved him and watch him all the time, but I respect him as an artist and I like his work. [27:29] 2001 A Space Odyssey, I must have seen that. I don't specifically remember, but it's a classic. If you've seen 2001 A Space Odyssey, you'd remember. Is that good? I remember the Dave thing or whatever, but I can't tell you where I was in my life when I watched it. Okay. And then I've never seen Wings of Desire. Let me see. [27:50] of Desire. This film echoes the mystical and existential quality of both Dillard and McGilchrist's work. It tells the story of angels observing human life. [27:57] capturing a contemplative spiritual mood that aligns with their philosophical inquiries. That's interesting. [28:03] Um, [28:05] So I would say, like, generally, it's on point. It's sort of steering toward, like... [28:10] Um, [28:11] more like introspective philosophical movies, which I'm like, I'm down for. Um, but it's probably missing some things about movies that I love. Like there are movies I love that are not part of this. Um, that I don't know. I don't know how, what, where you typically typically go from here, but, um, [28:30] Yeah, I think this is actually a really good illustration of the problem with this exercise is you are a professional writer. Like your living comes from writing words. And so, of course, you're going to have a really fine tuned, in-depth taste of writing.

[28:46] words, while in comparison, like movies, like you just like I know you just don't watch that many. It's not where you've really dived in deep. And so giving you the deep cuts, I don't know, 2001 is not a deep cut per se, but it is very different than most modern films. You're going to you're going to have this problem. So if you go, you know, [29:10] My experience with LLMs is they'll either go way too deep or they'll go way too surface level. So, you know, you might say, I like paintings. Who should I like? Like, have you ever heard of Van Gogh? You know, like, so I think with this one, with these five movies, I'm going to prompt it with my friend has only a passing knowledge in cinema. Can you recommend anything after 1985 that is slightly more accessible? [29:34] Now, I'm curious. We have the five shows that it has is The Truman Show, The Secret Life of Walter Mitty, Dead Poets Society, A Beautiful Mind, and Into the Wild. Have you seen any of these? Definitely seen The Truman Show. Great, great movie. I've not seen The Secret Life of Walter Mitty. That sounds interesting. What? I've definitely seen Dead Poets Society. I've seen A Beautiful Mind. It was actually filmed in my hometown. And I've read Into the Wild, but I don't think I saw the movie. [30:04] Thank you. [30:05] Okay. Funny because I was just in the town where the Truman Show was shot like three weeks ago. That's where we did our baby moon. So small world. You would love The Secret Life of Walter Mitty. It's so good. It's very accessible. It's about the collapse of Time Magazine. And then Ben Stiller's character is the backroom photo specialist. And he goes on this journey of self-discovery to Iceland and goes outside.

[30:35] think you would dig the secret life cool i want to watch it um [30:39] And so I think with the exercise, like the next step is the hard step, the one that requires the most emotional activation energy, which is where now you go and you have to go consume this stuff. You know, you're like, OK, now I actually have to go do it, which I think cinema is a hard version of this, but art is a really easy one. [31:09] and it'll help me out as well. [31:10] Yeah. Well, I think like, um, so one of the reasons I really love this as an extension of, of the original exercise is like, um, the original exercise that I did is like a sort of looking backwards type thing as if I found a lot of the stuff and I just need to name it. But there's a whole part of taste, which is like exploring new things you haven't heard of that are like, like the things that you like. Um, because often, um, there are like things, I mean, always things [31:40] of other works. And so if you like one thing, there's usually like a whole related chain. Sometimes it's like, um, it's in different mediums and sometimes it's just, it's still a book or it's still a movie, but it's like the five other directors that influence this one director. And so like, um, part of, I think part of like getting taste is, um, [31:59] traveling those like roads of who influences who and who thinks about what. Um, and I think Chad GBT and Claude are like also excellent for that. And I think that this is, that's what this exercise is like starting to do is like, um, you can explore that those chains of influences.

[32:15] And you can also just, I like it because you can bounce so easily from surface to surface. In my own writing, more and more I've been... [32:24] Feeling like I've been doing like philosophy where I'm skipping along from Foucault to Plato, whatever. And chat GPT is excellent at helping me get the surface level stuff and get enough understanding or at least know where to dig deeper. [32:39] Um, [32:40] I think the idea that you brought up of like, there's more chains to discover. [32:45] I'm just so passionate about content and about consuming good things. The world is just full of good stuff, and I just want people to know how to get into it and know how. So that's why I love these tools and discovering your taste this way because you can just – [32:59] There's so much good movies. There's so many good books. And your entire life should just be filled with greatness. Every day, you should get to consume something that blows your mind. There's enough out there that you'll never run out. And that's just such a gift. And it's overwhelming to find, but... [33:15] This makes it a lot easier. [33:17] Totally. I love that. Talk about good vibes. I don't know exactly how that fits into my vibes list, but I'm picking up the energy and I love that energy. So I feel like that puts a really nice bow on the taste aspect of what we're talking about here. It'd be great to go into topic. I would

[33:47] to help you like pick topics and find topics to write about. Yeah. I actually think this is, um, the least, um, [33:54] maybe one of the least AI-ish, AI-adjacent. What's the right? I don't know. You're the AI and I guy. AI-ified. AI-ified part of my process. So I publish twice a week, every Tuesday and Thursday. And then I write a decent chunk of our Sunday Digest, or it's now called Context Window. And so I don't have... [34:15] the luxury of a ton of time to think through all of my ideas of like, Hugh. Yeah. So I, [34:22] I had to find a way to really... [34:26] go into the zone and pick the right thing. And I found this is, I apologize. This is so Austin tech bro of me. Um, but I've, I go every morning when I, after I do my lift, I go and I sit in the sauna for like 15 or 20 minutes. And if it's a Monday, Wednesday, or Friday, I think about what ideas are good. And if it's, um, and what I'm going to write about and Tuesday or Thursday, like, yeah, so that I just sit in the sauna, like, isn't that a dumb answer? Like I just sit in the [34:56] in my brain. I'm like, hmm, that's a good idea. Yeah. [34:58] Um, and that's it. That's literally it. Isn't that dumb? That's such a dumb answer, but it's really, it's mostly how I do it. Many incredible thinkers, uh, have, have gone before you, uh, having ideas in the sauna. Um, so I don't think it's dumb at all. If it works for you, like, I think that's the thing that people, people miss about creative stuff is like, you got to just find what works and different things work for different people. And if like sitting in the sauna until like your,

[35:28] ideas like power to you. [35:30] I think it's like the Matrix. I just spend all day jacked into the internet through Twitter and emails and talking with people. I just spend all day jacked into technology. Every day I'll have dozens of ideas about what to write about. For me as a writer, ideas are never the hard part. It's picking the idea and knowing which idea will be right. [36:00] get overwhelmed but if i listen to my subconsciousness and just let it bubble up naturally where i'm not thinking about anything usually the first idea that comes into my head is the best one um and so i just sit and wait um and it doesn't take long because i'm a wuss and i can only last like 15 minutes or whatever but i sit there take a cold shower come home write down the essay [36:22] That makes sense. As you might guess, I have a little bit more of an AI-ified process for this. Yeah, tell me about it. [36:30] So, um, what I do a lot is, um, um, [36:36] I... [36:38] I feel like I think really well if I'm walking and talking. [36:42] Um, and, and so what I'll often do is, um, [36:47] Um, I'll either, uh, just get up and take a walk and record a voice memo. Um, and then I'll go transcribe the voice memo with whisper and then I'll feed it into Claude or ChatGPT and like have it basically pull out. Okay. What are the interesting things?

[37:04] Or what I'll do is I will... [37:09] I will actually have a conversation with [37:13] chat gpt advanced voice mode and i'll be like okay i'm just gonna brain dump and then i want you to um i want you to like reflect back to me what you hear and then we'll go down a rabbit hole on a particular thing that i'm interested in and i think it's like really good at helping you find like okay i have this like morass of things like swirling around in my head like what's an interesting thing to like start with or where do i what's a topic that i want to like kind of dive [37:43] And whenever I find one of those, I just put it in my... I have a things. I use things as my to-do list. And I just have a little thing in my to-do list with a little headline. Usually, if I... [37:54] If I have a piece I want to write, I want to write a piece right now called Generalists Own the Future. I just know that's the headline and I just put it in things. That's the handle for all the ideas. And when I sit down to write, I put it at the top and just go for it. [38:10] Um, [38:12] I also find that there are other... [38:16] and I actually can show you a demo for this, but there are other pieces. I'm writing this piece right now where it's not on my weekly cadence because I publish once a week. [38:27] And it's like a much longer piece that requires a lot of research. And like, um, basically what I have is this, like, I'll show you. Um, so basically what I have, so I'm, I'm writing this like longer piece and, um, it's taken me a month or two to write. I'll probably, hopefully I'll finish it this week. Um, or at least a draft. And it's about like, um, um, yeah.

[38:49] What is it even about? I can't even say what it's about. That's how long and difficult and complicated it is, but it's, it's, I'm grimacing because I have to edit this. So I'm like, Oh no. [39:02] It's, it's basically about like the sort of underlying way, architecture of language models and how that relates to some ancient debates in philosophy about appearance versus reality, which, which I can sort of get into, but like more or less it's like, [39:18] some of the philosophical implications of language models. And I basically have this note in, in, in my notes that has been, I've just been adding to for like, um, [39:29] months at this point. Right. Oh my gosh. And, um, and it's highlights its ideas. Like, you know, I wrote, I read this book, the cave and the light Plato versus Aristotle. And I'm like taking a highlight, like figures as archetypes, not figures for profit. He's supposed to have said, which is something about Pythagoras. And, you know, I have all these quotes in here. [39:50] And one of the things that's like really interesting about this kind of a kind of a project is I have an intuition about what I'm trying to say. And I'm I'm running into things all around the world that like reflect that intuition. Right. [40:07] but I'm having a hard time saying it. So it's a little bit like the language model. Sorry. It's a little bit like the taste thing from earlier where it's like, [40:17] I have taste already. I just don't know how to say it. And being able to say it is like a really important thing to actually being able to do it. And I find that language models are really good for like synthesizing down like a morass of things like this into something like much more compact. So if I go into Claude, I can probably find like historical chats where I'm like asking it.

[40:39] to pull out basically what I do is what I've been doing or what I was doing previously is I was like every day going into Claude and having it write a thesis statement based on all the notes that I was collecting. And then I was trying to like rewrite it and like make it better. And I was just like, every day I was writing a new thesis statement until I like refined something that's like, this is the idea. This is what I'm going to go with. Uh, and I found it was really, really helpful for that. Um, [41:03] Let me see if I, how do I? [41:06] Search for my. Oh, here we go. So I so I have this project in Claude called seeing like a language model. And I basically take that note file and I put it in as the as the knowledge for that for the project. So it has access to all this to this huge long note I've been collecting. [41:22] And I'll start a chat and I'll be like, given all of my attempts and all of my notes, write out what you think my thesis for this piece is. And so it'll say, like, based on your notes, it appears your thesis for seeing like a language model is. Language models offer us a new lens through which to view intelligence, knowledge and our relationship with the world. This perspective challenges the 2500 year old church of reason that has dominated Western thought since Plato and Socrates by shifting our focus from essences to sequences. [41:49] from definitions to usage and from abstract rationality to contextual understanding, this paradigm shift not only resolves longstanding debates about AI's capabilities, but also promises to transform fields from science to creativity. So I think that that's actually pretty good. And it's like something that I couldn't quite say. And it's like sort of distilling everything down into something that like kind of gets me there, but it's not quite there. Because there's all this stuff where it's like, what does it mean to shift our focus from

[42:19] That's just philosophical, like memo jumbo, basically. And so I'll say something like, make it better. And it will do it again. [42:26] I think that's a really good like Claude trick is just always ask it to make it better and it just will be better. Sometimes you can also ask it like, [42:34] is this any good? Like, what do you think of this? Please critique this. And then based on the critique, once it gives the critique, then say, make it better from the critique. [42:43] So it gives another one. I'm just basically saying, make it better, make it better. [42:47] Make it better. [42:50] And I'm saying make it better. We don't want to define intelligence. We want to dissolve the question. And I think this is me sort of like saying, I want you to make it better in this particular way and sort of seeing what it does. [43:04] Um, and I'm honestly just going, um, [43:08] going down the list like that. Now I'm saying, okay, please reflect on this thesis and all my notes that led up to it. How do you think it could be improved? Remember, I want it to be a concise, accurate, interesting thesis statement, including a few bullet points or paragraphs of elaboration to unpack it. Just reflect, don't rewrite it. So I want to split up the task into two. And often in a language model context, understanding that there are multiple tasks involved in what you're trying to do. [43:33] And splitting it up, like rewrite and reflect instead of just like doing it both together helps it. [43:39] So that's just to clarify, that's the just reflect, don't rewrite yet is like, I don't want you to rewrite the thesis. I just want you to tell me how I can improve it. And then I'm going to assume in your next prompt, do you tell it to rewrite it? What's the reflection?

[44:09] So it says, you know, the thesis effectively captures the paradigm shift from essentialist thinking to a more fluid context dependent worldview, blah, blah. So it's giving all the strengths. And then it says areas for improvement. It could be more concise. It could have more clarity. It could have a personal angle. It could talk more about practical implications and create more tension or conflict. So there's a lot of stuff it could do better. [44:30] And I'm like, rewrite it. And it rewrites it. [44:33] And I think the interesting thing from all of this is I'm not then taking the thesis and – [44:41] Uh, and like just being like, okay, this is my thesis or whatever. Like, it's not going to give me the thesis, but what it is doing is it's reflecting back to me patterns that it sees in what I've been thinking about and distilling it down in a way that like, every time I ask it, like I'll do this like literally every day until I have something I'm satisfied with. Like every time I ask it, it's like a little bit of like a kaleidoscope where I'm like, I get to look at all my notes from a different perspective because it's sort of like stochastic. [45:08] And it helps me be like, okay, there are these phrases that it's using that are resonating or phrases that aren't. And then I'll go and write it myself until I have like this over a period of days or weeks. I have like a really concise thing that I'm trying to say. And once I have that, then I can start writing. Is the stochastic element because it comes back a little bit different every time because of that? And that's why that's important? Yeah, exactly. [45:32] What's interesting to me about this process, one, like how you do it is interesting. [45:38] But also it's the exact opposite of how I think about my writing. I don't mean that it's neither good nor bad. It's just very, very different. Typically for me,

[45:48] There's no note taking, maybe like it's very rare for me to take a note, but just it's all in my head. I could just draw out in my head when the time comes. And so the the taste element helps me reach a level of emotional clarity and permission to do it. And then there will be some initial spark. So some news items, some headlines, some discussion I have with somebody that leads it off. [46:18] to go deeper on some fundamental thing that that [46:22] spark indicates so um [46:25] Have you ever used consensus before? Do you know what consensus is? [46:29] like the blockchain thing. [46:30] No. Dan, the blockchain thing. This isn't scam and I. That was a big blockchain company, wasn't it? Yes. I'm being mean about the blockchain. I shouldn't be mean about the blockchain. There's some use cases I believe in, but it's too easy to dog on. Okay. Well, I'm about to blow your mind. Let me show you this. This is consensus. I think they just raised like 10 million bucks or so in the last month or two. [47:00] mixed with Google Scholar. [47:02] Oh, I have seen this. This is really cool. I love this. Yeah. So it helps you answer like fundamental questions. And so, [47:11] A lot of my work think about monopoly dynamics, power dynamics within industries. And so if I'm trying to get more scientific and more rigorous in my thinking, I'll come to consensus and start pulling out studies and just to just kind of like fertilize the intellectual soil, if that makes sense. As I'm thinking about the topic, there might be some spark. I don't know. What was something –

[47:38] Um... [47:39] What was the news item that caught my interest lately? [47:44] Oh, the open source models for Meta. That's a really big deal. I want to think about it more correctly. Like, so what, I haven't done this before, so this may fail spectacularly, but what does-- - We're doing it live, folks. - We're doing it live. I find consensus is better with science questions, but we're gonna try this out. What does open source do? [48:07] On Monopoly Dynamics and Software. [48:12] Um... [48:14] So basically what it does, there's these synthesize and these co-pilot questions where it [48:20] Um... [48:22] And it pulls out the various pieces and then does the key insights. If you ever read a bunch of papers, like most of the writing is pointless and boring. [48:32] overly verbose. And so I love consensus because it helps me get right down to the middle bit. So co-pilot summary will tell you this, like, okay, duh. It says, these studies suggest open source software changes monopoly dynamics by increasing competition, altering market structures, and influencing software quality pricing and innovation, which is like, [48:55] Fine. It's not like a necessarily great answer, but it's useful because it says the impact of open source on monopoly dynamics. It pulls out six papers, which, [49:05] And I can start going a little bit more in depth.

[49:10] It's funny, but as a writer, you eventually learn that if you read like three papers, you've gotten to about 95% of the depth of most experts. You can get there quicker than you think as long as you're reading the right papers. And the issue online before LLMs was that it was really hard to know what the right paper was outside of just citations, which is a really flawed metric for reasons we can get into if you're interested. [49:35] Um, yeah, [49:37] So I use consensus, so there'll be some spark for me of like, oh, that's a good topic, but I need to better understand the fundamentals, and it'll be a combination of read consensus, having questions from the papers, and then I'll be able to answer that. [49:49] pulling it into chat GPT, explain a term. And then eventually I'm like, okay, [49:53] I have the idea it's time for craft. Yeah. I'm, I'm curious. Like, I really think that that, that consensus thing, it makes, it makes total sense. Like, and the, the place it makes sense, I think most for me is, um, as a writer, in order to write anything interesting, you have to understand the current context. Like, um, what is the consensus on this topic already? [50:23] And like, normally we know that, but you know, sometimes you want to go outside of your normal beat where like, I can tell you that the current consensus on like something AI related, like pretty easily. But if I'm writing something that's like not about that, um, just getting up to speed really quick. I think a tool like this is so, so, so, so helpful because otherwise it's like hours and hours or weeks or months or whatever to like really get there. And, um, yeah,

[50:51] it limits what you can even write. And so this sort of expands the number of things that you can write confidently, which I think is really cool. [50:59] Yeah, eventually what I want is a product where I can drop in all of the books that I have read, all the books that I know are adjacent to what I have read, all the papers into one place and build out my own consensus data bank. We're not there yet, but we're pretty close. We're remarkable. If someone could build that for me, I would introduce you to investors. We could get you funding. It's a really good idea. I mean, Claude Projects is sort of like this. [51:29] Thank you. [51:30] I will do that fairly often as I'll drop books or parts of books into cloud projects and use that as a jumping off point for distilling down an idea or a thesis. I think one of the problems currently is... [51:45] If you drop an entire book into projects, it basically works. But having that much context can confuse the model a little bit because it doesn't know as much of what's important. And I think what's really interesting is sort of doing the dynamic selection of like, based on what I'm writing, like what are the books and what are the like sections of books or papers or whatever that like would be useful here and what wouldn't be. Like deselecting is just as important as selecting in some ways. [52:15] We evolve that over time because I do think, yeah, that's like the dream. That's like the nerd dream is like, they're all my books in here and like, uh, help me get ideas out of it when I, when I want to understand something or I'm, I'm looking for, I'm looking to like distill something like help me do that.

[52:30] Do you think it's a question of context window? Or is it like, oh, you've got to fine-tune your own model? Do you think it's like, oh, I have to use a technique like RAG? [52:39] It's just rag, basically. You think it should be rag? It shouldn't just be like a 10 billion word context window or whatever? I think context window is great. And in general, you prefer to use just a bigger context window over rag because – [52:57] yeah, the more context you have, the better. But, um, if you're talking multiple different books, um, and some of the books are like 400 pages, like there's just a lot of extraneous stuff. And the more extraneous stuff you have in context, the more likely you are to like get, get off track basically. So the extraneous stuff becomes distracting and you can, if there, if there was like an easier way to select the parts that should be in the, uh, in context versus [53:27] time of knowing what to attend to, like, I think that would be, that would be better. [53:32] Um, yeah. All right. Well, if anyone has that product, you should email us. Uh, we'd buy it. Um, so, okay. [53:42] Yeah. Uh, DM DMs open for sure. DMs open. That's right. Um, okay. So I think that's, that's sort of the, that's the ID eight phase. I'd be really curious, um, to go into craft with you. So how are you, how are you using it to, um, you know, write and edit your pieces? [53:59] Thank you. [54:00] Um,

[54:01] Thank you. [54:02] Yeah, let's – I think the big thing when you're talking about AI and craft is you're – [54:07] it's mostly a tools question, right? How are you allowing the LLM to interact with what you're creating and [54:15] Uh, [54:17] And is it within a chat bot? Is it a co-pilot within an existing application in which you do your creating? Is it something entirely different? And so that's the big question. Um, [54:29] For the chat bots, this is, I think, level one of when you're trying to get better. The most common thing that I'll do as a writer, I suck at conclusions. I suck. It's just like I say what I want to say and that I'm just like, OK, I said it. Like, you know, that I need to find a way to land it. I always struggle. And so. [54:53] It's very simple, but I'll just copy and paste it, drop into Claude, and say, help me finish this. Give me 10 different... [55:03] subheads and the thesis that we could do. And, you know, almost always all 10 of those are wrong. But by being able to articulate what is wrong, [55:14] It's able to... [55:16] I'm able to say what is right. [55:20] Is that similar to how you use the chatbots? Or... [55:24] That is similar. So there is the kind of summarizing aspect or continue on when I'm stuck. There's a lot of different places that I will use it. So right now I'm writing this, seeing a language model draft. And I'm writing it in Lex. And Lex is a – it's sort of like Google Docs but with AI baked in. Every incubated it. It's now its own separate company run by every co-founder, Nathan Viches. And I use it because it's sort of just like –

[55:53] So having access to AI in context removes a little bit of friction, and that's really nice. And you can see if I show changes, actually, there's a way to do this. [56:07] AI view. Okay. So what you can see is what text is AI written. [56:16] Right. Which is really cool. So the text in blue is written by AI. And I'll say like, I probably won't be using this actual text. What I'm trying to do with this draft is like 5000 or 6000 words, 7000 words already, is I'm just trying to get it out. [56:33] Um, and, um, [56:34] There's a lot of times where I'm summarizing an idea that I already understand, but I just like getting it into words. It's such a drag and I just don't want to do it. So in this case, like I need to talk about Plato's theory of forms. [56:49] And I just basically have Lex like write the theory of forms and that is Claude on the back end. And then where I would have gotten stuck and been like, oh, I need to go read Wikipedia and read like the Stanford Encyclopedia of Philosophy and whatever. [57:04] generic and like it just explains exactly the idea and then I can move on. And like later on in my process, I'll probably go back and like make these sentences my own and like, [57:14] make it give it like the flavor that I wanted to have but like this is enough for me to keep going and I think that's like a really really really valuable thing [57:22] Um,

[57:24] Another... [57:28] Shoot. Another cool thing that I like to do is Lex has this feature where you can ask it, [57:37] Uh, uh, [57:38] uh, like ask it to complete things in comments. So I'll like highlight something like this. So, um, these are some notes that I have about a part of the article that I'm writing. Um, [57:49] It's basically about why science has been stuck in certain fields like psychology for a long time. And I want it to expand that part of the argument and give me examples of what I'm talking about. And rather than having to go into Claude and be like, here's what I'm writing about, here's all the context, blah, blah, blah, I can just make a comment and say, at Lex, can you turn this into something interesting? Yeah. [58:15] And it will give me like, um, [58:18] uh, like a bunch of thoughts on like examples I can use or, um, ways I could write a particular paragraph or section. And that's just like a really, really easy, easy way to like get the specifics in my head or get the examples I need or whatever, so that I can like, I can keep going. So it's, it's, it's really, really good for that. [58:38] Um, those are my Lex things. I have more stuff to show you in club, but I'll, I'll pause there in case I'm curious, like what this brings up for you. [58:46] Yeah, it's interesting seeing because these are I also will use Lex and this is very different than how I use it. So it's kind of fun to see the tooling here. I found that over time I'm trying to shift more and more of my.

[59:01] AI labor out of like the Claude chat bot and the chat GBT chat bot, because it's distracting and I don't know, it's clunky and I want to work in, in line so I can show you, um, [59:13] Do you do any of the custom prompting? I don't. [59:16] Okay, you want to show – I built one yesterday. Yeah, I want to see that. Okay. So like I mentioned, one of the things I really struggle with is a conclusion. And I do it so often where I want to write a conclusion that – [59:34] I don't really know. It's just I don't want to keep doing it over and over again. [59:38] Copying, pasting, match. I just don't want to do the prompting anymore. So what you can do is, [59:42] is you can go to Prompt Builders. [59:46] And this is one I call, what would Evan say? [59:52] and [59:53] And you can see that I name it here. I pick the model. So I'm using three and a half sonnet here and I, [1:00:01] Uh... [1:00:03] I have a draft, or a system prompt. So where I tell it, hey, I've got a draft I'm in the middle of. Below is going to be a big brain dump of things I've written in the past. Use that to create a list of things I might want to say next. And below that, I have, I think, one or two articles that I've written, because when it gives me the conclusion, I don't want it just to do the ideas. I want it to do the tone and the voice, and I just want it to have the whole thing. [1:00:30] So that's the system prompt. The next is...

[1:00:34] It says, what's up? Here's some ideas. [1:00:39] We'll bleep it. Just say the whole thing. Yeah, we'll bleep it. So it says, what's up? Here's some ideas. It says, what's up? [1:00:47] Just say it. No. [1:00:51] And so... [1:00:52] I also automated the first message back. So think of this when you're doing the chat GPT or the cloud experience. This is the first message that the AI will give you, and these are the instructions. And this is the system prompt is the thing to make the output good. [1:01:11] Um, [1:01:12] So what I'll do is this is my draft that I published, I think, last Thursday or Tuesday. I can't remember when I last published. It's been a week. [1:01:23] And so I'll just go to Ask Claude, and then I say, "What would Evan say?" [1:01:30] And it just gives me 10 ideas on how to do this finish. Welcome to the content thunderdome. That's like such an Evan thing to say. Oh, yeah. I was hoping you would do it again. But yes, last night when I was playing with this, it says copyright is like a condom. It works, but it's more fun when you don't have it around. [1:01:56] Which is something I would say and then you would make me cut. [1:02:00] That's really great. [1:02:03] But you can make these custom prompts for anything. And then what's also useful is if you do the checks. Do you use the checks at all? I do sometimes, yeah. So checks are basically, like, I really struggle with passive voice. This is something that Kate, our editor-in-chief, who is wonderful, is constantly getting me to try to be better at, which is passive voice.

[1:02:30] passive voice for me, um, and just run the checks. [1:02:36] And good news, this is an already edited piece, so we don't have it really in here. There's not too much passive voice. It'd be interesting to do it if we did with a new draft, the one that I'm working on today. But you can go through and do these edits. And the goal isn't necessarily to... [1:02:58] The goal isn't necessarily to get rid of your editor, but it's more the better and cleaner the draft is that you turn over to your trusted thought partner, your writing partner, the better the feedback they can give you. [1:03:28] like being able to eviscerate like 20% of the editing department at the Atlantic. Like they could just go away like their job or their jobs could be something different here because the language models can do a good enough job. [1:03:41] Um, [1:03:43] And so I find, you know. [1:03:46] come up with a spark sauna, right? Edit and Lex. And then I turn it back over to my editorial team. Yeah. I mean, I think like, um, for us, like obviously we have editors, um, which is great. Um, but some people don't have editor. A lot of people don't have editors. Um, peasants. Many people don't have editors. I mean, also sometimes editors are asleep or on vacation

[1:04:16] to give Kate a draft, for example, that's like just better. Um, it helps her. Um, [1:04:21] You get better edits because of that because she's not thinking about things that are like... [1:04:25] something else can catch, which is really cool. Another thing I use Claude for that's sort of in the crafty realm is finding ways of doing metaphors and analogies and similes. Nice. I do this too. And so I have this particular analogy in the piece I'm writing that's about Socrates and Socrates' search for truth. And I'm talking about him splitting the sea of words into like [1:04:52] words that express the truth and words that express opinion. And I want to, I want it to like, um, [1:04:59] to revise that metaphor for a different philosophical outlook called pragmatism. And I think the specifics don't really matter, but I'm just like saying to Claude, like I'm writing this piece. [1:05:11] I talk about the Socratic method using a metaphor of, you know, dividing up this sea of words. How do I modify it to show the pragmatic method by contrast? [1:05:22] And it gives me something that I think is not that great. [1:05:26] And then I'm just pushing it a little bit. I'm like, hmm, what about something like in a pragmatic viewpoint, you just find currents that are going to take you where you want to go. So basically what's happening here is it suggested something that I didn't like, but that pushed my brain to be like, okay, but here's a metaphor that I actually would like or is partially expressing what I want. And I'm just going back and forth with it.

[1:05:49] on, um, [1:05:51] on, uh, on sort of building that metaphor and it's not doing the best job. Um, and so what I have it do is again, this is in my cloud project. So I'm like, what are some quotes from my notes that might help me write this section on, on pragmatism a little bit better. And what's really interesting about this is it like, it makes the, the stuff that, uh, [1:06:12] that is relevant to pragmatism, which is the sort of school philosophy that I'm introducing in this part of the piece. [1:06:20] it makes it more relevant to the model because it's just right there in the chat history. And once I do that, it gives me a bunch of quotes, which is really useful just to see, what am I thinking about in terms of pragmatism? And then I pick a few of the quotes that really express the idea that I'm trying to express as this metaphor. And I say, okay, we've number eight. So number eight is like, [1:06:44] Each of these numbers is like a number of a note that I've taken. So we've notes number eight, four, and six into this metaphor. And then it rewrites the metaphor. [1:06:54] um, into something that, um, [1:06:58] that incorporates some of those, some of those ideas. Um, and, and sort of, I just keep going with that. I ask it to reflect, like we've talked about reflecting what you wrote, how can you make it better? Um, and then revise. And like the thing it came up with is like actually really good. It's [1:07:16] Uh, okay. In the Socratic view, we dive into the sea of language, hoping to separate the murky waters of opinion from the clear streams of truth. But when you look closely at even the clearest drop, we find no indivisible essence of water, only space, molecules, and relationships. This is the pragmatist revelation. Meaning isn't a substance we extract, but a property that emerges through use. Just as water becomes refreshment when we're thirsty, cleansing when we're dirty or danger or drowning, words shift their meaning based on context and purpose.

[1:07:46] good. I want to make this better, but it's this dual collaboration. Some of the stuff that it's coming up with, I put in there, I said, when you divide a drop of water, you never find a pure substance. It's weaving things that I put in there. It's weaving in notes and it's weaving in its own sense of what good is and what's relevant to create this metaphor that I probably wouldn't [1:08:16] I think it's going to be one of the central metaphors of the piece and it's like beautiful and amazing. And I like, I love it. Um, and totally would not be possible in this way without, without Claude. It's really powerful for this. [1:08:28] How long did this exercise take you? I was doing it in like the 10 minutes before this show because I was actually just doing it for myself. I actually just wanted to do this. So say like 10 minutes to come up with a metaphor? Yeah. [1:08:41] interesting. It's interesting seeing how much of our relationship with these models comes from our publishing deadlines. No, I'm serious. I don't mean that in a derogatory or a moral judgment way, but more just so much of your usage is like, I'd really like to do that. I'm like, I don't know, time to do that. Which is my own fault, because at the start of this year, you and I sat down, I was like, I need to publish twice a week. I need to get to that speed. [1:09:08] I don't know, man. You definitely publish more than me for sure, but if you want to talk about who's busier, I might give you a run for your money. Oh, listen, I'm not trying to compare it all. Oh, the podcast, I have to talk. No, come on.

[1:09:25] Anyways, we don't need to talk about the podcast. It's very funny that the marquee post of your year was like, admitting what is obvious, I want to be a writer. And then the big thing you've done this year is do a podcast. It's kind of funny. [1:09:38] Um... [1:09:39] I mean, that's, that is one of, one of the big things I've done this year. Like let's, let's be real here, but yes, the, the, the podcast, uh, the podcast is one of the big things. And, um, [1:09:50] And the writing, it is always a continual struggle for me to like – [1:09:55] figure out how to prioritize both and like wanting to prioritize the writing and all that kind of stuff. And I'm constantly finding that balance. [1:10:02] I think it's less of who is more busy, because who knows? I'm not going to compare that. But it's more about the attitudes that we have or what we want to pull out of the models. I'm not quite as interested in a thought partner, where I'm just like... [1:10:19] I got the juice. I just need you to clear the runway for me. You know, I just need you to let anytime I get blocked, fix my emotions, give me the next step, and I'll just take it from there. And while you – it's a much more collaborative process. So it's really, really different. Yeah. [1:10:36] but, uh, valuable. I want to try, I want to try the, maybe I need to take a note. And then once I start taking notes, I'll put them into, uh, clock projects. Yeah, no, I think that, I think that is, I think that that is very interesting. Um, and I think generally like it reflects like how we work in general. Like, I think like, I just like a more collaborative like work process. And I think you like a more like, I'm going to just clear the runway. I got the juice, you know? Um, and so, yeah.

[1:11:06] I think that's really interesting. And I think, yeah, I think the note-taking thing is it's just like a – [1:11:11] it's a psychographic. Like it's a thing that some people do. Um, and some people don't. And, uh, I think some, there are people who are like, Oh, I should take more notes. And I'm just like, no, [1:11:23] if you want to take notes, great, but like sometimes that's just not how your brain works and that's totally fine. You know? Um, [1:11:30] So, yeah, I think this is a really good... [1:11:34] good summation of like some of the ways that we use, use Claude for the kind of craft part of the writing process. Um, let's, let's talk about the last one. So audience, tell us about audience and how you use it for, for audience. See, I actually think you are much better than me, uh, at using just an audience in general. I think this is actually one of your big strengths as a writer. Uh, when my big weaknesses, it's why we're a good team. Um, [1:12:01] But the... [1:12:04] Like, I don't know. [1:12:06] I'll do the typical things. So we have Spiral. Have you talked about Spiral on this podcast? I've talked about it a little bit, but we should introduce it for anyone new. Okay, so Spiral is an app that Dan came up with the idea for, and then our internal team of engineers and designers in partnership with our entrepreneur in residence, Brandon, built together. You can think of it... [1:12:29] I don't know how you describe it, Dan, so let me try to describe it and you tell me how close I get. [1:12:34] I kind of think of it like a Mario pipe, where if you've ever played Mario, sometimes he'll go into the pipe.

[1:12:43] And then he comes out in a different shape or he comes out in a different place. And Spiral is a pipe designer. And so you can take one body of text and stick it in the pipe and it transforms it into something else. So pragmatically, it means you write an essay, it can make that essay into a good tweet. Or you write a good tweet and it can turn that into a good YouTube description or whatever it may be. [1:13:11] Am I close? Yeah, that's more or less right. I mean, basically, the insight is... [1:13:18] as a writer, you're constantly like, I feel like I'm constantly like I do the core creative work and then I'm constantly translating that work from one format to another. So I'm taking an essay and I'm like, I need to make a headline from it. Or, and that is a new format of the essay. It's like a compression of that essay. Um, or, or I'm taking an essay and I need to tweet it or I'm taking a podcast transcript and you tweet it or making LinkedIn posts or whatever. Or I have a podcast and I want to make show notes. Like there's so many things where it's, [1:13:47] You're transforming it from one form to another as a way to get distribution, as a way to reach people where they are in the channel that they are, for the amount of attention that they have in the format that they expect. And that is a really skilled task. It requires a lot of knowledge and skill to do it well. [1:14:07] Um, and it's also like really repetitive and kind of sucks. Like no one wants to do it mostly. Um, and I realized that like Claude is actually good enough. Um, if you do the right prompt for it to like automate a lot of that, where it doesn't do everything for you, but it's like, it gets you 80% of the way there.

[1:14:27] Yeah. [1:14:28] And, um, [1:14:30] And so I was, I made a prompt for myself for like a couple of these things, like for, um, you know, podcast transcripts to tweets or whatever. And I was using it, but it was like hard for me to type. And I just felt like it would also just be hard for, I felt like it could be really valuable for every, but I felt like it would be hard to get people to use the prompt because it's like big and hard to create. And so we have this thing called think week at every platform. [1:14:53] where we don't do meetings and we just sort of reflect and think about what we want to do next and also just spend a lot of time just letting our creativity run. And I just built an app to do it called Spiral. I did it in a couple of days. And you can basically make a Spiral. You give it a bunch of examples of the tasks you want us to do. So like podcast transcript to tweet. You give it a bunch of podcast transcripts and tweets you've done. And then... [1:15:18] It just gives you a little text box where you can paste in a new transcript and it'll make tweets for you. [1:15:24] Really simple, but it works really well. [1:15:27] Yeah. And, and yeah, Brandon and, and the team kind of like took that MVP app and just built it into like this beautiful thing that, that we launched a couple, a couple months ago. And I mean, it's doing really well. I think I use it a ton internally. I use it a ton. I think you use it a ton. We use everyone internally uses it. I think it's going to pass like 5,000 users in the next like couple of weeks, which is pretty cool. Oh, wow. Cool. [1:15:51] So, um, yeah, so that's, that's what spiral is. So I'll use spiral mostly, um, because,

[1:16:01] Social media is like the bane of my existence. I do not enjoy it. I am not good at it. However, we do not make any money if people do not find our essays. And so social media is a really key component. And so I'll use Spiral to... [1:16:15] take an essay and transform it into a tweet is my most common usage. [1:16:20] Um, [1:16:22] I assume it's the same for you. I'm curious for your spiral usage, if you move beyond just tweets, is there other places you're using it? Yeah, and I'll show you an example. [1:16:37] So yeah, I mean, I'm using it a lot for tweets and LinkedIn posts and all that kind of stuff. And it works super well. It's kind of crazy how well it works. I'll show you. Here we go. [1:16:52] We have a tweet, right? It's got 157 likes, which is not the most viral tweet I've ever done, but it has 30,000 views. [1:16:59] And it's about this... [1:17:01] model that just came out or not came out, but like that open eyes been working on that the information reported on. And, um, [1:17:09] uh, [1:17:10] And I want to tweet about it because I think part of my job is when something new comes out, I want to tell people about it. But also composing that tweet, even though it's pretty rote, it doesn't require a lot of thinking. It's not a new idea. I'm not that interested in it. But I want to get a tweet out so that people see it and people know about it because I think people rely on me for that kind of thing. And so what I did was we have this spiral that is an internal spiral that converts articles into insightful conversational tweets.

[1:17:39] And there was someone who on LessWrong summarized all the news about this. LessWrong is like a forum, basically, for rationalists. And summarized all the news about this new model. So I read it, understood it. And then I was like, okay, I want to turn this into something I can tweet. And I just threw it into Spiral. [1:18:09] multiple and then it generated a bunch of tweets so open a strawberry is about to change the game this ai can solve complex problems on the first try without hallucinations open a strawberry set to revolutionize ai here's what we know and it gives a bunch of stuff and um [1:18:23] These are not things that I want to tweet just wholesale, but like a couple of these things would have been hard for me to come up with. Like it solves complex problems on the first drive without hallucinations. It generates high quality training data for Orion. It may be integrated into chat GVT as soon as this fall. [1:18:37] And obviously I could write that, but it would take me a little while to figure out the bullet point structure and what I want to say and having this thing like, oh, why does it matter? And so what I was able to do is I just took that, I pasted it into Twitter, I revised the headline, I revised the top because I didn't like the set to revolutionize AI thing because it just felt like kind of... [1:18:56] cheesy. I edited a couple of things. I took out some of the emojis, whatever, and I tweeted it and it has 30,000 views. And that's a really simple thing where I would have done this ordinarily, but it would have taken me like...

[1:19:09] 30 minutes or 40 minutes or something like that. And it would have been a lot of brain work. And for this, I'm just editing, which is like much easier than writing wholesale. And it took me five minutes. I was in bed. Like it was really, really easy. And I do that a lot for news article news stuff. I do it for obviously all of our articles for our podcasts and podcasts. [1:19:29] It means that I tweet more. I have more interesting stuff to say. And, um, and like all my engagement and stuff is, is way up because I'm able to put out more stuff, um, which is really cool. [1:19:40] I'm curious, like, as a writer, I know that some people are going to watch this and, like, have, like, moral... [1:19:47] horror, right? That you're like, oh, you took someone else's content, you transformed it with an AI, and now you're going to monetize on top of that. I think that's a case where some people, some writers have real apprehension, and this is the worst case scenario. Do you think about that at all? Does it bother you, or have you worked your way through those emotions? I mean, obviously, I think that's a really important question, and it does bother me if I [1:20:15] uh, [1:20:16] If I think there's a case of like it's stealing or plagiarizing or whatever, like all that stuff is really bad. And I will say also like it's much more common for me to be doing this with my own stuff than someone else's stuff. But I think this is like a really interesting case that like is important to like reason through. My basic thing is... [1:20:36] Um, so for, in this case, like I cited the information in the tweet and linked to it, both linked to the information and linked to the article, uh, that it originally came from. And I think like, there's a very, very well established practice of like reading stuff from another news site and then summarizing it, uh, for your audience. Um, and, and that in general, I think is like not a problem at all. Um, I think there's a, there's a, like a further component,

[1:21:06] you're using AI to do this. And I think that there are like [1:21:10] Um, I think that there are cases in which that's okay in cases where there, where that's not okay. Um, the, the case where it is not okay is, um, you are lifting wholesale without attribution, like sentences or ideas that come from someone else. Um, where it is okay is you are summarizing it in a new way, uh, for the audience that you have. And I think that that's totally fine. Obviously like there are blurry lines there. And one of the problems with AI is it's like hard to, um, [1:21:40] It's hard to tell always where the output is coming from. And I think what we need are both new tools to detect, like, okay, does this sentence come from somewhere or not? Not was it AI generated, but does it come from somewhere or not? [1:22:00] And then two is a new ethics about what is okay and what is not okay. [1:22:10] is ethics. And we just haven't updated our ethics to account for this new thing. But I think we will. I don't think that this is going to be like a... We never figured that out. I think in the next five to 10 years, we will shift what is okay and what's not okay. And my general belief is that [1:22:30] Using, for example, training these tools on publicly available text to create this intelligence layer is very different from training these tools, creating the intelligence layer, and then having the intelligence layer output wholesale copyrighted stuff without attribution. Those are different things.

[1:22:53] And yeah, I think we'll come up with ethics to differentiate them. Yeah. [1:23:18] Sometimes they'll give me attribution. Like at the very end, they'll have like a tweet, a shout out to Evan Armstrong for doing this or for writing about this, or they'll get called out in the comments by one of my readers. Thank you readers for being vigilant Armstrong warriors. [1:23:36] But like, they'll say, Hey, like this sounds like my post that I had recently written. And I, [1:23:42] Thank you. [1:23:43] I listened to your logic. You're right. Like, it makes sense to me. Like, transformation feels is totally fine. But when it happens to you, [1:23:50] I'm like, no, I don't like this. I spit on you. I don't like it at all. But I then go do and I'll use Spiral. I haven't done it in the case where I'm pulling other news articles or whatever. But like you said, you gave attribution to the people who have the paywall and they did the original reporting. But [1:24:14] There is no, like, I think it's really important to acknowledge, uh, even for us, which is a very AI forward organization. Like we don't, we don't have it figured out. Like, I don't know what's right or wrong. Like I, I can, you know, and I don't think like anyone does. And that's the hard part. I think, I think that's totally right. I actually, I have a very different response to that. Like, um,

[1:24:33] Obviously, someone talking about an idea I had that they got from me without citing me, I don't like. But I do get people all the time summarizing articles or podcasts and stuff. [1:24:45] And being like, this is from Dan Chipper. Dan Chipper had this cool take or whatever. And I feel... [1:24:51] Like I, like I think, um, in general, those kinds of things indicate that like people are, um, [1:24:59] value your content and are consuming it enough to do something with it. And I think as a writer, as an internet writer, that attention is really, really, really important. And it always sort of bleeds back into subscriptions for every year, people reading more of my stuff or whatever. So I actually like it a lot. Yeah, I think it's... [1:25:25] If you think about the bar of intellectual effort that's required to engage with the content, when you and I first started writing online and AI wasn't a thing, the responses I would get and the ones I liked the most were the criticisms. I loved when somebody would take my post, think it was the dumbest thing they've ever read, and write a substack about it. I loved that because even though I obviously disagree, but I liked that they took it seriously enough to try to refute it. [1:25:55] four and a half, whatever, it like the intellectual activation energy is decreased because you can do more of the rote labor by the models. Um,

[1:26:04] And so I wonder if there's a point eventually where we're like a GBT six where we say, OK, I don't like this is no longer OK because you're just doing the whole thing without any effort on your own. It's completely a completely automated process. Maybe maybe it is OK, but like right now we're in this really fuzzy middle ground where it does require an engagement. It does require like. [1:26:26] enjoyment, but a lot of the work can be outsourced to an AI, you know? [1:26:32] Yeah, I think my general feeling about that is what these models are good at right now is replicating patterns that you've... [1:26:43] that have been pre that they've seen previously. [1:26:47] Um, and, uh, like there are certain formats, like for example, this, like, you know, strawberry tweet or whatever, it follows a particular type of format for a kind of tweet that currently works, that changes a lot. Um, and the models are actually very, very bad at like when things change and, um, [1:27:08] uh, need to be like a new thing that works needs to be found. They're actually like not very good at that. And I, and I think it's like unlikely that the language model architecture is going like on its own is going to learn to do that. [1:27:21] Um, which means that even if, even at the GBT six or seven place, um, until the, until the models, um, get much better at reasoning and learn from experience, they're not going to just not going to do that. Um, and like, I guess who knows, who knows what's going to happen, but I'm actually like not particularly worried about, um, um, uh, uh, uh, uh, uh, uh, uh, uh, uh, uh, uh, uh,

[1:27:42] about that, it will happen. There's going to be a lot more AI-generated content that's shitty. [1:27:49] I think we will develop tools and sensibilities to differentiate between them. It's not going to be perfect. This always happens with new technology. There's always trade-offs. There's always bad shit and there's always good shit. And I think generally, we've actually been living in a sea of garbage for a long time. [1:28:05] both in like on the Twitter sphere and Facebook, but also just like the scientific literature or whatever, like there's a deluge. There's way more information available now than there ever has been. And I think language models are the first tool we've ever built to like, [1:28:21] actually effective, more effectively deal with that information and get you the right information at the right time and sort of wade through it. Obviously, they're not perfect. [1:28:30] And what it means is the amount of information that you as a writer, I as a writer, can traverse in any given minute of our day is like... [1:28:40] so much higher. And so, yes, like there's more stuff with less engagement, [1:28:45] Um, but what that means is you're, you're bumping up against the things that you want to engage with more, more frequently, uh, cause you're, you're have access to many more things for us, much smaller unit of, unit of attention. And those things are filtered for you adequately by the language model. [1:29:02] Um, and so I think it can, you can look at it in another way, which is like, it will get you to the things that you want to engage with more deeply, more quickly. Um, and I like, that's sort of how I think about it. Interesting. Um, that was really far off where I think, or how to write with AI. Um, maybe this gets cut in the end, but I, I don't know. It was just like, I was like, if I'm having some sort of emotional reaction, I am sure that listeners of the podcast will be as well.

[1:29:32] I thought it was worth bringing up. [1:29:33] Totally. [1:29:34] No, I think it's important. I think it really is unsolved. I think you're right. There's new problems. I do wonder with the point of we'll build antibodies if it ends up being like social media where now in 2024, I think people are more and more rejecting social media than they used to 10 years ago because they're like, oh, wait, this stuff is rotting my mind. And I wonder if it'll be similar with AI in the early years. People get sucked in, but over time you build up [1:30:00] social antibodies to it. I think so. And it changes like the way that Gen Z uses social media is just different from the way that we do. And, um, and that's just like a, a kind of like, it's one of the interesting, interesting and beautiful things about like how technology like changes the human experience. Like we sort of co-evolved together and we've been doing that for a long time. Um, um, [1:30:21] Cool. So is there anything else you wanted to show about using AI in your audience process or just in any part of the process? I'm curious if you have any reflections on the conversation. [1:30:35] I think the last point I'll make on AI in audience is that we've spent all of today talking about AI in the context of generation. But a lot more importantly is AI in distribution, where it's most of the content that we see online is algorithmically selected. It's AI selected. We don't use large language models, but they're machine learning algorithms.

[1:31:05] I do have to think about it in the context of the algorithm in which it will be distributed, which is why when you're talking about Spiral, the Spiral that works for a tweet will not work necessarily for a LinkedIn post or the LinkedIn post will not work for Facebook. And that is an audience, but it is an algorithmic thing as well. And so when I think about distributing online, it is like, oh, I want to automate away writing tweets because I don't [1:31:35] like them and I'll tweet them anyways. But it's more about as I tweet what [1:31:41] you have to think about what's going to engage the algorithm, which is like a multiple hour long conversation on getting into that. But I think it's a really important point that most people miss is that you're serving the algorithm, the AI algorithm, as much as you're serving the audience in the context of distribution. Totally. And there's a lot of sort of taste involved in knowing how to do that, which is kind of interesting. And it can be dystopian or it can be like this is this is sort of how you get to people, you know. [1:32:11] shit sandwich you have to eat if you want to write online. There's just no way around it. You can kick and scream as much as you like, but it's just the way it is and you just have to deal with it. [1:32:21] Yeah. So this is great. I think we're around time. I'm really psyched that we got to do this. I had a lot of fun. I feel like I learned a lot. I hope you did too. And I'm also just psyched about the course you're running. So tell us a little bit about the course before we sign off.

[1:32:39] Yeah, so I mean, it's very similar topics to what we have today. You can think of it in two parts. Well, the course's name is How to Write with AI. And it's... [1:32:51] general sensibilities around how to write. So the elements that we discussed today of taste, topic, craft, and audience, and the writing principles you need to understand. And then for each of those principles, the accompanying tools that you can use to automate away the rote work, which is similar to the tools that we discussed today, which, you know, Claude, ChatGPT, Lex, and Spiral. And then from there, so that's the lecture format, but the thing I'm [1:33:21] about is there's all these student groups that are going to be working together and writers. We'll have editors that we trained that will be helping each of these groups. And then at the end, everyone will have a chance to share their essay with every audience of 70. I don't know. Where are we at, Dan? What did our Monday metrics meeting say? 78,000 around 78,000. Okay. 78,000, 78,000, 3000 more than we were last week. I think that when I sat down, when you and I were [1:33:51] can we take the very hard, hard lessons that's taken us many years to learn and just like share those with people. Um, and so they don't have to go through the many years of suffering that we did. Totally. That's what the class is. It's going great. We launched it last week. People are really excited. It starts September 17th of 2024.

[1:34:11] Amazing. So if you're listening to this or watching this and you want to learn more, we'll put the link down in the show notes. And you should follow Evan on Twitter at It's Your Boy Evan. I guess we're calling it X now on X at It's Your Boy Evan. And obviously subscribe to every where we both write every week. And Evan, thanks for joining. [1:34:31] Thanks for having me. [1:35:01] that will leave you on the edge of your seat. [1:35:03] 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 [1:35:11] So do yourself a favor. Hit like, smash subscribe, and strap in for the ride of your life. [1:35:16] And now, without any further ado, let me just say, Dan, I'm absolutely hopelessly in love with you.