A (3:39)

Very, very cool. I was researching before we joined each other and tell our listeners and viewers about your professor Tootsie and how he inspired some of. I think he had a great line that is like, are you an architecture or are you a critic of architecture for the New York Times?

B (3:58)

Yeah, exactly. We tend to romanticize our own process, so we fall in love with the journey to come up with something. But this professor of mine, he was old school, right? He really believed that what is on the table speaks for itself. And he would always just cut you off, said, enough of that bullshit. Like, let's just look at what is here. He'd even go as far as when you first came into class, he would organize everyone's model in a line from best to worst, and then he'd start with the worst one and go, what are you doing? We can all see this sucks. And then he would work on it with you. And then he could take a really poor design and actually save it. And so it's like he understood the pattern language. He's been doing this for 50 years. And through his class we started to see the pattern language ourselves.

A (4:43)

Yeah, that's an interesting segue because as you know, I talk a lot about, er, patterns, UR patterns, which are kind of the primitives. And an AI person would refer to a model as a primitive that you can build things off of. It's kind of the essence, the beginning that you can find patterns in, and then you can build kind of really magnificent structures from those patterns. And so your essay, architecture is a pattern language arranged across three dimensions with nine elements, 27 patterns. Stick with us, group. We're not going to go through every single pattern, but let's give our listeners and viewers a sense for the map, right? The idea that you've got various dimensions and, you know, kind of the idea, the conceptual center of an essay. Right. And you give scoring systems, which I'd like you to explain. I'm looking at the one for the idea. And I love the way it goes. One is kind of the worst score you can get, and five is kind of the best. And on the idea you have your number one is this is a Wikipedia entry, which I really, really love. And then you go all the way to two vague allusions to your life, up to five, which is biographically distinct, very self aware, et cetera. Talk about the process and how you do these ratings and how they all work together.

B (6:24)

Right, okay. So I think the first thing to start is with the ratings because people are very scarred by scores. Right? We have that high school model. It's like, oh, got a 84. And you interpret scores in a certain way. And I used to have a one to 10 system. It seemed traumatizing. So let's do one through five. Five is mastery, one is missing. Three is like, oh, you kind of have the basics. Like if you have a three out of five, that's publishable. And the important thing to note is that this rubric is very flexible. So what I'm not saying is there's only one specific way you can score a 5 out of 5 on personal experience. So this whole pattern language is based off of Christopher Alexander's system. And he sees these patterns as fundamental questions. And you can see that pattern solves a million ways, and each one will be different. So even though we're applying quantitative analysis to this, each one is flexible enough so that it can be different every time. And I think that's important. That's what an artist is. An artist is someone who is not defaulting to their templates, but they're always trying to say, hey, I already got a five out of five, but let me reinvent what that thing is to switch now to the idea of form and voice. This is like the larger scaffolding that all the patterns fall into. And the way I see it is this whole language, it kind of stems from the shared psychology of your readers. So when you talk about, like, an idea, all writers, it starts with an idea. And readers generally have limited bandwidth. They can't handle infinite complexity. And so a good idea has a center, which is the thesis. It then has all of the material that orbits around that center, which is the material, and then you want to name that center, and that's your title, right? And then when it comes to form, have you seen the movie Arrival?

A (8:09)

Yeah, just. Just watched it last week.

B (8:13)

Oh, so you're familiar. So you have these, like, heptapod aliens, and they could effectively read essays all at once. They can see beginning and end at the same time. We can't do that as humans. We have to read from beginning to end. And because of that constraint, there are ways that you structure all of your material so a stranger without context can get it. There is an arch to how you compose the paragraphs, your little units. And in terms of tension, you generally want to make it so that it moves from uncertainty to certainty. Because people can't bear certainty. And if you bake that in, sorry, they can't bear uncertainty. And if you have tension, they are invested in the question and the characters. And the last thing about voice, the whole idea is that the act of reading is friction. Right. It takes bandwidth to consume sentences and paragraphs. And so if you imbue them with sight and sound and spirit, the whole idea is you are making something like a linguistic hallucination where you can feel those words in your nervous system. So again, these are not like prescriptive solutions. These are just the questions. And as a writer, it's up to you to be creative in how you solve each one.

A (9:24)

Yeah. I'm fascinated by Alexander's work and he mentioned something I wanted to get your read on.

B (9:32)

Sure.

A (9:32)

He warned that pattern languages can sometimes devolve into style kits. And I know that you've taken that into consideration with essay architecture. You know, what's the Oregon experiment equivalent for essay architecture? Where living local patterns instead of a universal template. I imagine it might be like me writing a very personal essay about where I live. So maybe the patterns of Greenwich, Connecticut are different than the patterns of Queens.

B (10:08)

That's a great question. And the way I'd say it is every pattern has a whole dictionary of types. If you go into repetition, for example, there are dozens of Latin named concepts like an epizuxis or an anaphora. So you have infinite types. And the risk is the development of a global style where everyone is using the same forms of repetition, everyone's using just the hero's journey. We take these proving global templates we know work, and then it just becomes boring because everyone's using them. And the equivalent of the Orgone experiment is to understand how can you be idiosyncratic in how you approach each pattern? That could be trying to think of location. Yeah, I mean, like how would a writer from the south who's enmeshed in that history. Right. Different from a writer in New York City? And I think that that's like the critical nuance in how you can have this shared language. But we each still use it very differently based on where we come from and who we're inspired by.

A (11:12)

Yeah, I'm reading a biography of Mark Twain right now, and it's really interesting, although the author doesn't really seem to like Mark Twain, and I love Mark Twain.

B (11:23)

That's an interesting concept for biography.

A (11:26)

Yeah, well, lots of interesting things I didn't know about him. So I am enjoying the book, although it does annoy me when the author clutches his pearls and talks repeatedly about Twain's failures to become a business tycoon and some of his idiosyncrasies. I think that's what makes him kind of an interesting character. But one of the things that what you just said brought up is Twain changed pretty dramatically over the course of his literary career. He became, as many very famous authors said, you know, the true first American style novelist. Right. But then as he. As he let more of his thinking about issues outside of humor in his. His writing changed pretty dramatically as his experiences changed. And I. One of the things that I like about your essay architecture is you're all set. If somebody starts off if. If we put essays that maybe I wrote when I was, I don't know, 18 into essay architecture and then compared them with now, I would expect that they're going to hit a lot of different scores on your. Your various factors. How do you. Or what do you think about the journey an author takes? Because when we were together, I thought, like, one of the cool things that essay architecture could be incredibly useful for would be, like, substack writers who just want to maybe experiment with a new type of style, you know, in their. In their personal journals. They're finding themselves, wow, I'm writing completely differently now. How would SA architecture help them along?

B (13:24)

Yeah, so. Well, there's two parts to this, I think. And the first is it's almost like when Twain's audience changed, his general style warped with it. And basically your audience is a huge factor in changing how you might use these patterns differently. And when you're writing in your journal, you're much more willing to push the boundaries and experiment than if you're writing to, say, your whole professional network. And so when it comes to essay architecture, it doesn't really have the audience in mind, which is interesting, right, because it tolerates all forms of style. It's looking just at the primitives of composition. And so this is software that I'm building right now so you can upload your own essay and it will both say, hey, you've actually done very well at patterns two, four, and seven. But for pattern 17. You scored a one on that. You're not even thinking about pattern 17. And you know, usually writer will be like, well, you know, I wasn't going for 17. That's not my style. But then my tool can recommend, here's a classic essay where it takes 17 and it takes the patterns you're already great at, and it confuses them into a single thing. So the whole idea is this is like a nonlinear curriculum. I'm not telling everyone to go read my textbook cover to cover. The whole thing is you upload your drafts and it'll say, hey, here are your three weakest scoring patterns. Go study these. And we're going to teach you how to weave that into what you're already good at. And I think this is a little bit different than the whole model of these sycophantic chatbots today. Because right now these things are designed to conform to you. And it tries to understand your taste and make you feel like, oh, yeah, you're doing a great job with what you're doing. But this system has, like a stubborn, unchanging quality standard. And no matter what, it's going to always kind of, yeah. Champion each of these 27 patterns as having equal importance. Right. Because some people say, I only care about these 15 patterns. And this is a great way to upscale in the things that you haven't thought about.

A (15:29)

And one of the things that I find interesting is how does. How would it deal with like a James Joyce? We talked about this when we were together. You know, when Joyce came on the scene, his type of writing was really, really new. And people didn't know how to read it. Literally, they didn't know how to read it. And so if you go back and like read some of the original reviews of his work, they weren't glowing.

B (16:01)

Right.

A (16:02)

And so is there a mechanism for you to incorporate that? Or let's say, let's use Joyce. Let's say Joyce or a Joyce like character today wrote an essay in a style that was really, really different, that didn't fit any of the 27er, patterns that you've got in the software. How would you approach that?

B (16:29)

Yeah. So my understanding, if you look at Joyce or even Picasso or the Beatles or any artist in their earliest phases, they do master the fundamentals before they break into very experimental territory. Alec Corbusier is an architect in a similar state. He started with very machine like boxes, and he became known for these very expressive curved buildings. And I think if you look at Portrait of an Artist as a young man, I believe that is much more conventionally structured than something like Finnegan's Wake. And so it's almost like once you master composition, you kind of get bored. It's like, I want to do different things. And if you look at something like Finnegan's Wake, for anyone who hasn't read an excerpt, it's almost like to me, I have to read it out loud and I can't force myself to logically understand it. And it's almost like the sequence of dream images that make sense at a layer that I can't quite understand. But it's fascinating. And you could say that Joyce is actually far, or put it this way, he's maybe scoring a 5 out of 5 on imagery or 5 out of 5 on rhyme, but he's doing it in a way that no one has ever done before. And I suppose you could, if you had a big enough data set, you could attempt to categorize all the different ways someone gets a perfect score in imagery. And then you can be like, oh, Joyce is doing something here no one has ever done. I'm not sure if that would be useful because I think the number of people who are doing that level of pioneering, I don't know if they need numbers to quantify it. I really think this system is really focused on composition, and I think quality is this larger thing. And there's multiple reasons why something is high quality composition is one of them. And I feel like once you master it, you then have license to break it and have a low scoring essay because you've earned that. And there can be other reasons why your piece shines. And so this kind of ties into the fact that I am using my tool to host an essay competition coming up September 15th. And we are using the tool to kind of score everybody on composition, but then we also have human readers and some batch of readers. They don't care about composition. They're going to say, is this essay timeless? Is there a singular aura? Is it strange? Right. So these are some of the more intangible degrees of what makes quality. And then we want a guest judge who's a wild card, who doesn't even tell us what their standards are. They're just ranking the essays in order of how it hits them, say, emotionally. And so, yeah, hopefully that articulates that that composition is. Is like kind of just one part of the quality puzzle on what makes something great.

A (19:14)

Yeah, I. As you were talking, I was thinking about, you know, get the basics first. And I think it was Charles Mingus, whose son was studying to be an artist and. And wanted to go right to abstract painting and. And Mingus said, maybe even quoting an artist, something like, hey, man, learn how to paint an apple. That I can understand that it's an apple. After you've mastered that, then go ahead and get as abstract as you want. How would you. Coming back to Christopher Alexander, he has this concept of quality without a name. And how would you deal with a quan to make it an acronym in your architecture, of your software, in your book?

B (19:59)

Yeah. So his system, it covers these 253. So his is 10 times more complex than mine. 253 patterns that you can use from everything from the design of towns, then to buildings and to details. And it's all this hyperlinked maze. So if you're designing a garden, well, then it points you to the 10 other patterns you need to design the garden. And so the design process is this. You know, it's kind of like a sudoku where you're going in and out of different problems and you fix it in one area and then it changes somewhere else. And you can be logical in how you think at these very little isolated parts of your design problem. But then all together, they come together to create this thing that the mind cannot behold. Right. It's almost like sacred. Where you've done your design work, you've pushed the boundaries of how you can think about it, and then there's this emergent thing. And he kind of gets to the point where we can't really name it, we can't describe it, we can't quantify it. It's almost like you can't even aim for it or desire it. It just emerges, I think, when you start to solve all of these design constraints earnestly.

A (21:10)

And now we're kind of talking about a level of writer who. Maybe that's their occupation. They're an essayist, or they have a substack or whatnot. I know from having looked at your software and chatting with you that you can serve that artist very well. But I personally think one of the areas, as we talked about when you were here, where this might really be something that you could. Not only. What's the old joke about missionaries? They went to do good and did well where you could do good and well at the same time. This wasn't my concept in our conversation. This was Jimmy Sony's, my editor in chief at Infinite Books. But it's kind of like, what's the one time in life that everybody is required to write an essay when they're going to college and college doesn't, at least in my review of the discussion, let's call it a discussion that academics, colleges, et cetera, are having with I'm doing air quotes here for our listeners that kind of is fearful of AI in a way like don't let it write for you, blah blah, blah, blah. But your thing doesn't write for them. Essay architecture does not write for them. But it's a really great learning tool. And right now, college admissions, it's not a level playing field. As Jimmy brought up at our lunch. He knows people in Manhattan who are literally paying consultants $1,000 an hour to help their child write an essay that will get them into the ivies or whatever. And I see your tool as something that could level that playing field. If you could get buy in at the college level and not call it AI. But as I mentioned when we were chatting, call it what I think it really is, which is intelligence amplification, you would have a way. It's not an AI detector, but it's also not a ghostwriter. It isn't writing anything for the student. And it would give information to colleges that they simply don't have right now. And that is how did this student progress? Let's say I'm any university in Vermont or whatever state and I say, you know what, I'm going to embrace this. I'm going to use Michael's Essay Architecture. And you have every student use the same template to write their essay and you get to see their progression. Because again, let's emphasize an underline. Essay architecture is not a ghostwriter. It is something that helps the student get better at the craft. And you would get a really high signal score by looking at the delta between what they did originally and then their final essay that they submit with the scores from Essay Architecture. I think it's like a really great idea. What do you think?

B (24:39)

Yeah, there's so much here and I looked it up and I think I read that 25% of the incoming students going to Harvard are using professional admissions consultants and they're spending up to $3,000 for this process. And you could argue that a tool like this, like what I'm building, if I'm trying to build a world class editor that anyone can access for under $10 per essay, right? So a tool like this could suddenly give everybody access to that essay expert to articulate their thoughts at their highest potency. And there's a funny, what's the word? There's a discrepancy where even though I Have a textbook, and it articulates all 27 patterns, and it describes what makes it a 5. If you upload your draft and you say, hey, make it a 5 out of 5, it still can't really write an essay on its own that exceeds a 3.5. So there's some difference in capabilities where even though we can analyze precisely and accurately, we can't yet have a chatbot generate from those same instructions. Like you're saying we could manage, we could draft student progress over time. And it's not writing for them, but it's giving them all the right questions and ideas for them to rewrite the draft at a higher form. And so if you have a student who now is getting past a four, it's very hard to get past a four. Even for me. I struggled to get past a four as creating the system. It takes a lot of deep thinking, synthesis, and time. Right. You just really need to go through multiple drafts on your idea. So the hope is that this tool can develop a quality standard that is a proxy for has the student actually done the thinking? And have they actually worked through all the different challenges of composition?

A (26:26)

Yeah, I think it ensures integrity and encourages improvement. Right. And rather than, you know, hide their heads in the sand, I think that colleges, universities certainly have to come up with a game plan.

B (26:42)

Right.

A (26:43)

When I was a kid, nerd alert. I really wanted a calculator, which were just coming out, the usable ones back in 1970 when I was 10, and I got one for my birthday and I was really excited and I brought it to math class and my professor had seen them, but a lot of the other kids hadn't seen calculators yet. And, like, everybody was like, oh, my God, this is so cool. Then what did the school do about. As they became more popular? Right. As they went down in price, they banned calculators. And I'm kind of like, I've always been. Had a bit of a rebel streak in me. I'm like, what the fuck? Like, you want us to go back to abacus and slide rules? I see that in today's debate about this incredible tool of intelligence amplification, AI. And it's like, it's not going away. Colleges and universities, and to instantly label it as, ooh, that's bad, that harms human creativity. I completely disagree. If used in the context like we're discussing here, Right. It allows you, through technology, to level that playing field because it scales. Right. If universities embraced SA architecture and it became the platform, then you can have comparisons from universities, then you can have oh, what can we learn? And then iterate. It would become kind of a self defining great loop where you're going to learn a lot from the students that are using it because you're going to have a much larger sample size. Also the quality of the writer, right. If, if you're only dealing with people who already are professional substack writers and that's their job, I would assume that their level of composition and all of that is going to be higher than your average 17 or 18 year old who is facing this daunting task. And mom and dad can't afford that thousand dollar an hour consultant. And to me that just doesn't seem fair and right. Like I'm a full believer in free markets and the way they shake out. But if you do have a technology like yours where every student could have access to it, presumably every student is going to learn from it. You're not doing ghost writing, you're not doing any of that. Wow. I mean that seems an auditable thing that universities could be like wow. And it would also allow them to not just hide their heads in the sand. Right. And this idea that they're going to ban every new technology just seems beyond idiotic to me. It's like who was the most distraught when photography became popular? Portrait painters. Right. I just read Morgan Housel. My friend who I call the sage of Seattle just wrote a piece of some of his thoughts. And I didn't know this, but in the late 1800s as cars were first coming on the scene, Washington banned the Washington D.C. because they would impact the employment of horses.

B (30:15)

No way. Yeah.

A (30:17)

Yes, yes way. And you know, you can see it in every innovation. Like ice boxes are called ice boxes because they used to have ice at the top that kept you cool. And it was a huge profession here in New England ice harvesting. People would go into the river and carve out big blocks of ice, haul them to people's homes and deliver the ice. Well then refrigerators came along and guess what wiped out the ice harvesting industry. But all of those people probably found much more enjoyable jobs for the very least. Why do you think that there is this innate hostility toward innovation technology that in my view, and by the way, I'm not naive, I know it can be used in a bad way as well. Right. But it seems to me that the immediate response is always hostile. No, that's going to break us as a species and we can go all the way back to Socrates who said writing is a bad idea. This seems part of our human os. What Are your thoughts?

B (31:29)

Yeah. So I think it's good to break it into two buckets where you have the open market where the best ideas win. And then you have schools which are supposed to kind of like train the citizens to have all the skills needed to live a fulfilled life. And in the open market, AI is never going away. Right. It's just going to get better and better. We have to adapt to that reality. I think what schools are seeing now is that some of that technology is seeping into our schools and now 60% of kids are just automating their homework. And then the teachers are just, you know, using ChatGPT to score it. And it's exposing, I think, the shallowness of accreditation and all the gates of our school system. So the first flash reaction is like, we'll just ban it, get the technology out of the schools. And that's a temporary fix. It's not really going to stop it. So I think the challenge here is we need to think more nuanced about how we think about what is the point of school. I think at the basic level, it should be trying to motivate students to learn. I think it's failing at that in a lot of ways. But I have a story. So I went to University of Miami. I transferred into architecture school and I found out, hey, by the way, we banned technology for the first three years. I was like, what are you guys talking about? You're going to make me hand draw all of the stuff and it's going to take 20 times longer because I can't use AutoCAD or SketchUp. And like, yes, exactly. You're going to learn by drawing those lines. And so this map behind me is something that took me 120 hours. And it's a depiction of Manhattan drawn with only dots. Right. Effectively, this is a job for a printer. A printer should do this. Why am I doing this? So I got pissed and I transferred after one semester and I went to a modern technology school. And when I was there, I realized like, oh, wait a second, because I drew every line on my floor plan, I really understand how architecture works. And now when you give me the technology, it's this exoskeleton around me that lets me amplify all of the hard earned classical skills. I think the problem is if school doesn't teach the slow, hard, boring, ancient fundamentals, there's going to be no intelligence to amplify. And I think there's a way to fix this. And I think it just comes from sports, how you train athletes and so I have one more story where in ninth grade, I did not make the baseball team. I was a water boy. I was devastated. I said, let me get a hitting coach. So I got this guy. He's affiliated with the Yankee minor leagues. Okay, I'm going to learn how to hit. And on the first day, he says, okay, the first drill is you're going to put the bat behind your back. I'm like, what are you talking about? Why would I put the bat back there? He's like, I'm going to pitch to you, and your only job is to watch the ball and pivot your back leg. And he's like, we need to isolate that one skill. And I learned from him that there's these, like, 10 different parts of a baseball swing that you have to isolate part at a time. And, like, none of them involve or a lot of them involve not using the bat. So you're taking away the main tool. Right. But then when you go to actually do it all together in context in the game, all of these little micro movements are just fluent to you. Right? And so how this ties to education is we need to figure out how these two different sandboxes can coexist in one sandbox. We're isolating mini games where you can't use all the technology. I've designed exercises, a whole curriculum of exercises. And one of them would be, okay, you're going to write a paragraph, and you can only use one syllable words, and then do it again. You can only use two syllable words. And again, these aren't trying to produce spirit writing, but they're teaching your mind to think in a certain way. And then we need another sandbox where we say, now we're going to give you all the best tools in the world, and you can take your fundamentals and leverage them. So I think, yeah, I just think education could think along those two lines, like mini games for skill training and then understanding the cutting edge of what's possible.

A (35:34)

Wow, that is a really great answer. Because as I was listening to you, I remember when I wrote the book what Works on Wall street, the data provider gave me an automated tool that would allow me to say, hey, how did the 50 stocks with the lowest PE ratios in 1995 do in the ensuing year? And as I was doing it, I was realizing that really doesn't look right. And so I ended up having to do it all by hand. The tool did not work as advertised. And the doing it by hand, oh, man, I was so grumpy. It was just like I can't believe I'm actually doing this, but, man, it really gave me a foundation for understanding the way data works, the way errors creep in. For years, I was their best error finder in the Compustat database because literally, I had to, like you doing the map of Manhattan, I had to by hand walk the data for every year between 1952 and I was writing this in the early 90s. And the things that I found on the way were really, really cool. And ideas that I'd never had, right? Like, boy, boy, this data is really dirty. In other words, there are a lot of errors. It's error ridden. And if I hadn't had to do that by hand, I would have never known that. So that's a really important concept. How do you think universities could go about the two sandboxes? I like that metaphor as well.

B (37:30)

Yeah. I think the challenge is that these little granular skills that you need to do, brute repetition on, to an untrained mind, it feels like torture. It felt like torture making this. And similarly, if you were to talk to a new writer and I tell them, hey, I actually go and I read essay and I pause in a paragraph and I score it 1 through 5 on 81 dimensions. That could sound like torture to somebody. But for me, that brings me so much joy. Weirdly enough, that's actually where I'm in the pocket at the edge of my thinking. And I think it's because I am an essay writer myself. I'm trying to grow an audience on substack. I understand the value of practice and of writing, and there's a larger story that motivates me, and it makes it worth kind of going through these little drills. So I think two things. I think school needs to figure out how you actually motivate people. This is another discussion we could have, because I think architecture school nailed this. But you need to give students autonomy. There needs to be social stakes, and they need access to resources where they can actually see improvement quick enough. So we need to get, like, the motivational os, right? And I think the second thing is you need to gamify it, right? Like, if you just say, hey, you're just going to go in and you're going to, I don't know, like, just handwrite the same thing a thousand times on a blackboard like that. That. I mean, that is more like a torture than a game. But if you make it a competition where there's a leaderboard and. And some kids win, I think. I mean, synthesis does that, right? Like, you can use the structure of games to get them to inherit the right skills. So I think it's motivations and games.

A (39:13)

I think also part of it is there's a great quote. I think it was Tony De Mello who said, everybody wants progress but nobody wants to change. And I think that fits what's going on right now at the educational level. On the one hand, I think it's hard to argue that say, K12 is prospering. Right, right. And the negative outcomes. I was just reading a piece about a kid who went all the way through college and he's functionally illiterate. He's literally functionally illiterate. So the institutions to a large degree are failing their students. And that doesn't mean I hate the institutions. It means, hey, you've got to reform, you've got to try new things. And that's why I was so excited about this idea that Jimmy Sony had. Because your software is kind of like the perfect place to do it. Because they can overcome their fears that an AI is just writing everything, because that is not what happens with your software. But it also levels the playing field so that the rich kid from Greenwich is operating under the same kid, same circumstances as the kid from wherever, the Bronx. And to me, that's very exciting. Another thing, I mean, as you can tell, I'm very enthusiastic about SA architecture. Another thing that would be really cool is your idea of a contest. But also, what about a tool where you simply ingest through RSS feeds every substack essay, run them through your system that allows you to discover, wow, there is a great essay writer who nobody's ever heard of. And then kind of like a hacker news spot where you elevate and amplify this writer. Hey, you really got to check it out. Like, what a great way to find great new talent. What do you think about that use case?

B (41:32)

Yeah, that is probably what I'm. It's hard to say. I love the vision of education and helping people discover the process of not just learning, but learning through writing. I really think writing is the wedge from which you can become a self driven learner. But the other implication of having a quality standard that's baked into AI is that suddenly we now have the ability to discover where great writing is. And the Internet right now can't do this very well. The only data we've had since 2005 or so, and we have engagement based metrics and all of our algorithms are based on the volume of people who are engaging with something. And so I think it amplifies a certain kind of content and it's not necessarily the best written or the most visionary stuff. And I think AI is going to make this even harder, both because generation and engagement hacking can be done at scale. And we will need effectively a quality rhythm to. Sorry, a quality algorithm to find the essays that are worth reading. Yeah. And I think there's value to doing this in real time. I would love to have a newsletter where every week it's like, hey, we've read 100,000 essays this week, but you've got to read these three. So that's kind of one angle. And then I think there's something to this big annual essay contest. There's a long history of essay competitions and they still exist in modern time, but I think they're much narrower in their focus. Like you have literary magazines and they have the Best American Essays anthologies. And I'm just asking the question, like, how would Mr. Beast run an essay prize today? Because this whole thing is he gives away huge sums of money and he creates these attention games. And could you use that same mechanic to rebrand the essay? Almost like a Trojan horse. Right. It's this. It's this thing that everyone has a certain perception of and can it actually be fun and gamified? And I think the difference with this is if you are someone who has this tool and you're in this competition, you're most likely not going to win. Right. If there's thousands of entrance and one winner. But every loser now gets this essay on an important idea to the edge of their ability, and they still have full ownership of that idea and they can publish it and themselves. So a lot of these, like, literary compositions, they really try and like, own the submissions. And I think in the spirit of the Internet, you want to let people, you want to lean into self publishing. And I think you could really build the community around this kind of like prize quality, standard. There's even like a textbook that comes with it. So that's kind of my question. Like, what does it look like to build a modern kind of like writing institution, both to teach writing and to celebrate the best works that are coming out of it?

A (44:37)

Yeah. As you know, I've written all of my adult life. I have, you know, more than 45 journals sitting around me here. And writing is. I. I could not agree with you more. Writing is maybe the most important aspect of learning kind of what you think. Right. We all have a bunch of ideas jumbled up in our heads. And oftentimes people will say, ah, I think that's a great idea. And of course, that's happened to me many, many times. I've had lots of crap ideas, but the way I discovered they were crap ideas was I tried to write about them. And as I was writing, I was like, you know, the, the gif where the guy is like, he's starting to write and then he goes, I got nothing. And unless you take that transfer from your head to pen and paper or your keyboard, I happen to believe pen and paper is even better. And apparently there are some studies that show that that is true. We won't devolve into that right now.

B (45:49)

But I believe it.

A (45:50)

Yeah, you're absolutely right about just the value of writing. To improve your thinking, to improve your communication, to improve. Like, there's just so many aspects of it where it just really sits at the center of everything. And so I am certainly not one to advocate just having the AI do everything for you. I think that's going to lead to the tsunami of sloth. But that makes me super interested in apps and structures like yours, because I think what's going to be big and something we'll be building at o' Shaughnessy Ventures is we're going to need curation apps for people who are just like.

B (46:38)

Oh.

A (46:41)

I don't have the time to read 100,000 essays, but I would like to read really good ones.

B (46:49)

Right? Show me the best one and then give me summaries of the other ones that I might want to read after.

A (46:55)

Exactly. And I think that the more you zero in on ways to do that in your case, this is a way to rise the best essays to the top. But we also are big believers in what I call what is generally called the Senator model of how to use AI. That means man, woman plus machine, not machine alone, not personal loan. It's like the quip that AI isn't going to take your job. A human being using AI is going to take your job. And so I think that, listen, I've been lucky enough to see tons of innovations in my life, but I think this is right up there with Gutenberg. I think that the. Especially the intelligence amplification reframe of it. I agree with you, by the way, that you got to get the basics, and schools should be trying to focus on that as well. But I definitely see a cognitive chasm opening up between people who are using these intelligence amplification tools and people who are not. And so I like your idea very much. That at the student level, make it fun, right? Like, if you look at almost all of human history, basically. And by the way, not just humans, animus, most of them learn through play, right? And you know, we're highly mimetic creatures, but that can lead to downsides. But it's really good for learning and, but if you, if you make it fun, you're going to get, I think, much better results. I think one of the big mistakes we made was borrowing the Prussian educational system. It was fine pretty much when they did that, but they left it. Right. It didn't evolve. And there are some theories that really the reason we have public schools the way we have them is because during the Gilded Age, when everything was becoming industrialized, the industrialists said to the politicians, yeah, we want not people who can sit calmly in a room for eight hours doing what we tell them to do. And the fact that we are still kind of doing that to our hasn't changed much. To me, that's insane. It's absolutely insane. Because the time of life in childhood when you should be full of wonder and full of the desire to explore and learn and play is being almost beaten out in the current system. It's like I saw somebody who said, what group in society has even fewer rights than prisoners? And the answer was schoolchildren. That's just awful.

B (50:17)

And it's so normal. It's just the thing you have to do. And, and I think this whole homework apocalypse is hopefully a blessing because it's making us realize that we've been stuck in this old system for 200 years. There's an essay by Paul Graham called Towards a Golden Age of the Essay. I think he wrote it in 2004.

A (50:40)

I've read it and it's good.

B (50:41)

Yeah. And he noted that the five paragraph essay came from, from medieval law schools. So in the medieval times, it wasn't just seminaries, it was mostly law schools. And so that's why the five paragraph essay reads like a legal defense in this essay. I will argue this, right? And so to tie this to your framework of the thinker and the prover, our whole method of essay writing, which should be the tool to unlock curiosity, is now basically lawyer training. Right? From sixth grade on, it's like it's completely backwards. And so I think this came to the US in the 1830s, 1840s. First compulsory school was Massachusetts in 1850. And even Emerson was like, guys, what are we doing? Out of 10 years out of the gate you have Emerson saying, this is ridiculous. What are we doing? And he says, every student needs to be inspired to a lifelong process of learning. And they need private tutors. Right. It's like he had the vision, but it was ultimately so impractical. Right. In 1850, they were just desperate to get anybody in the room to look after these 30 kids. Right. And so it's much easier just to teach a formulaic five paragraph legal essay than to like sit one on one with each kid and be like, okay, here's Montaigne. Here's how you actually question authority. And there's been no solution on how do you actually equip each student with what they need to learn to write. And arguably AI is that moment we finally have the technology to realize Emerson's vision of education. And it's like there's this very urgent moment where like you're saying there could be a radical gap in those who know how to think and use AI and those who don't know how to do either. But it within this decade, we have the tools to suddenly teach essay writing as basically the wedge for someone to start actually caring about learning. And it's just amazing to me how much I love essays now. I completely hated writing in high school because it was all these legal defenses and it's the prover, it's not the thinker. And it wasn't until much later, when I'm writing to make sense of my own ideas, that I really love the process.

A (53:01)

Yeah. And just to get off the soapbox, but with one last blast. Clearly we have a system that kills as opposed to encourages, that love of learning, that exploration. And Robert Anton Wilson was talking about his time in Catholic schools in the 1930s and 40s. And he said, it seemed to me that their only real objective was to install the only one correct answer machine in my brain. And that doesn't lead to people being really excited about self learning and self direction. But certainly in my own case, almost everything I've learned, it was not in the schoolhouse. It was because I was curious and went down that path. Another idea though is like nobody, because maybe because of that five paragraph legal. I mean, who wants to read that? I mean, nobody. Let's talk a little bit about some great essays. You've done a list with showing the greatest essays you scored. And I'm going to lead in with the question of the top 10, why does David Foster Wallace take three of those top 10 slots?

B (54:26)

Yeah, he has three of the top 10. He also has some essays that are in the seven out of 10 and not high nines. So he has variability. And I also find that he has two versions of a lot of his essays. He has one in his essay book where he basically didn't have an editor. He could throw in all the tangents he wants and then the public version that had to go to a magazine. And I've tried scoring both. And the ones that have editors working with him do score higher because it's more like we're trying to compress the insight versus see every nuance of his mind. But I just get the sense that he just had this intuitive grasp of that pattern language. His essays just push the boundary on every single dimension. If you read that book, consider the Lobster. It's just like a perfect example of what a microcosm is, where he could have written a treatise on animal ethics and would have been very boring and comprehensive. But instead he brings you to him at a specific lobster festival with his parents and girlfriends and the chaos around him. And it's fun and psychedelic and weird, and then he gets into all of these philosophical dimensions. So it seems like every essay in that book because he has a whole book called Considered a Lobster, every single one is like a masterclass in how you can pull off a microcosm.

A (55:46)

Which is another reason I'm excited about SA Architecture, is you provide a path for people to understand how they, with their passions and their particular interests can do the same kind of thing, right? They can learn through continual repetition of. Of interaction with SA Architecture. Oh, wow. Wow. I'm getting a super low score over here, but I love that maybe I. Maybe I need to put that back in. And as someone who's written four and is currently writing a fifth book, they would be just pure shit if they didn't have editors. I was very lucky because my wife graduated summa cum laude in journalism and had the reddest of red pens. And I was first really angry when I would write something and it would come back with just a sea of red all over it. But as I got over myself and I realized, wow, she's right. And so I just. On the fly. That's another great use case for how AI can be helpful, right? Not everybody's going to be lucky like me and be married to someone who graduated summa cum laude in journalism. The editorial function of AI Again, let's underline not the ghost writing aspect of AI but the editorial aspect has great promise. As a matter of fact, at Infinite Books, we have a thing we call the portal, which we put manuscripts in and it ranks it across many different categories. And then our human editors look at it and fine tune it, right? Like, ooh, got this One wrong. You know, Dylan thinks that this is a masterpiece. Let's train it on why that is so. Another important reason, from my point of view, why you want the cenotar model, the human plus the AI, but then the quant in me is basically one of the reasons I became a quant was because precision quantitative models work, not because they're these incredibly complex things, but because they are uniformly applied every single time. And when that is the case, guess what? Their batting average, on balance, in other words, on all of the forecasts or decisions they made, tends to be higher than the batting average of a human. Right. Because. And by the way, this is true not just for investing. There's a great book written back in the 70s, the limits of Scientific Reasoning, I think is the name where he looks at literally. I think the author's name is David Faust, but literally it's everywhere. He looked at what I would call quantitative models, others call algorithms or whatever. And a huge variety of tasks, right? Horse handicappers, handicapping a horse race, admissions councils at universities, deciding whether somebody gets in or not, doctors making diagnoses, et cetera. They were all outperformed. They thought that these quantitative models would be a floor in which the human would soar above. They proved to be a ceiling that the humans very rarely touched. But the thing that I found in there was there was a persistent group of subset of humans, exactly. Who were like, amazing. And then. So what I did when I was developing all of the investment algorithms was incorporate those incredible human insights as best I could in the model. So I wonder, you've said quality is statistical. And a lot of people, we have this math anxiety that the minute you bring in statistics or whatever, it's like, no, no, I'm like, no, it's not. And we get violent reactions if you say things like that. But it's objectively fairly true. Right. You're getting, I think, correct me if I'm wrong, 99% precision on the various essays. And I think the closest human is at around 73%. That is not to say we should not use humans. Let me be very clear and underline that. I love your wild card idea, by the way, for your judge.

B (60:40)

Nice.

A (60:40)

And I think it's this combination that will lead to a lot of the things we've been discussing. What are your thoughts? Is this going to be a slow slog? Is everyone just going to keep burying their head in the sand and saying, no, no, no, no, no, and let's go back to calculators, right? So there was this period Calculators were new. They didn't get banned yet. Then they got banned. Then we had this, this stub period where I was trying to figure out how to use a slide rule. And then of course, like, literally, now they're in every classroom. They're required in. In many math classes. You see a similar adoption curve here.

B (61:27)

I think this decade historically could be remembered as one of extreme, like, existential anxiety for writers. I think it's very natural that people are pushing back against AI. Some people will just always have a blanket, no AI stance. And I think that could change over time. My hope is that by saying, hey, this tool is not going to write for you, that signals that this is a tool that is for the earnest writer. We're not using statistics to replace writing. And it is not the only thing that leads to great work, but it is the thing that could identify your weak spots and help you improve so you can articulate your ideas better. The reason that I think this has to be statistical is because we need some sort of objective way to kind of. The AI needs a framework on what makes something good, because even though it has seen trillions of words, it has seen all of the great works, it doesn't have a model of what makes any of them good unless that is written. And so the goal is to kind of take words and then turn it into math, right? And so this system is very much thinking in terms of numbers. And I'm there watching how it thinks. And at first my model is like, very off, right? I had these 27 prompts. It was like, oh, it's not working at all. And so I find all the nuances, then I make it more complex. And I said, okay, now it's using 121 prompts, and it's like, slightly better. But the whole thing is you translate words into math, but then you can't just give the writers a bunch of statistics. That's not useful for them. You have to make human readable, compressed summaries online. And it has to be fun and motivating too. So you have to turn it into feedback too. And then I kind of realized, like, oh, I got all the math right, but it's like, the feedback's not great, so we have to keep changing the model. And so now I'm at a point where for every draft you upload, it runs between 1 and 5,000 evaluations on your draft. And I have the systems to evaluate and see the specific line level feedback it's giving you. And the way I see it is Writers love to romanticize writing. They never romanticize writing. Writers hate editing. It's like one of the most people construct elaborate worldviews. I'm like, I mean, think of Jack Kerouac, first thought, best thought, like, editing the devil. Like, people will come up with any excuse to avoid it. And the hope is that, hey, we can actually use math to have a very stable and simple way to help you understand how to edit. And the difference between my tool and a tool like Grammarly is that it's not just giving, like, little line edits, like, oh, fix the tense of this verb. It's trying to give you the big picture sense of how you want to improve the composition of this piece. And that often involves doing a complete rewrite. So the last piece I published, it went through seven complete reader writes from scratch. And I think writers avoid that even more because there's the sunk cost fallacy. It's like, well, I worked so hard on this draft. Why would I start from scratch? But in my mind, when you rewrite, that is really when you push the edge of how you think about an idea. If you're just writing a first draft and you're doing little line edits, you're not actually thinking. Because in my mind, writing is the process to reveal the thoughts that are in your head so you can see what you think, but you can't necessarily change what you think unless you edit it. And so it's through editing that you change how you think. I love the quote by, I think S. Kelly Harrell, which is that editing is not rewiring words, it's rewiring synapses, which is exactly what this whole essay process is supposed to do. So it's like, hey, you know, let's. Let's try. Try using math to help lead to this very transformational benefit of. Of editing that everyone is already avoiding.

A (65:26)

Yeah, I certainly. I am not one of those writers having written four books that. That, you know, romanticizes writing. I love the Dorothy Parker quote. I hate writing. I love having written.

B (65:43)

Yeah.

A (65:44)

And that was kind of me. It's like. But.

B (65:50)

But it's a workout.

A (65:51)

Yeah, it is a workout. But listen, I owe most of my successes in my career to writing to. To books. And so I personally have definitely seen the power that writing can unlock. And one of the things I'm experimenting now with is I'll write a first draft of something and then reread it. I always read it aloud. That's a trick, I'm sure, you know.

B (66:20)

Yeah, definitely.

A (66:21)

And like, if it doesn't sound right to my ear. I'll rewrite it, et cetera. But then I'll. We have our own AI lab at Oshana Subesh's, and I'll put it in there and I'll give specific instructions to be like, hey, look into the liminal spaces here which we humans have a really hard time making those connections. Right. And tell me what you see. Right. Just as feedback. And I gotta tell you, sometimes I have been like, my jaw drops open, like, oh, my God, I certainly didn't think of that. And then that kind of leads to the next jumping off point from what it had surfaced as a good editor and contributor would be able to do. I also completely agree with your idea. Again, back to Mark Twain. Right? The difference between the okay word and the perfect word is the difference between lightning and lightning bug.

B (67:25)

Yes.

A (67:28)

Yep. And the other thing that I love to read as well, and I think, look, we're not going to re engineer human beings here, but I think what we can do, especially with systems like yours, is at least give them a chance to have a fun way to get it. I don't know about you, but a lot of my friends back in the dark ages when we were. We didn't have writing coaches. We only took the SAT once. We didn't have any study guides, and we only wrote that goddamn essay once. Some of us were lucky enough to have friends or parents or family members who would take a look at it and rework it a little bit. But I remember, at least it was kind of like universal Eid. I remember when we were all writing our college essays, my classmates were all like, ah. And I was the editor of the school newspaper. So everybody came to me, will you read this essay? I'm like, you were the guy. But I did read a few of them. And like, it did strike me even back then. I just wonder. There's a theory that has been developed that we've got the software pre installed in our brains for learning how to talk. Right? You take any child of any nationality or ethnic origin and drop them in a place. Guess what? Even if you borrow a child from Japan and move them to Queens, they're going to be speaking unaccented English by the time they're five, Right?

B (69:09)

Right.

A (69:10)

And vice versa. If you take a child born in Queens and move them to Japan and at birth, right. Five years later, they're going to be very fluent without an accent in Japanese. Some of the theories that I've read said that writing, on the other hand, very, very different because we developed it much later. And it's one of the reasons why learning how to write takes a lot longer than just the natural ability to use your pre installed software in your brain to pick up language. And in fact, I think it's the book the Weirdest People in the World that calls out that if you take brain images of highly literate person versus illiterate people, the shape of the brains of the highly literate people are different than the shape of the brains of illiterate people. And what they contend in the book, the Weirdest People in the World is that that happened because the ability for us to learn how to write colonized a different part of the brain. If memory serves me, it was the one for visual acuity, which. Which were obviously pretty important to our hunter gatherer forefathers.

B (70:34)

That's like edge detection, right?

A (70:35)

Yeah. But do you think that that might be like one of the lasting remnants why people are just like, not. Not just naturally drawn to. Man, I gotta be a good writer. That's. That's gonna be so helpful in everything I do in my life.

B (70:55)

What do you think? That's a great question. And I'm of two minds on it because I really think that if you want to learn to compose better, whether it's your idea, form or voice, one of the best things you can do is just read great essays.

A (71:10)

Yes.

B (71:11)

So part of this project is, well, I now have a list. You can read these top 10 essays and you'll become a better writer just through osmosis. And it's a similar thing where. What's the story Hunter S. Thompson rewrote? Was it Hemingway? Like word for word?

A (71:25)

He rewrote Hemingway word for. By the way, I was doing a little research and it wasn't just Thompson. Many writers made a claim not for Hemingway, but from taking a writer that they absolutely adored and literally writing it out or typing it out.

B (71:41)

Yeah, but is that where copywriting the phrase comes from? Like you were actually copying? Even though it's known today as advertising, I think they were actually copying advertisements to know how they worked. I'm not sure. But the other side of that. Right, so one angle is, oh, writing can be learned through osmosis. But I think there's a similar to just spoken conversational language. But part of me believes that writing has to be studied to be mastered. Right. And it's like a lot of writers default say, hey, just trust your intuition. Right. The answers are inside of you. And I kind of think that's BS and most people just have bad Intuition, right? Especially when it comes to writing. That's why we all use cliches. That's what it means to follow your intuition. And it's through very conscious and deliberate practice in studying the different elements of writing. Through doing that over and over, you eventually internalize it where you. Then you've trained your intuition, right? Like the end goal of essay architecture is to write through stream of consciousness. You forget all the rules, then it just comes out without you thinking. But there has to be this intermediate process in how you actually become aware of these tools. And so basically, for example, the concept of modularity and structure, most people are unconsciously incompetent about that. They don't even know that it exists. And so now through SEO architecture, it's like, oh, well, I know it, but I. No way I can do that. And then through slowly editing, you can gain competence, and then eventually you forget it. With enough reps, you internalize it. And I get the sense that one of the reasons writing has never clicked is we've never actually built a formal system that maps out all of the compositional rules that we want to practice and then. And then forget.

A (73:23)

Wow, that's very insightful. And I, and I agree with you. I'm a huge fan of what I call imbued or saturated intuition, which is quite simply like in my old job of asset management, I. I got to a point where I had seen the same pattern so many times in markets that I just intuitively knew what was coming right now. I tried to keep myself honest by anytime I would get an intuition, I still do it to this day. If I get an intuition about something, I always immediately put it in an apple note so that I can see my real batting average. You know, the people who are always like, my gut is always right. No, no, it's not.

B (74:10)

Kevin wrote down all the bad ideas.

A (74:12)

Yeah, yeah. No, it's not. You think that and then you convince yourself of that. And as you mentioned about the chat bots, right? Confirmation bias is kind of the king of the biases, right? Like, of course people are going to love the chatbot that says, wow, what a great idea. In terms of the recent south park about one of the characters always putting his business ideas into a syncopantish chatbot. Like, what about turning bacon into salads? Wow, that's great. And so one of the other tricks that I have found is very useful in our AI lab is, I will say, it is your job to act as the most highly literate but vicious literary critic. Take this chapter apart Piece by piece. And guess what? They follow instructions. Like, I had a chapter for the book I'm writing now, which is a fiction book, which is very new for me, that I really loved, quite frankly. And then I put it into our AI editor and made it that explicit instruction, you are embodying the most literate, but the cruelest and meanest and vicious critic. Do your worst. And oh, my God, like, did. But it was great because I'm like, you know what? I hadn't thought about that because I'd gotten so in love. I'd gotten so in love with the way I was reading it, that my confirmation bias was excluding all of those after I read it's vicious attack on me.

B (76:05)

Yeah, it's like a kill your darlings GPT.

A (76:08)

Yeah, totally. Exactly. And that's one of our watchwords at Infinite Books and has been a watchword in my life. My wife was the first to say it to me. You've got to kill your darlings. And I was very reluctant to at first.

B (76:24)

Sure, yeah. Sometimes I've done that before, and I'll say, do it in the style of Hunter. As Thompson. Be really funny and make me feel bad about it. And when it goes that over the top, it's almost more palatable because, you know, it's like a joke, but then it's like it incepts the idea. And it's like, oh, he's actually kind of right when he puts it that way. And it kind of shows me that these chatbots aren't inherently sycophantic. That's actually part of the programming and the product system prompt that they put into it. And I think it's funny because I see this whole. I mean, this is a 2025 issue of these chatbots are just so overly validating. And that's never happened to me. And I didn't get it. I'm like, what's going on? And it's because if you have a system in one system prompt, you can prevent that whole effect. And what I have in mind is it says before every answer, state your assumptions, so I know what you're basing this off of. And then at the end, tell me where I might be wrong. Give me the exact opposite perspective so I can at least consider that. And that's very different from the current system prompt because now it ends every response with saying, well, do you want to know more? It's just trying to beat you into endless conversation. Right.

A (77:40)

And I love that you do that. Another habit I've gotten into is Whenever I read something that I'm just sort of naturally in favor of, Right. I will now dump it into our AI lab and ask multiple large language models to make a steel man argument against the subject. And wow, is that ever good. And it just reminds me endlessly that we are kind of slaves to our own internal assumptions and our own internal preferences. And you know, it, it, it devolves at scale into these us versus them tribalism that we see, which is not great for society, in my opinion. And yet you see that when you see it yourself. You're like, okay, I get it. I get like the fact that this is a natural inclination if you're a human being. I don't remember. Do you have anything in your system that. Yeah, okay, tell me about that.

B (78:52)

So that's the argument pattern and there's a few different criteria, but I think the worst kind of essay is when it starts by saying, here's what I believe and anyone who disagrees is an idiot. And then there's just like you spend 2,000 words just like unhashing this, like this stubborn belief. And the best essays actually open with a question where it says, huh, I'm typically on this side, but this extreme opposite point of view actually has some validity to it. And then the whole essay is about exploring the tensions. And this is like basic dialectics. You have your thesis and you have your antithesis, and by the end you arrive at some nuanced synthesis.

A (79:32)

Yeah, good old Kant for the win.

B (79:35)

Right?

A (79:35)

So tell us a little bit about the essay competition. I know that we Ushana's the Adventures and you are chatting about some other use cases, but the essay competition sounds fun. Tell our listeners viewers about that.

B (79:51)

Yeah, so the inaugural competition for SA architecture, it starts September 15th and will run I think like six weeks through the end of October. And it is a way to both try the tool and to see how far you can push this like, recursive feedback loop. And one of the things that inspired me is to make this an open essay prize. So there are all sorts of essay prizes. There's a $25,000 essay prize if you're a college student who will write an Ayn Rand book report. Right. Or you can get a $50,000 essay prize if you are a consciousness researcher from a particular university. So we have all of these like hyper specialized, high value essay prizes in terms of open prizes. And in my mind, open is something that is not restricted to Canadians. Right. Anybody can submit and the prompt enables any writer to enter. The highest prize is $5,000. And so the idea here is for $10,000, this is the world's biggest open essay prize. And the prompt for the competition is simply the year. So it's 2025. Write an essay about a personal experience of yours that is microcosmic of something that unfolded in this year. And so the goal is, if you have a thousand people trying to write a world class essay on this theme, the best 10 or 20 essays, you'll have a great anthology of sharp thinkers with highly refined essays to help us make sense of the weird times that we're always in. Right. And so I love the idea of closing the year and saying, okay, great, we've got all the best essayists and here are just different meditations on what's happening.

A (81:35)

Very cool. And you say the top prize is 5,000.

B (81:39)

$10,000.

A (81:40)

$10,000. And then are there prizes beneath that?

B (81:44)

Still working out the sub prizes. There could be a world in which if we publish the book through meta label, there could be some sort of royalty share between all of the finalists. So there's different models still working that out. And in terms of the judges, so the idea is to have, I think we mentioned this, but human readers and also a guest judge. So in the end it's not just AI doing the scoring. You want to write an essay that is going to appeal to a human. There's no way to cheat the system just through coming up with some prompt injection, which I'm building defenses against. But just sharing that, that this is like who can put in the earnest effort to write a great essay.

A (82:19)

Yeah. And it's a great way to highlight up and coming authors.

B (82:23)

Exactly.

A (82:24)

That's one of the things that I'm most excited about. Not just the connectivity of the Internet, but also the ability of AI to surface talents that like in earlier eras, just like nobody would have ever heard of. Right. Because of where they lived, because of their circumstances, because of a host of reasons why they just lived in their little village. So I think it's a great idea and obviously one that we will support enthusiastically from our various divisions at Otronicy Ventures. What's next? What's next for you? What do you, you just want to keep improving SA architecture or do you have something new and different planned?

B (83:19)

I think right now, SA architecture, it's just like I have all of the prototype versions of a platform. Right. Like there's a curriculum, there's data, there's a tool, and then there's media. And so I think just focusing on this project lasts me many years. I feel like I'm just starting this thing simultaneously. I'm expecting a daughter end of this year, so that's going to be another project to work on. And I have this idea, and this is again, another tangential idea related to writing, but it's an idea to redesign the dictionary. It's really more of a thesaurus, but it's trying to give a new architecture to our language. And so the problem with the thesaurus in my mind is that, you know, it gives you a whole cloud of synonyms, but it doesn't actually give you a very concise definition on why you would use one synonym over another. You know, when do you use elated versus jubilant? Right? Like, they're like. That's useful to know. Otherwise you're just bullshitting and throwing in random words from your synonym checker. And so I think that's one dimension. But I think the way to organize a language is to figure out what might be 500 core synonym antonym pairs. So, for example, you have happy, sad, rich, poor, tired, energetic. What are the core synonym anthem pairs? And then what are all of the synonyms below them with their corresponding unique qualifier? And my theory is that if you built out a thesaurus dictionary in this way, it would be much easier to advance your vocabulary. Right? Because there's all these studies where if you just throw a human in a swarm of complexity, they retain almost nothing, whereas if you package it with an architecture, they can actually not just retain it, but leverage what they've learned. And I think the same applies to vocabulary and my thesis. And this ties into having a kid, like, I have five years. Can I build a new thesaurus that can help kids understand the nuances of a language? Where someone who's graduating high school, instead of being illiterate with only a 15,000 vocabulary, might they be able to know 60,000 words just because we have a better design dictionary? In my mind, you have essay architecture. And then there's another crazy project that goes down to the word and. And then there's another project that goes up to the scale of ideas. So I just have one more project. Again, this will take 10, 20 years to unfold, but it's like trying to actually map out the core archetype, archetypal ideas that have occurred through history and trying to say, like, oh, maybe there are actually like a hundred lineages and we should understand how from ancient times to modern times, the same idea has been evolved. But, yeah, I think, like, once you have that full stack, it's like you're giving someone mastery of composition, of. Of diction and of philosophy and like, that is almost like a core sense of what it takes to be educated.

A (86:19)

I love that idea. When you flesh it out more, definitely share it with me because I think that's, that's really. You might be the Dr. Samuel. Samuel Johnson of the 21st century.

B (86:32)

Right. NSI writer made a dictionary.

A (86:38)

Well, Michael, this has been really, really fun. We are very, as you know, enthusiastic about what you're building. We think it's turned out super well. We think there are multiple use cases for it and it's a very robust and powerful tool for learning, which we find really interesting in terms of, you know, it's not going to do it for you, but it's going to help you learn how to become a better writer, which will, in my opinion, obviously unbiased, will impact many, many other areas of your life positively. As you know, at the end of each episode, we make you the emperor of the world.

B (87:25)

I've been waiting for this to be emperor.

A (87:28)

Well, it's not going to be a really fun gig, Michael, because you can't kill anybody and you can't put anybody in a re education camp. But what you can do is we're going to hand you a magical microphone and you can say two things into it that will incept the entire population of Earth, all 8 billion plus humans. The next morning, they're going to wake up and they're going to say, I just had two of the best ideas, and unlike all the other times where I didn't follow through on them, I'm going to actually act on these two. What are you going to incept in the world's population?

B (88:09)

All right, so I think I'm going to do one writing related one and one not writing related two. Okay, so the first one is like a pretty practical challenge, and it would be for tomorrow to write down 100 of your thoughts. It's an experiment that I've done a lot. I don't do it every day. That'd be crazy. But I probably do write 10 thoughts, passing thoughts per day. But 100 is pretty remarkable because if you do it for eight hours, that's basically a thought every five minutes. And my argument is that that could be the best form of journaling, right? To actually see, to use writing to see what's in your head. I know morning pages are very popular, but usually it's like, oh, I'm going to create this separate space in my life where I get all my feelings out and then it's disconnected from what I'm actually doing. But if you have an output log of what you're doing every five minutes and what you're thinking, you have the ability to actually see the patterns in your thinking and improve from that. You have material for essays, you have the training corpus for an AI. And when you just watch yourself think, it's like a new lens to reality. So many people are like, oh, I'd love to write, but I don't have ideas. And it's like, oh, no, no, your head is filled with ideas. You're not paying attention. So that's the challenge, right? A hundred thoughts tomorrow.

A (89:23)

I love that one. I'm going to do it. Awesome. What's number two?

B (89:28)

Okay, number two, this is a little more abstract and I wanted to make it about the human os. If I can make one contribution to add to the human OS or to augment it, it would be to become a master of conditional logic around your own identity. And what that means to me. Conditional logic, if you've ever written software, it's just a very basic if then statement. I think everybody knows what that is. But when it comes to our identity, I think we tend to think very insingular things like, oh, I'm a New York Mets fan or I belong to this religion or to, to this political party. But conditional logic says I'm not just going to bulk subscribe to all of the different tenets of this identity. I'm going to pick them apart and say, well, in some conditions I do this, and in some conditions I'm not about this at all. And I just think we avoid that style of thinking because of fear of complexity, of being illegible. No one gets you. Fear of just ambiguity. We hate uncertainty. But if you really take conditional logic seriously, it's like the kernel of, of cognitive liberty. You're actually thinking for yourself. You're not just part of something you absorbed. And yeah, conditional logic. And I think that to bring it full circle, that's what the essay is about, right? You have some tension and you get into the nuances and you get some new lens to the world, that it's complex, but it's distilled and made simple so you can just live through it.

A (91:00)

Wow, I love both of those. I'm a huge fan of conditional logic. When thinking about myself, I've never really understood our just basic almost at our base code, this need for certainty, the illusion of control. Because that's what it is. It's an illusion. I always laugh when people are talking about, oh, Those large language models always hallucinate, hey, guess who was the original confabulators and hallucinators? We human beings. And so the idea, I personally think that certainty is a kind of death. Because, like, you know, okay, I'll give you. I'm fairly certain. I'm 99% certain that the sun's going to come up tomorrow. And like, so for the 1% error factor, I'll never know if it doesn't give up tomorrow. But people apply the certainty way, way too much. And I think that it shrinks their life because it closes them off to many, many things that they might really, really enjoy or really, really grow or whatever. Have fun, all of it. Absolute certainty is absurd in my opinion. I often say one of the greatest challenges is we are deterministic thinkers living in a probabilistic world, and hilarity or tragedy often ensue. And the more you can change your thinking, like you've suggested for your second inception, through making it a little more conditional, you're gonna. I think you're gonna find, wow, there's a whole other world out there that I now have access to. Michael, this has been. Yep. You had.

B (93:06)

If I could just add one quick thing is that I think it's almost inefficient. It would be inefficient to run through a whole experiment if the sun's gonna come up tomorrow. Right. When you. When you think like that, you're. You're effectively doing the proofs on your own from scratch. You're re deriving Christianity or whatever it is, and it's very inefficient. But in the end, by doing it, this is the whole thing where, why it's worth doing things manually. When you actually think through it, it becomes more efficient because you now have an upgraded lens that colors everything. So in the end, it is worth it.

A (93:36)

Totally, totally agree. Where can everyone find you? Michael, I know you have a substack.

B (93:41)

Yeah. So it's Michaeldean site for my substack and sarchitecture.com if you want to read the book, try the tool or enter the competition.

A (93:50)

We are huge fans. We will do everything we can to amplify it. So you get a lot of submissions to the competition. Thanks so much. This was super fun.

B (93:59)

Yeah, this was great, Jim.

A (94:01)

Cheers.

B (94:02)

Bye. Sa.