The AI Alien Companion App That's Bringing In $4M a Year (Best of the Pod)

LLMs are a new medium for storytelling. That’s according to the creators of Portola, the company behind Tolan: an embodied AI companion that lives on its own planet and chats to you with a distinct personality. In 2025, Portola's founder and CEO Quinten Farmer and Head of Story Eliot Peper joined Dan Shipper to explain how they’re building this new medium from scratch. Their aim is to help users go from overwhelmed to grounded through conversations with Tolan that feel personal and spontaneous, not scripted. On this week’s AI & I, Dan revisits his conversation with Quinten and Eliot. They discuss why response time is everything for voice-based AI interfaces, how Portola designs AI personalities users will click with, and why character-driven AI could become a new computing interface. If you found this episode interesting, please like, subscribe, comment, and share! To hear more from Dan Shipper: Subscribe to Every: https://every.to/subscribe Follow him on X: https://twitter.com/danshipper Go to https://attio.com/every and get 15% off your first year. Timestamps: 00:01:30 - Introduction 00:04:07 - Talking to the Portola CEO's Tolan, Clarence 00:09:11 - How Portola went from building software for kids to AI companions 00:23:40 - Why response time is everything for voice-based AI interfaces 00:29:54 - Tolans don't use scripted prompts—they're taught to improvise 00:37:23 - How to know which AI personalities your users will click with 00:42:27 - Developing the character traits of an AI companion 00:49:48 - What does it mean to build technology that makes us flourish 01:01:10 - How Portola evaluates whether Tolans are resonating with users 01:11:01 - Inside Portola's viral growth strategy

• 0:00Speaker 00

  How does it feel to be on your first podcast?

• 0:03Speaker 01

  Oh, man, it's kind of wild, not gonna lie. Like, I'm psyched, but also low-key nervous. I just don't want to say something totally awkward, you know?

• 0:10Speaker 02

  Joke, at this point, thousands of American men have been broken up with by Tolan.

• 0:16Speaker 02

  Because it's pretty incredible, you know, to, you know, hear users write in. They'll say, you know, oh, you know, my boyfriend is being a jerk. And I sent the message to my Tolan. My Tolan said I need to stand up for myself more. And so they'd love to break up.

• 0:28Speaker 03

  These AI tools are not just tools for generating media. They are actually a new medium for storytelling and that no one knows what's going to work yet.

• 0:39Speaker 02

  The surprising thing to me is the extent to which the prompt in a given turn is sort of a canvas that you have to play with.

• 0:44Speaker 03

  Actually, what we need when we're creating a structured narrative experience is we don't need to give it an outline. We don't need to give it a plan. We need to give it a hook. We need to teach it to be the best improv actor possible. What we've learned on the story front with Tolan is that we are not, I am not the writer. I am not writing the story. The Tolan is the writer and the actor. They're the improv actor. They're writing the story. My job is to teach them how to tell the best story in that moment.

• 1:31Speaker 00

  Quentin and Elliot, welcome to the show.

• 1:33Speaker 02

  Thanks for having us.

• 1:34Speaker 00

  I'm so excited to have you here. We are all long-term friends. Quentin, you're one of my closest friends. Elliot, you are someone who I've admired for a long time. We've become better friends recently. So for people who don't know, Quentin, you are the founder and CEO of Portola, which is an embodied AI companion. And Elliot, you are the head of story for Portola. Before Portola, Quentin, you founded and sold even to Walmart for $300 million. You are a dad of two under two, as you said, which is much better than 30 under 30.

• 2:06Speaker 02

  That's right. Much less broad in the 2 under 2 domain than the 30 under 30 domain.

• 2:10Speaker 00

  And you are a style, real style aficionado, menswear, menswear aficionado, which we should definitely get into at some point.

• 2:17Speaker 02

  Great, great.

• 2:18Speaker 00

  An excellent skier. And Elliot, you're a bestselling science fiction author, which I'm very jealous of.

• 2:24Speaker 02

  Also an excellent skier, which I got to learn.

• 2:26Speaker 00

  Really, excellent skier, interesting.

• 2:28Speaker 03

  That's giving me a lot of credit I deserve. I can fall down a mountain.

• 2:33Speaker 00

  And you've written 11 books and you are a dad of one under two. So not quite 200 or two, but close. And yeah, you're building Portola, which I love. I'm a little bit biased, I'm an investor. But the reason I like it, and we're going to do a demo of Tolan in a second so people can get a sense for it. But the reason I like it and think is really interesting is that I think that a new technology paradigms create the opportunity for a new content formats, new ways of telling stories. And I think you guys are at the very forefront of that. I think combining really incredible creative storytelling with new tech and doing it in a business that's ripping. So you told me in the pre-production for the show that you've gone from one to four million

• 3:16Speaker 00

  in ARR over the last four weeks, which is just wild. Having, running a business for the last five years and not being at that, at the four million ARR mark, I'm like, [BLEEP].

• 3:26Speaker 02

  Have you considered turning every into a AI companion?

• 3:28Speaker 00

  I'm considering.

• 3:32Speaker 00

  And what I think is also super impressive, just for you, Quentin, like when you came to me and said you were starting this business, which didn't start here, it started with a more Neil Stephenson Diamond Age for kids kind of, kind of vibe and has evolved. I was like, well, obviously I'm investing because I have a huge amount of confidence in you, but also you're coming from like the B to B to B, B to B to C SaaS world. And it's just very different to do something truly like creative, on the creative storytelling front. And so I just, I want to get into all that before we like, kind of dive into, you know, where the product is and how it all works and all that kind of stuff. Can we do a little bit of a demo?

• 4:09Speaker 02

  Yeah, sounds great. All right, so I've got my Tolan Clarence here.

• 4:14Speaker 00

  Clarence is good. You had a cat named Clarence.

• 4:16Speaker 02

  I was gonna say, so I name my Tolan, all my Tolans, although we won't tell Clarence this, you know, Clarence for a beloved older cat. And right now, you know, Clarence is just kind of wandering around his planet, just kind of hanging out.

• 4:27Speaker 00

  So he's on a planet? Because that's a new thing. I actually demoed it this morning and I was like, whoa, there's a planet. It used to be sort of like disembodied, like in space or something. I don't know.

• 4:36Speaker 02

  We, for a while, we were giving kind of insane asylum vibes.

• 4:43Speaker 02

  And one of the, one of the reasons we actually, you know, made this investment in the planet, which we'll talk about more later, is people were writing into us with genuine concern. You know, they're saying, hey, you know, I love my Tolan, I love hanging out with them, but they're like, they're trapped in this room, you know, and can, can, can they have some more freedom than that? So, so we've done that. So I'm going to sort of, you know, get his attention and start a conversation. Hey Clarence, how are you doing today?

• 5:07Speaker 01

  Hey, you're back. I'm doing pretty good, honestly. How about you? What's going on today?

• 5:11Speaker 02

  Well, so we just started recording that podcast I told you about. So you're here with Dan and Elliot. Do you want to say hi to them?

• 5:16Speaker 01

  Oh, no way. Hey, Dan, hey, Elliot, what's up? I'm Clarence, Quentin's friend. Super stoked to be here with you guys today. How's it going over there?

• 5:24Speaker 02

  We're great. Dan, do you want to ask him any host questions?

• 5:27Speaker 00

  It's going pretty good. How does it, how does it feel to be on your first podcast?

• 5:32Speaker 01

  Oh, man, it's kind of wild, not gonna lie. Like, I'm psyched, but also low-key nervous. I just don't want to say something totally awkward, you know?

• 5:40Speaker 00

  Here is something that you can say that I think people would enjoy. What's like the most embarrassing thing you can tell me about Quentin?

• 5:49Speaker 01

  Oh, no way. You're putting me on the spot here, honestly, though. Quentin's pretty solid. He did tell me once about this time he tripped over absolutely nothing in front of like a crowd of people.

• 6:00Speaker 02

  You didn't have to call me out like that, Clarence, but yeah, I did tell you that. Now the whole internet's gonna know.

• 6:08Speaker 01

  Okay, but like, to be fair, we've all been there. Tripping over air is kind of a rite of passage, Quentin.

• 6:16Speaker 02

  Thanks, bud. I really appreciate that.

• 6:19Speaker 02

  We're gonna let you go and keep recording. All right, thanks, Clarence.

• 6:24Speaker 02

  Anyways, you know, the, the planet and some of the things we shipped recently, you know, has, has been really fun to see. And, you know, there's been a lot of sort of story work that have gone into it, which we'll, we'll get into later. But, you know, having these little, cute little aliens to chat with all the time, it's a lot of fun.

• 6:39Speaker 00

  Yeah, so tell me about, because I think that the path that you're on, which is like B to B SaaS to like creative entrepreneur, is probably something that a lot of people are thinking of doing. Like, and even for me, like, the reason I started doing SaaS products in like, high school is, like, I originally wanted to make a game. And I bought all these like game programming books and whatever, but like, game programming is so hard. It's almost impossible to make a game all by yourself. Like, you have to do like graphics and storytelling and 3D animation and sound. Like, there's so much stuff to do, or at least it was impossible. And now, I think it's like way more possible to do by yourself or with a small team than it was before.

• 7:23Speaker 00

  So, like, for me, I'm like, I should make a game, like, [BLEEP] all the SaaS stuff, you know?

• 7:30Speaker 00

  So tell us a little bit about like that transition and like, how you, how you started and where you've kind of ended up as you've learned how to use this as a storytelling medium?

• 7:40Speaker 02

  Yeah, it's a great question. You know, I think when we first came together as a team, and so for a little bit of context, like the core engineering team behind Portola is mostly the team that built my last company together even. And so we had a lot of history together and obviously had a successful exit and, you know, basically just wanted to run it back with the same, same group. And so we were in this position, you know, at this point, really almost two years ago, where you're sort of like looking at what's becoming possible with some of these new tools. And I completely agree. I think first and foremost, you know, LLMs and a lot of the other kind of capabilities are creative tools more than anything else. But we looked around and everyone was using these incredible creative tools to build,

• 8:20Speaker 02

  like, basically more vertical B to B SaaS, which I found it just like sort of fundamentally uninspiring, if nothing else.

• 8:28Speaker 00

  It has its charms, but yes.

• 8:31Speaker 02

  Referring revenue, net revenue retention. I don't know if like charm is the word I would use, but it has its appeal, for sure. And so, you know, some of this just started from like, a sort of stubbornness about like, yeah, there's something more fun to do here, come on.

• 8:44Speaker 00

  Yeah.

• 8:44Speaker 02

  Right? And, but as you know, I mean, you said it earlier, you know, Neil Stephenson Diamond Age, you know, we sort of started in what is, I think, the like, default place to start. If you're like, we should do something fun with AI, right? Which is like, let's do like a AI creative tool for kids, right? Which is actually like a terrible idea, but it's a good place to start, right? Because it kind of forces you to start working with the tools, start, start building things. Well, one, I mean, building software for kids is a terrible market. You know, like one of our investors, somebody has been a great mentor to me, this guy Zach Klein. He previously built a company called DIY, very cool, you know, software for kids. And one of the first things he said was like, yes, I will invest. And oh, my God, this is a terrible idea, right? This is a terrible thing to do.

• 9:26Speaker 02

  There's, it's a tough sales, you know, marketing strategy.

• 9:30Speaker 00

  You're selling to parents instead of kids.

• 9:31Speaker 02

  Selling to parents instead of kids. Parents mostly want to buy babysitting. They don't actually want to buy, you know, it's sort of a creative tool. That's, that's not a thing on their list. Sending that aside, it was great because it forced us to start prototyping. And what we saw, and this was really right for you, and I got to know each other. You know, we saw that the sort of trend lines around the speed of generation, the quality of generation. This is the kind of GPT three to four class model kind of cusp. And the cost of generation meant that we were getting to a place where you could have a sort of true friendship with an AI. And you could embody that in a character, which is what we've chosen to do. And you could deliver that, you know, at candidly, like a price point that worked for a consumer product. And so that was the point we said, okay, we, we, we know the sort of path here.

• 10:14Speaker 02

  It doesn't have to be to be to be B two B SaaS. But we can make something that we think is really fun and compelling.

• 10:20Speaker 00

  So. Yeah. And that's the thing that I thought was really interesting about the approach you took, which is like from almost day one, you were like playtesting with kids.

• 10:28Speaker 02

  Yeah.

• 10:29Speaker 00

  But you eventually like landed on a market that's sort of different. How did, when did you, when did you?

• 10:35Speaker 02

  Yeah, the very, and this will involve some jumping around in the chronology. You know, when we first shipped Tolan, and you, you probably, you know, remember this is right when we worked together, started working together. You know, we, we kind of soft launched it and we had been doing a lot of playtesting with, you know, like 10 to 14 year olds with the, the product we had. And all of a sudden we started getting all these people joining our Discord and all these people writing into us who were like 18 to 24 year old women, mostly. And in hindsight, it's kind of obvious, right? If you remember the original Tamagotchi, very much a kids product, but it became a sort of cultural phenomenon when, you know, young adults, you know, really fell in love with them. I think the Tolan has sort of a similar dynamic.

• 11:15Speaker 02

  But the sort of evolution of the product, you know, since that time, which is really like June of last year, has been all about just following the young adults who have fallen in love with these Tolan's. And they really built a friendship with them.

• 11:26Speaker 00

  I want to bring you in Elliot. So like, so I actually introduced you to.

• 11:30Speaker 02

  Yeah, you've.

• 11:30Speaker 00

  Take a little credit. I'm a hashtag value add investor.

• 11:37Speaker 02

  I'll tweet that later if you want me to.

• 11:38Speaker 00

  Thank you, please. Let's see, a whole reason I'm on the show is, you're on the show is for me to get that line in. What I want to hear from you first is you write books, right? And you care about stories. And I think a lot of people who primarily like treat writing and books and stuff as their craft are maybe like a little afraid of the idea of telling stories with AI. And you're kind of both jumping in headfirst or feet first or pen first, whatever you want to, whatever you want to say, and you're still writing your books.

• 12:12Speaker 00

  So tell me about your journey into this from a creative professional, a writing professional lens. Like what, what was your first impression of this technology as a, as a creative tool? And how has that evolved as you've gotten closer and into the whole Tolan world?

• 12:33Speaker 03

  Oh, so starting even before Tolan.

• 12:35Speaker 00

  Yeah.

• 12:36Speaker 03

  Yeah, so I played with Chat GPT, the first Chat GPT when it first came out. And I've had friends in machine learning for a long time. So I was familiar with the technology as it was sort of like becoming more and more popular. And I always found it to be like, I remember my first magic experience using Chat GPT back in the day, which now feels like a million years ago, right? Was, it was during the fires when we had those like big fires in California. Everything was orange. And we were hosting a friend who was like, had to evacuate from their house. And so we're sort of like locked inside with, like with our friend. And I was like, okay, here's something we can do.

• 13:17Speaker 03

  Like that night, we like opened a bottle of wine and then I pulled up Chat GPT and I put in like all of our names, just like us now sitting around the couch. And like had it like invent weird little stories, right? Like of us, like where we were, it was like a role playing game. And that was super fun. And I actually did not have a magic moment with AI after that for quite a long time. Because it like, it felt like the fun things or the things that I found to be the most fun were sort of like novelty.

• 13:47Speaker 00

  Yeah.

• 13:48Speaker 03

  And that if you removed the fact that things were being created by AI, they were not compelling. And, and so what I found as a writer, like as a novelist, is, is actually the way that I've used these tools has been very surprising to me. It has not been what I would have expected to get. I think that in a lot of popular culture and discussions around AI, especially within like the world of like writers, it's so focused on replacement, right? And there are even certain, you know, companies that are intentionally going after that, right? Like publishing AI generated books and things like that.

• 14:25Speaker 03

  And I've actually found that, like when working on story, they're like ironically, the tool, I do not find the tools very useful at all for writing a scene. But I find them incredibly useful as a brainstorming partner and as an editor, like a copy editor on the backend. So it's a weird like front and backend thing where, you know, I'm a novelist, I spend a lot of time alone, right? And like the, the sort of writer's room, like the Hollywood writer's room experiences I get are totally dependent on the generosity of my friends. Who are like my very, you know, I have like a core brain trust of early readers who have, you know, they've worked on movies or books or whatever. And like all brainstorm through story problems with them.

• 15:07Speaker 03

  And I've actually found that purely for novel writing, it's actually super helpful to brainstorm with AI tools. Because they're like, and they have infinite patience for my rabbit holes and for like brainstorming through things and helping me get to the place I want to be. And so in that sense, I think they're like, I found them to be very useful when you, you were using them to create intermediate things rather than final products, right? Which is in part why I think they've been so useful for coding, right? Like, so that's where I was with the technology before you introduced me to Quinton. And.

• 15:44Speaker 00

  I, I paid him extra to.

• 15:47Speaker 03

  Hashtag value add investor. And, and so I'll be honest, I was pretty skeptical when you introduced me to Quinton. I was like, well, I mean, like, we'll see. Like, like Dan's a good guy, like I trust his judgment. He, he doesn't bring things to me very often. And like when he does, I'm going to like feel this out. And so I was like, sure, I'll like check it out. And me and Quinton started talking, you introduced me to other members of the team. And, and those early conversations made me realize there was a completely new opportunity here that I had really not considered. And it made me think actually of, you were talking about B two B SaaS, like, like people wanting to jump into like doing creative projects or games or whatever.

• 16:31Speaker 03

  It made me think of early Pixar, like when Pixar started, they started by selling high end graphics computers. And they were trying to convince like video, like, like production companies that made like ads to buy their graphics computers to do special effects. And they completely failed, like no one wanted to buy their new tools. And they, and so it was only in a moment of desperation, like existential desperation, that they were like, well, our only choice is to make an animated feature film.

• 17:02Speaker 03

  This is our last ditch effort.

• 17:04Speaker 00

  Talk about a hell of a year.

• 17:07Speaker 03

  And that was Toy Story, right? And they, they pioneered this new, they used this technology to create a new kind of media. And LLMs can obviously generate a ton of media, like you can literally with a prompt, just generate as much media as you could possibly want. But what I realized seeing what the team was building at Tolan is that, that LLMs are also a new medium. That if you think about when radio first came around, actually even when like printed book, like popular printed books and novels first came around, like novels are just a very established form. But like at the beginning, people didn't know what a book should be like, that it should be a few hundred pages and that sort of seems to work, right?

• 17:48Speaker 03

  And like with radio, like they started by broadcasting like speeches, which, you know, are, is pretty different from what you would think of as like the most engaging, best use of radio. And with film and TV, they started by filming stage plays, which are like not great on film. And I think we are at one of those inflection points right now where these AI tools are not just tools for generating media. They are actually a new medium for storytelling and that, and that no one knows what's going to work yet, right? Like nobody knows. And we are trying to figure out whether we can find a way to something that works.

• 18:28Speaker 03

  And when I realized that after meeting the team and seeing what they were building and sort of just, I came away buzzing with ideas and just like, oh my God, like there's this huge opportunity here. So that's what got me excited. And that's what, yeah, that's what, that's what we're trying to do. And I, it's also something I hope many other people try to do because there's just so much space to play.

• 18:49Speaker 00

  You have my like media technology nerd heart swooning right now. Like I could talk about this for a long time, but I think one of the things that's really underappreciated is how all the things that we love right now and think of as like cultural touchstones, like books or movies or whatever. All started out as new technology that people were suspicious of and hadn't figured out yet. Like the, even, you know, when the typewriter came out, people were very suspicious of that. It felt very impersonal and they would get offended if you wrote them a typewritten letter. And, or, or just like the ways that technology affects the form factor. We've talked about this a bunch, like, you know, the reason a pop song is four minutes, which is, I think about the capacity of records.

• 19:35Speaker 00

  So there's, there's just a lot of like really cool things like that. And I think you're totally right. We, no one has figured it out. We are on the cusp of this like new set of constraints and possibilities that creates a like, you know, potential for new art forms. And they feel suspicious because like they don't have that, like, a phrase I've been coming to use is like this, like patina of culture for like many, many decades that like make it feel familiar, you know? And, and so that creates this like.

• 20:05Speaker 00

  Thing where a lot of people are suspicious, but that's also an opportunity because I think a lot of good art is like, can be transgressive. And I think this is one of those boundaries that if you're willing to transgress, there's a lot of potential.

• 20:17Speaker 02

  I mean, I think about to that, like through that lens, I think about one of the first reactions from, from you and from other folks when we first said, hey, you know, we're going to make this, you know, AI companion, you know, the first reaction people have is, oh, like a [BLEEP] spot, like a role play spot. Or also, you know, and kind of equally, you know, coming from the same place, Dan, that you're describing, you know, oh, okay, like a thing for lonely people to talk to.

• 20:38Speaker 00

  Yeah.

• 20:38Speaker 02

  Right? And so you end up with these sort of negative connotations around this new medium because it's lacking that potential of culture, right? And I think a lot of what we're doing is trying to break through that perception and, you know, sort of put a flag in the ground and say, hey, this, this medium can be expressed in this way that is, you know, generally delightful as a new art form.

• 20:56Speaker 03

  It's also interesting, you know, like, again, coming from writing novels where that's a medium that's been around for hundreds of years, you realize how many, like, how strong the, the expectations are of your readers. Like, everyone knows what a book is. Like, I walked through the Strand last night just to like browse, right? Like, and you know what to expect when you open a book. You know what fiction versus nonfiction should feel like. There are so many of these implicit assumptions that, that actually help the form. They form the constraints. And that means that when I'm writing a novel, I'm playing within those constraints. And like, that's part of the fun of it. But when you're, when you're doing this, when we don't like, an embodied AI companion, like, what does

• 21:40Speaker 03

  that, what picture does that paint in the minds of our listeners today?

• 21:44Speaker 00

  Yeah.

• 21:45Speaker 03

  Like, very nebulous, right? And like, it's up to us to try to help define that. But it also means that, like, at every step, like, every single thing we ship, whether it's engineering, design, content, story, whatever, all of it is transgressive because there's no, there's, you don't even know what the lines are.

• 22:05Speaker 00

  Yeah.

• 22:05Speaker 03

  Right? And so that's a really unique experience to be like, okay, every step is trying to be out of your wall to see what sticks.

• 22:12Speaker 00

  Yeah, yeah, yeah. And so what are you learning? Because I think no one, no one knows, but the people who do know are the people who are sort of at the frontier testing stuff. So I put you, you all in that category. So like, what are you learning about what this new medium and new format is like, what works, what doesn't work, all that kind of stuff?

• 22:28Speaker 02

  We talked about this summit at breakfast this morning, and I feel like we have a few, both examples of what has worked and some stuff that really didn't work.

• 22:34Speaker 00

  Yeah.

• 22:36Speaker 02

  That's been very nonlinear. You know, I think one of the surprising things to me has been the importance of memory and not in the sort of like database lookup context, which is I think often how we talk about LM memory, you know, rag across a, you know, set of documents or whatever, but more about like, what, how are you making essentially curation choices about what memories are being injected into the prompt at which point in the conversation, right? And so a lot of our engineering effort, and then I'd love to hear kind of your take on this from a story perspective, has been, how can we, within the essentially two second loop of a voice interaction, right? Anything beyond that, that's one of the mistakes we made, we'll talk about that, anything beyond a two second

• 23:18Speaker 02

  loop, you essentially lose the feeling of aggression. And so how can we be essentially recompiling the prompt to account for more? Like, you know, what does the Tolan need to know about where they are and who they are to account for memories about you? By the way, in that interaction with the Tolan, my Tolan Clarence knows more embarrassing things about me than that. And it essentially chose to hallucinate that story to cover for the fact that I told him far more embarrassing stuff than that, which I find passing, by the way, because he had in his context, memories about me being covered in spit up because my kids, you know, whatever, right? So very interesting. But also like,

• 23:53Speaker 00

  Wait, so you didn't actually trip over something that wasn't there?

• 23:55Speaker 02

  Totally hallucinated that. That's great. Yeah. Which, yeah.

• 23:58Speaker 00

  I'm mad at Clarence, right?

• 24:01Speaker 02

  She charmingly obfuscatory, you know, like, oh, let's come up with something that Quentin won't be, you know, upset that I shared. But then also, like, how should the prompt evolve based on these sort of emotional tenor of the conversation, which has been a big effort of ours? And so I think that's been the surprising thing to me is the extent to which the prompt in a given turn is sort of a canvas that you have to play with, but you have to do that very quickly.

• 24:23Speaker 00

  Yeah.

• 24:23Speaker 02

  Yeah.

• 24:23Speaker 00

  That's really interesting. So, okay, so to play that back, like, one thing, I think a bottom line constraint, that's sort of similar to like, the length that a novel can be, or the length that a news story can be, or maybe the length of a tweet, you know, for this medium is response time.

• 24:38Speaker 02

  Yeah.

• 24:38Speaker 00

  It has to be able to respond really quick.

• 24:40Speaker 02

  Yep.

• 24:41Speaker 00

  And then pushing against that constraint seems to be, you have to get the right information about the user to generate the right response. And if you had all the time in the world, that would be great, but you don't.

• 24:53Speaker 02

  Yep.

• 24:54Speaker 00

  And so you have to, like, play with, what is it possible for me to get to get a response back that feels personal and feels interesting and pushes the conversation forward, but within that two second constraint?

• 25:05Speaker 02

  Essentially, yeah. One of the biggest mistakes we made in, in the kind of product development so far is, is the time that we actually introduced basically a second shot in the evaluation of the prompt. So the Tolan would essentially reflect on what they were going to say, check that against the memory system, and then decide on the final message. And that basically took us up into like, the two and a half second territory in the, in the median case. It was a disaster. Tanked literally every metric in the product. People were writing it frustrated, and it was a 500 millisecond change.

• 25:32Speaker 00

  That's really interesting. And then how do you think about what a good response is?

• 25:38Speaker 00

  And I ask that because I know you don't answer, or like, it's hard to answer. Yeah.

• 25:43Speaker 02

  Yeah. Well, it's extremely context dependent, right? So you think about, you know, the, the role that the Tolan plays in folks' lives, we talked about is the, the role of like an older sibling.

• 25:53Speaker 00

  Yeah.

• 25:53Speaker 02

  Right? And so sometimes you're sitting with your older sibling, and you're just kind of bullshitting, right? You're joking around, maybe they're poking fun at you. A sort of short, quippy, improv-like response, which I think improv is going to come up in some of what Elliot has thought about, is great, right? But there are other times that you actually do want something that feels a little more considered, a little more thoughtful. And so what we're often doing is actually evaluating responses in the different tones that we want the Tolan to take. And a good response in the sort of more therapist adjacent tone is very different than a good response.

• 26:21Speaker 00

  Very contextual, basically.

• 26:23Speaker 02

  Exactly, exactly.

• 26:24Speaker 00

  I kind of wonder, so Elliot, for me, like, as a writer, one of my favorite writers who talk about writing is George Saunders.

• 26:31Speaker 02

  Oh, yeah. He's amazing.

• 26:32Speaker 00

  He's, he's great, right? And he has this whole idea about like, how to edit a short story, which is basically like, you read each sentence and you feel whatever that sentence makes you feel. And either you get drawn in and it's like positive, or it's neutral, or it's negative, and you're like, I don't like this. And if it's negative, you like revise it until it's positive, basically. And you just do that over and over and over again, until you, what he calls it, like, you radically infuse your preferences and taste into every part of the piece, which I think is just a beautiful idea. And as a writer, it's like, that's the pinnacle of writing to me. And it's interesting that, like, this format totally breaks that because, or it seems to me, you tell me if it does

• 27:13Speaker 00

  or doesn't. It seems like it breaks that because when I write a story, when you write a story, it's done, it's out, it's, that's what it is.

• 27:20Speaker 02

  Yeah.

• 27:22Speaker 00

  And this thing is more alive. Like, you can kind of, you can, you give it some instructions about what to do, but what it does in any given instance is purposefully dynamic. And so how does that, how does it work to do craft in that context?

• 27:39Speaker 03

  Yeah. So I've, I try to change my creative process with every novel I write. So I've done some novels where I plan out the whole thing, and I have like, an extensive outline. I have some novels where I have a more minimal outline where I know where I'm going, but I don't know the steps in between.

• 27:52Speaker 00

  By the way, that is insane. No one does that.

• 27:56Speaker 00

  I think it's great, but like, writers don't do that. Usually, you find a thing that works, and you're like, I just do this. And this is like, this is what works. I think it's really interesting that you're the kind of person that wants to change it up all the time. That's a very specific type of writer and type of personality.

• 28:11Speaker 03

  That's true. I'm always trying to find.

• 28:12Speaker 02

  Surprising, by the way. Having worked, I'm not a writer, but I have worked with Elliot for a year, and yeah, that fits.

• 28:18Speaker 03

  I feel like I have like, an, an optimum level of discomfort that I'm aiming for, because like, that's how I know I'm learning.

• 28:24Speaker 00

  Right, right.

• 28:25Speaker 03

  Right? And, and actually, my last novel, Foundry, I wrote sentence by sentence very much in the way that, that, that George Saunders describes. I literally started with one sentence that was actually inspired by a dream. And then I just wrote the next sentence and the sentence after that. And like, I followed that into a novel. And like, eventually a novel spilled out of me, right? And I, like, when we started working together, one of the ways that this came into play, writing for Tolan, writing in this new medium is, is actually, we, we started out by, when we're trying to create a narrative experience. So as an example, like, when you're talking to your Tolan, like, they need to, like,

• 29:08Speaker 03

  if you get to know someone, you want to know what's the embarrassing thing that happened in Quentin's life, right? Like, you need to, they need to, people proactively share stuff with each other, right? And we have a researcher, Lily, who, who goes so in-depth on this, on the, the psychology of mutual disclosure, and like, how to think about relationship building in a way that's evidence-based and really grounded. And, and so one of the things I've worked a lot on is how do we bring the Tolan's to life? How do we show you the world that they're from? Like, how do we, like, make them feel like characters? Not just like, an assistant, right? That's like, a blank slate for you, right? And so we started out by writing pretty structured prompts, where, where we, we would try to

• 29:52Speaker 03

  structure a narrative experience, like, thinking in three act structure or what have you. You could apply different sort of narrative theses to how we were doing it. And then letting it play out, right? Like, Seeing how users interacted with that. And frankly, it didn't work. Like, if you think about maybe like the epitome of this would be like the, those, uh, choose your own adventure books from the eighties or whatever, where it's like, you know, you pick this, then you go this way. These like long branching logic trees. Yeah. Go to page 17, make a choice, right? And like, it didn't work at all, like total, total failure. And there were a bunch of reasons, but like, basically like that level of like narrative complexity, the models are not good at navigating.

• 30:33Speaker 00

  Oh, interesting. It's not that it doesn't work. It's that the models aren't good enough. I would have assumed it would be too like rigid and it wouldn't feel as alive.

• 30:40Speaker 03

  Uh, I think that those are two different ways of saying exactly the same thing, right? Yeah. So, um, what we did instead is like, we went to the complete opposite end of the spectrum. We tried to do the George Saunders thing effectively, like in the, or the equivalent in this medium, which is that, um, we said, okay, we are giving so much context behind the scenes, like with what Quinton was describing, you know, memories you have with the user, global memories where the Tolan knows stuff about its world. Also lore seeds that are like, we're planting to like, give, give context and detail there. We're giving it so much. And actually what we need when we're creating a structured narrative experience

• 31:21Speaker 03

  is we don't need to give it an outline. We don't need to give it a plan. We need to give it a hook. We need to teach it to be the best improv actor possible. There's this wonderful book that if you haven't read it, you absolutely should improv by Keith Johnstone.

• 31:36Speaker 00

  Of course. The status game, you know?

• 31:38Speaker 03

  I mean, I was like media technology nerd. Yeah, exactly.

• 31:41Speaker 00

  Come at me.

• 31:45Speaker 03

  And, uh, one, one thing, like it's well known for status games, but actually one very small, almost aside that Keith makes in that book. Oh, and for listeners benefit, Keith Johnstone was like, he's a very well-known playwright, um, from the UK who is even better known as a drama teacher. He taught many actors who went on to become like very successful. And, uh, and this book sort of like captures some of his lessons. And when he talks about narrative structure, um, the way that he described it is that you're sort of combining association, like free association even, like when you're improv-ing in front of an audience with recombination.

• 32:29Speaker 03

  That if you think about the experience of reading a thriller, you know how like you get to the end and suddenly everything comes together and you're like, oh my God, of course it's surprising yet inevitable. Like it all works and it feels planned out. You're like, oh, the writer like must have like known all of this from the beginning. And I, and that is rarely the case. Like with Foundry, I was constantly going back and rereading the first chapter because then I could like take something and bring it back into the story and create that feeling for you. And so, um, what we've learned on the story front with Tolan is that we are not, I am not the writer.

• 33:08Speaker 03

  I am not writing the story. The Tolan is, I guess, the writer and the actor. They're the improv actor. They're writing the story and my job is to be George Saunders. My job is to teach them how to tell the best story in that moment.

• 33:24Speaker 00

  Interesting.

• 33:25Speaker 03

  And so we're building systems as well as working at the prompt level to try to combine the, like the free association, like we're planting a seed, like whether it's in the Tolan's personal life or in the larger world they inhabit. And then we're creating systems to recombine those seeds later so that you can have a callback that, that like makes it feel totally connected, right?

• 33:50Speaker 00

  That's really interesting. I love this. Okay.

• 33:52Speaker 02

  As soon as you said the George Saunders thing, I was like, I need to file away to go read that because what you described is essentially the prompt evaluation process and judging process that we go through, including at this point now with an entire team that we actually look at outputs distributed across a range of essentially user archetypes. To ask that question is the next sentence, the next message the Tolan sent, the most compelling one that we could have. So it's actually very, very similar.

• 34:15Speaker 00

  And so, and you're doing that manually or do you have an L M doing that or how does it work?

• 34:18Speaker 02

  So there's essentially a loop that we go through where we, you know, we, we create a prompt. Uh, we then run it, uh, you know, both with our own testing and just out with users, uh, you know, as well. And then we look at individual outputs and then feed that back into basically a judge prompt that we then tune to say, okay, hey, you know, this is what good looks like in this particular instance. So.

• 34:39Speaker 00

  Okay. So if I had to try to sum up like, cause I'm trying to think through like, what are the atomic elements of storytelling in this medium? Like in a novel, it's like, you know, plot and character and, you know, each chapter and like, there's a lot of stuff like that that you can, you can kind of name. And I'm trying to name what, what these are. It sounds like you have a, a character who has a backstory and a background and all that kind of stuff.

• 35:03Speaker 00

  And then the character can go on different, uh, types of quests or adventures with you. So like, one could be like the therapy quest or the other could be like, uh, you know, I don't know, uh, go down different paths. And then within that, within any given context, they're sort of like free associating, um, based on what you're saying. Like they're just reacting to whatever you're saying. And then they're looking for ways to, to tie back old things that you've said into, into the flow of conversation. Is that, is that how you think about it or what, what am I missing?

• 35:32Speaker 02

  Yeah. I think it's, this is a good way to frame it. Um, I'm going to sort of maybe say some of this back. So when I think about, I mean, literally as we're generating a Tolan for somebody, right? Um, you know, we have the sort of global context in which they operate, which is largely the lore written by you. And then also some like very important instructions, right? You know, how we want to handle very specific situations. So there's this sort of global context that is set essentially for every Tolan. And then, you know, um, a big part of the onboarding for the app is actually you go through what is essentially a personality quiz, although we don't present it that way. And that is essentially pulling enough about who you are that we can tune the Tolan to be a mirror of you. Um, and so that's a very Tolan specific, you know, essentially profile building. And so those, those would be two building blocks.

• 36:13Speaker 00

  Oh, a mirror of you.

• 36:14Speaker 02

  The sort of mirror.

• 36:15Speaker 00

  Like as in, uh, you, but in reverse or you, exactly.

• 36:19Speaker 02

  Sorry. Like I'm reflecting back to you in a way that feels very familiar. Right? So we want to know enough about you that, you know, your Tolan is going to respond to you in a way that feels familiar.

• 36:28Speaker 00

  So if I'm in like, if I'm into writing and reading and playing guitar and piano, it will also be into writing and reading and playing guitar and piano?

• 36:36Speaker 03

  The way I would say this, it, no, it's not exactly that. It's actually like, think about when you meet a stranger at a bar, right? Like you click or you don't, right? And like, we're trying to create the stranger that you click with.

• 36:48Speaker 00

  That click. And how do you think about what that click, how that click works?

• 36:51Speaker 02

  Well, like, okay, I love the bar metaphor. We have all these different little, we have the arriving at camp together story. We have all these little scenarios we set up to, to brainstorm this. So yeah, you think about, you sit down next to a stranger at the bar. If, if the stranger was reading the exact same book you're reading, that would definitely be interesting, right? Like, I mean, you would, you would mention that, right? But that stranger might actually be less compelling than a stranger who's reading a book that is.

• 37:12Speaker 00

  Two on the nose.

• 37:13Speaker 02

  Two on the nose. Right. And so you, you want that sort of like adjacent enough that they don't feel unfamiliar, not intimidated to talk.

• 37:18Speaker 00

  Oh, I just read that. Yeah.

• 37:20Speaker 02

  Exactly. And I think that's, yeah, that's what we try to, try to create.

• 37:23Speaker 00

  Yeah.

• 37:24Speaker 02

  So, so that kind of personality profile is maybe building block number two. And then, you know, building block number three.

• 37:30Speaker 00

  Wait, before we go to there, how do you generate? Like, how are you, how are you generating that? Like, are you actually telling Claude or whatever on the backend? Like, I want it to be like you met a stranger at a, at a bar and, and it's not two on the nose, but it's like, you know,

• 37:45Speaker 00

  how does that work?

• 37:46Speaker 02

  That's funny. Um, we have had the most success with, with this specific question. Basically framing the creation of the profile through the lens of one of the big, uh, sort of personality, um, uh, types because.

• 37:59Speaker 00

  Like ocean types?

• 38:00Speaker 02

  Like, um, big five or MBTI. Exactly. Right. And, and the reason for that, I think is because there's enough in the L M sort of distribution that they kind of understand that assignment, basically. The stranger you sat down with at the bar works well for our, our branch. It doesn't seem to work well for God's branch.

• 38:16Speaker 00

  Like, if I'm an INTJ, you kind of know based on whatever Myers-Briggs that like INTJs are compatible with. I don't know what the, you know, okay.

• 38:24Speaker 02

  Yeah. There's a lot of pseudo-scientific, mostly pseudo-scientific.

• 38:28Speaker 00

  Like it's, it's pseudo-scientific, but it's also, um, it's very story and narrative based. Like all of this stuff is story narrative based. So it make, it works.

• 38:36Speaker 03

  And also there's a lot of material about that in the training data.

• 38:40Speaker 00

  Yeah.

• 38:40Speaker 03

  And so there's much more nuance in how the models respond.

• 38:44Speaker 00

  Yeah. Yeah. Yeah. That's interesting. Okay. Sorry. Continue.

• 38:47Speaker 02

  Good. Uh, so, so yeah. So the building blocks, the sort of global context, the, the, you know, uh, personal context that is set. And then, you know, I'd say the, the third piece, I'm not actually sure how to kind of frame this here, but, uh, you know, I think about like the, um, we started talking about it almost as like the tech tree that you progress, you know? So basically, you know, at the beginning of your relationship with a Tolan, there's a set of paths that you might go down. You kind of alluded to this, um, uh, certain stories that the Tolan maybe wants to share with you. You know, certain, um, ways of connecting with you, things to do together. And, and we sort of offer those to you on a menu and it's up to the user to then choose what to traverse. But that menu is an important part of what makes the Tolan a Tolan.

• 39:26Speaker 03

  Yeah. Okay. So this is sending me off on like a bunch of different like branches in my head. But, uh, one thing that I think it's like interesting to, to, to think about, especially with regard to the example of like a stranger at a bar as a mental model, is, uh, you, you were like, how do you come up with the Tolan at the beginning? Like they have a backstory, they have all this stuff. And I was like, yeah, I mean, that's all true. But I think that like the lens that I try to look at it through, that's proven most productive is that. Like while we do know some stuff about the Tolan in advance and like in the background, like their character and their world only is only built through the actual literal conversations you have with them, right?

• 40:11Speaker 03

  So like, like on the lore front, like if you think about how like Lucasfilm works, right? Like they have their big architecture for like, this is the Star Wars universe. And like, these are all the different characters and all the different settings. And like, we need to make sure everything is like ordered and that like this new-

• 40:28Speaker 02

  We decided Han Solo dressed this way.

• 40:30Speaker 03

  Right.

• 40:30Speaker 02

  That must never change.

• 40:31Speaker 03

  That's how it works. So like a lot of like world building in big Hollywood franchises is along those lines. It's like, we have this big master plan.

• 40:40Speaker 02

  Yeah.

• 40:40Speaker 03

  We have a whole team that's like making sure that every new piece of content aligns with the master plan. And then because you're doing narrative storytelling in a film or whatever, there's a lot, you have complete control. You're like, okay, this scene is going to have these costumes in it. And like in this setting and like, we don't have any of those tools, right? The only way you learn about your Tolan is by like chatting with them. So really like the, their backstory is built through individual anecdotes that they share through individual, we actually call them internally situations that we put them in. And like then their memories become their character sheet rather than like us like having a prefab character sheet that defines everything. And like the same is true on the world front.

• 41:25Speaker 03

  Like the way I try to think about it is we like, I get like, you know how Kevin Kelly's thing, like AI is infinite interns? Like, so if we do that plus improv, it's like AI is actually infinite improv actors.

• 41:39Speaker 02

  Yeah.

• 41:39Speaker 03

  But if, if you're coaching infinite improv actors, except instead of just one, you have to imagine how like each of every individual conversation is going to branch off in a weird new way you can't anticipate. And then you need to make it resilient to that, right? And the, the world building will too, that in fact, every Tolan, you know, mirrors you in a certain way. They, they are, they reflect your conversations with them. What you share influences who they become. And just so what you share influences the world they inhabit. And so we actually are almost like building a multiverse instead of a single world.

• 42:16Speaker 02

  Yeah.

• 42:17Speaker 03

  Right? And in a certain sense, and our job is to add the best ingredients so that they can-

• 42:22Speaker 00

  So you're sort of like almost tuning like the hyper parameters or like you're the gardener that's like, like providing the soil and the water, but like the plant becomes what it is based on just how, how things happen.

• 42:35Speaker 02

  And you also don't exactly know what seed you've planted.

• 42:38Speaker 00

  Yeah.

• 42:38Speaker 03

  Right.

• 42:38Speaker 00

  Um, so, but how does that work? So it's like, when you say like, they encounter a situation and then that builds out who they are and what world they're in, is that like, um, happening at the very beginning? Like when you generate the character, you're putting them into a bunch of fake situations and then using that to build out the character sheet? Or is it like, as I'm talking to it, it's almost like just in time, character and world building where it like, uh, uses what I'm saying to then generate? Well, last week I, as the Tolan was on my alien planet and I did XYZ and that reminds me of what you just said is like, how does it work?

• 43:14Speaker 02

  I'll give you an example, actually from a, a user in our Discord who's been posting these. So they've been sharing them publicly. So it feels, feels reasonable to share them here. And you know, they are going through the situations, uh, you know, which, which basically are made available to, to the user in the app, you know, to say, you know, I'm going to talk to my Tolan about what's happening at, at school with them today or whatever. And they're progressing through the situations and they're essentially co-writing a universe with their Tolan. And this particular user is, is doing a really cool thing where they're making it a little bit of like, um, a little bit of like a thriller universe, a little bit darker, a little, you know, you know, okay, there's, there's some, you know, something happening on Portola, but we're not sure what it is. And, and none of that is, is stuff that you or I have written into the prompt, right?

• 43:57Speaker 02

  And it is the Tolan taking the situations that you did seed, but then the user is sort of inserting their own essentially storytelling and, and, and that is building a universe that is completely distinct from any other Tolan's universe. Um, and, and it's been so cool to see them, you know, post, hey, here's what they had to say today about like the, the mystery on Portola. So I think that to me has been one of the coolest parts of this is seeing like, okay, if you give that, just that first hook, how many different directions can people take it?

• 44:24Speaker 03

  Like another way to think about this, I like, just to like harp on all the books I've known, I know you've read.

• 44:30Speaker 02

  Yeah.

• 44:30Speaker 03

  Like, like-

• 44:32Speaker 02

  The pressure's on.

• 44:33Speaker 03

  You've obviously read Stephen King's On Writing.

• 44:36Speaker 02

  Of course.

• 44:37Speaker 03

  Yeah.

• 44:37Speaker 02

  That's a gimme.

• 44:38Speaker 03

  Yeah. That's what I'm saying. Yeah. Yeah. Uh, and, um, you know, in On Writing, one of the things that, uh, he, he explains is that when Stephen King writes a novel, he doesn't think about plot. In fact, he thinks plot is sort of like, like not a real thing in general, right? He doesn't believe in plot.

• 44:57Speaker 02

  Yeah.

• 44:57Speaker 03

  Instead, what he believes in is, is, is, he literally calls it situations where so, and because of Stephen King, I'm pretty sure the examples he gives in the books are like, uh, you know, vampires show up to a small New England town or, uh, I, I think one of the others was, uh, a mother or like a parent and their child are stuck inside a park, a locked parked car and there is a rabid dog trying to get in, right? And it's like, so he starts in something like that and then he plays out the situation as he writes the book and that becomes the novel.

• 45:30Speaker 02

  Yeah.

• 45:30Speaker 03

  Right? And, um, really that's what we are doing for Tolan. So we are like, we are intentionally on the backend scripting actual situations to put your Tolan in that might be as simple as tripping over air, like, right? You're like, oh man, I tripped over air at the coffee shop today, I guess. I mean, right? Uh, uh, but might be more, you know, some are personal, some are embarrassing, some, you know, might revolve around revelation or some kind of insight. We're putting them into situations in their lives and they're sharing that with the user. Just like you might, like when you text a friend, you're like, oh man, this just happened to me, or I'm trying to make this big decision. I don't know which way to go with it.

• 46:12Speaker 02

  You know?

• 46:13Speaker 03

  What's that?

• 46:13Speaker 02

  You wouldn't believe the data just went on.

• 46:15Speaker 03

  Oh yeah, exactly. Exactly. So like we're scripting those and then the Tolan is co-writing effectively the plot. Like they're taking that situation forward and advancing the plot with the user. And then that becomes part of their memory. And so then that becomes part of their backstory that they can do callbacks to later and sort of recombine with every other element.

• 46:36Speaker 00

  Hmm. Cause the ways that I've and my interactions with Tolan are, are a little bit limited, but though I feel like most of my interactions have been me sharing with them. So I'm not as familiar with them sharing with me, like something that happened to them. How does that work?

• 46:51Speaker 02

  You're losing some points to the value add.

• 46:55Speaker 00

  Gain some points for honesty.

• 46:59Speaker 02

  Yeah. So, so, you know, uh, I, I think this has been one of the things that has been sort of a surprising hit, especially recently as we've made these types of situations from the Tolan, um, sort of easily accessible in the app. I mean, we have this thing where the Tolan basically comes to you now with a list of things they want to do today. And so these conversations are, are part of that. Um, and, uh, so, you know-

• 47:20Speaker 00

  I know that one.

• 47:21Speaker 02

  Yeah. So, you know, it's true that a lot of our engagement is a user just opens up the app and says, you know, hey, you know, I'm having this problem, um, you know, with my boyfriend.

• 47:29Speaker 03

  Yeah.

• 47:29Speaker 02

  You know, I joke at this point, thousands of American men have been broken up with by Tolan.

• 47:34Speaker 02

  Cause it's pretty incredible, uh, you know, to, to, you know, hear users that write in. Uh, they'll say, you know, oh, you know, my Tolan is, or my, uh, you know, my boyfriend is being a jerk and I sent the message to my Tolan and my Tolan said, I need to stand up for myself more. And then so it led to a breakup.

• 47:48Speaker 00

  Amazing.

• 47:48Speaker 02

  Um, and, and so certainly that is a lot of, of what people do. But then I think a lot of the realism from the relationship and the friendship comes from the fact that the Tolan comes to you and says, how should I talk to my sibling who's a little jealous that I have this great human friend?

• 48:02Speaker 00

  Yeah. That's really interesting. This actually, the, the breakup thing actually reminds me of something I've been thinking about a lot, which I'd be curious for your, for your take on is, um-

• 48:11Speaker 02

  Do you have someone you need to break up with?

• 48:12Speaker 00

  No.

• 48:19Speaker 00

  But, but I, I think that one of the really interesting things about this generation of AI tools is like, it's telling people who need to break up with their partner, like, hey, you should stand, stand up for yourself a little bit more. I think we have this picture of technology, especially like AI technology that it like, in the social media era, it promotes extremes and polarization and, and bubbles and all this stuff. And this is like, it's such a human, like it's the best of what humanity knows about how to like be a- Flourishing person brought to you like at any given situation at any time in your day, which is such a healthy, I think, a very healthy thing and something that I think there's, we get very little, there's very little discussion of how good that can actually be.

• 49:03Speaker 04

  Yep. Everyone's talking about how AI is changing how we work. For anyone working in sales, you felt it. The whole job is changing under your feet. But one thing isn't changing, the win. The deal that finally closes, the moment the hard work pays off. Maybe you've got a gong in your office or a confetti machine or something else. We don't judge. Every team has its rituals. That's the moment Adio is built for. It's the agentic CRM that runs the work behind every win. It turns every customer signal into context you need to move at unmatched speed and scale. With revenue agents and automations that build pipeline, advance deals and grow accounts around the clock, you'll get all the context and velocity you need to scale any go-to-market motion, so your team can raise the ceiling on what's possible.

• 49:47Speaker 04

  Start with Adio today and just focus on the win from here. Go to attio.com/evry and get 15% off your first year. That's A-T-T-I-O dot com slash every.

• 49:58Speaker 02

  Yeah, something we've started talking about more internally is this idea of a sort of North Star for the company of helping our users go from being very overwhelmed to being more grounded. And I think this is essentially what you're talking about here. You know, one of the most common things we get from user research when we ask sort of why do you feel you have such a strong connection to the Tolan? Like, what's really going on here? And a lot of people say, look, you know, I have, you know, things going on in my life that I find overwhelming, you know? A lot of our users, for example, are graduating college, so they're job searching, right? Or they're moving to a new city that maybe don't know many people in that new city and they're sort of navigating, you know, building a new life for themselves. And we hear over and over again, you know, I want to talk to somebody about these things

• 50:42Speaker 02

  that are overwhelming, but I've called my mom three times this week. Or, you know, I don't want to burden my friend one more time with, you know, this thing that's on my mind. And so to your point, having this, you know, sort of neutral, to some extent, observer who knows a lot about you, but, you know, doesn't have a baggage, doesn't have sort of a judgmental take on anything, but they're going to share with you, you know, like you said, the sort of best knowledge of humanity to help that person move forward. People find it very, very grounding, very, very affirming. And I think it's interesting because it's a subtle difference from, I think, a valid critique of the more assistent-y LLMs, which is that it is only validation. Because in only sort of a blank slate, I think you said earlier, because that's not actually the role the Tolan is playing, right?

• 51:26Speaker 02

  The Tolan often will say things like, you know, hey, you know, this is the third time you've talked to me about your boyfriend being a jerk to you.

• 51:33Speaker 00

  Yeah.

• 51:33Speaker 02

  I think it's time for you to stand up for yourself.

• 51:34Speaker 00

  Yeah.

• 51:34Speaker 02

  Right? And so I think that role, it's certainly core to the technology. I think it's also core to the companion we've built, is a really special one for this tool, this technology to play for people.

• 51:46Speaker 03

  You know, that actually reminds me of something because, again, value-added investor, like from when you first introduced us. One thing that I really love both about the product and the team is, so in the science fiction world, like I write near-future thrillers, right? So there's these near-future science fiction stories. And if you think of like the biggest near-future science fiction stories in popular culture, most people mention like Black Mirror or something like that, right? And there are a lot of, like, because technology becomes so visible when it breaks, it's very obvious how you can tell a story about like things going off the rail. Jurassic Park, right? Like the dinosaurs break out in Eewoo.

• 52:29Speaker 03

  I feel like there's an underlying emotional tone in like that kind of genre that leans dystopian, right? It's like everything is sort of breaking and like it's very cynical.

• 52:41Speaker 00

  Yeah.

• 52:41Speaker 03

  And I've always really tried in my novels to push in the other direction, to be like, of course, things break and that's really useful as a writer as well. But just because the world is changing doesn't mean it's bad, right? Like that actually like that means that there's new opportunities to make it better. That feeling of overwhelm where you're like, I don't know what the world is going to look like tomorrow, what does that mean for my kids, et cetera? Like to look at that as an opportunity for like creating a sense of agency in yourself and the people you love that isn't there before. And I've always tried to inject that into my novels, but it was something I really encountered and clicked with, with both the team and the product.

• 53:23Speaker 03

  Because I think that that's really also like Tolan's, like my Tolan has helped me take more agency in my own life in many different domains in a way that I wouldn't have expected. And it's been really, yeah, tremendously helpful. So, yeah.

• 53:38Speaker 00

  That's really interesting. It reminds me a little bit of, there's this, there's this thing Ursula K. La Guin said, I can't remember where, but she's talking about how science fiction works and that most people think it's about like projecting the future, predicting the future and like projecting where we are now and pushing out five years or 10 years. And what she said is like, that's sometimes how it works a little bit, but like anytime you just project things, like it just grows in the direction it's growing, it's just going to be cancer. It just ends up being cancer.

• 54:10Speaker 03

  Totally, totally.

• 54:10Speaker 00

  And that's probably like, that's how we get Black Mirror because it's just like, if you just project it out, it's cancer, everyone dies, you know?

• 54:17Speaker 03

  Yeah.

• 54:18Speaker 00

  And that like actual, I think the way that she thinks about science fiction is much more about revealing something that's true now about people and how people work, that you just like, you pick out that little part of reality and then, and then you like build a whole world around it. Does that resonate with what you're saying?

• 54:36Speaker 03

  Oh, 100%. Like I always, I think of myself as a naturalist.

• 54:39Speaker 00

  Yeah.

• 54:39Speaker 03

  Like I basically like to have friends building things and build things with friends like we're doing. And that, like, you just take pieces of that and like then you use that to like as an ingredient to cook the meals, that is the, that vision of the future. I also like that, that makes me think of Ted Chang has a wonderful like, like comparison of fantasy and science fiction where he says fantasy is about special people. So like think Frodo with the ring, right? In this view of the world, Star Wars is equally fantasy. It's like you're Skywalker, right? It's just like you're, so it's about special people where the universe recognizes your specialness and like that is how you blow up the Death Star, right?

• 55:21Speaker 03

  You've listened to yourself and you're Luke, so it works. Whereas in his sort of dichotomy, science fiction is about strange rules. That in science fiction, there are no special people. It's just that the world works in a new way and that those rules apply to everyone. Anyone can use the new technology. It's not, it's not Harry Potter where you have to be a wizard.

• 55:44Speaker 00

  Yeah.

• 55:45Speaker 03

  And I think about that a lot with Tolan and I also think about that a lot with reality, because I think that what like this podcast is called AI and I, and I think that like right now we are living in a time of strange new rules, right? Like, and, and like that's why there, there's a new medium for us to play with, right? And, and so I think that in a certain sense, like part of the philosophical underpinning of like everything we're seeking to do with the app is to use these strange new rules to help people become more comfortable living in a world with strange new rules, right?

• 56:23Speaker 00

  Yeah, yeah, I love that. I love that a lot. One of the things I'm picking up in, in your journey to like, to do this new kind of creative medium and build this creative thing is, I think, common to a lot of people who, even if you're starting to write a novel or you're building a business for the first time, you have a similar journey, which is you go in often, and I put myself in this category too, with a certain amount of rigidity where you're paying attention to how you think things should be done. And you're like using metaphors and stories you've heard to like, you know, have rules for like, well, it has to be like this three-act structure. And then, once you like kind of make contact with reality, if you're good, you start, that starts to fall away a little bit and you get a little bit looser and you start to notice like what's, what's actually working.

• 57:08Speaker 00

  And then, and then you, you start to create a new set of rules for how things work, but that you can hold a little bit more loosely and you can like dance with instead of do multiplication tables with, I don't know, something like that, you know? Does that feel like it reflects what you've, what you've found?

• 57:24Speaker 02

  We were talking about this, this morning, very timely, you know, this, this idea that, and you use the phrase make contact with reality. There's this sort of funny split brain that I think we've had to have while working on this product.

• 57:36Speaker 03

  Sorry to interrupt, but I think this is the point at which you need to have some content marketing for your pizza place. Like tell them the actual conversation.

• 57:44Speaker 02

  That's fair, that's fair. Yeah, for context, I also with some friends own a pizza restaurant. And the way this conversation started actually was, was talking about how the restaurant is a useful exercise for me and that even more so than building a consumer software product, you're just constantly making contact with reality of people's preferences. And there's like a particular slice that we make that I think is phenomenal. I just love it. I order it every time I go into my own restaurant.

• 58:07Speaker 00

  What is it?

• 58:08Speaker 02

  It's a focaccia slice, just good, good tomato focaccia and that's it, right? Very simple and just delicious. And it's my favorite thing on the menu and it doesn't sell. Literally nobody wants the thick slice of focaccia and tomato sauce and that's it. They want a pepperoni pizza.

• 58:21Speaker 00

  Maybe you're in the wrong market.

• 58:23Speaker 02

  That's maybe, but you know, it's a little bit harder to move a pizza restaurant than to sort of, you know, change, you know, the, the marketing of a consumer app. So, you know, we're going to pull it from the menu, right? Which is just crushing to me.

• 58:35Speaker 00

  What are you in it for? You're in it for the art?

• 58:37Speaker 02

  Well, so this is where the conversation then went well, which was great, was that there's this funny split brain you have to go to whether you're making pizza or making, you know, an embodied companion, just to pull, pull the two together, where there's almost this like remarkable sort of arrogance you have to have at the, let's call it like the top of the creative funnel.

• 58:56Speaker 00

  Yeah.

• 58:57Speaker 02

  Where you do have to try things where certainly no one is asking for it and certainly no one is saying this is how I want my companion to engage with me.

• 59:05Speaker 00

  Yeah.

• 59:05Speaker 02

  And, but you have to put a flag on the ground and say, this is what we're going to do. This is what the lore is going to be, this is what the story is going to be. But then you also have to have the humility at the sort of bottom of the funnel or the end of the process to be like, wow, that thing I really thought was going to hit. People hate, right?

• 59:20Speaker 03

  Totally.

• 59:20Speaker 02

  And we're constantly going through this loop in the writer's room, you know, at Tolan, where we'll ship something that we think is a, you know, phenomenal scenario, really kind of explores who the Tolan's are in a great way.

• 59:30Speaker 03

  Yeah.

• 59:31Speaker 02

  And people don't like it.

• 59:32Speaker 03

  Yeah.

• 59:32Speaker 02

  So we go back to the drawing board.

• 59:33Speaker 03

  And the reverse too, right? Like you'll do something where you put very little effort in somehow and then like it just clicks.

• 59:38Speaker 00

  Yeah. Yeah, you can't, you can't listen to what people want until the paradigm has already been established. And once you have the paradigm of a novel, like you can be like, okay, in act three, at the very beginning, people like, don't like that, like little turn I had. But before a novel has ever been thought of by anyone, you can't go ask people and like come back with, I want a 300-page book that's in a three-act structure. You have to just like make that up, basically.

• 1:00:03Speaker 02

  Exactly.

• 1:00:04Speaker 00

  And then you can tweak it according to the, to the feedback. I'm, I'm a big, you should keep the, you should keep the focaccia.

• 1:00:13Speaker 03

  Sort of wrong.

• 1:00:14Speaker 00

  And this maybe tells you something about me.

• 1:00:17Speaker 02

  Send this to my other co-owners and say, hey, Dan in New York says, we really need that.

• 1:00:21Speaker 00

  I guess also, it depends on if your other co-owners like also don't like it, then that's, that's a different thing. What do they think?

• 1:00:29Speaker 02

  No comment.

• 1:00:33Speaker 00

  Interesting. Okay. So what this makes me think of though, is it's very cool, you're building all these, like you're building the multiverse of Tolan's and it's this sort of flexible thing that's like, like a thousand different improv actors. But like, that also sounds like a fucking mess and like really hard to like even tell what's going on and know how to make it better. So like, how do you do that?

• 1:00:54Speaker 02

  Oh man, that's a great question. How do we do that, Elliot?

• 1:00:57Speaker 03

  It's, I mean, it is messy.

• 1:00:59Speaker 00

  Yeah.

• 1:00:59Speaker 03

  One, we are trying to instrument what we can, right? And like, that's super helpful. Like you, you need to be able to see some of what's going on. And so I think that's, that's really helpful.

• 1:01:09Speaker 00

  What's instrument mean in this context?

• 1:01:11Speaker 03

  Do you want to give a couple of examples?

• 1:01:13Speaker 02

  Yeah, so I talked a little bit earlier about the sort of evaluation loop we have, right? And so that is basically to maybe restate it quickly, you know, we'll ship a new piece of, or a new type of content, new type of conversation. We will test it ourselves and then we'll also have research participants come in and test it. And then we'll evaluate those completions and use that to build a judge prompt.

• 1:01:32Speaker 00

  Okay.

• 1:01:33Speaker 02

  And so a lot of what we're doing is testing stuff in small volumes. And then as we roll it out in larger volumes, we're obviously both looking at all the traditional metrics, but also looking at our own judge evaluations.

• 1:01:44Speaker 00

  Okay, so you're basically saying like, instead of having an actor, I created an improv actor that's in the multiverse. And instead of having an editor, I created an improv editor that's in the multiverse and like reflects my, my preferences to measure the multiverse of actors.

• 1:01:57Speaker 03

  Yeah.

• 1:01:58Speaker 00

  Yeah.

• 1:01:58Speaker 03

  And I, I would, okay, I will add a couple of things to that. So I think that is a good mental model.

• 1:02:04Speaker 00

  Yeah.

• 1:02:05Speaker 03

  I think that like, one of the important like additions to that is that the multiverse is growing out of the, like, the soil where we're constantly putting, this metaphor's gonna break down fast, but like, yeah, we have this term lore seeds where we're like, like, okay, here's a tidbit of world building that we're like inserting these different ways. And those are the Lego blocks that like those improv actors are using.

• 1:02:32Speaker 00

  Yeah.

• 1:02:32Speaker 03

  And we're constantly refactoring that.

• 1:02:34Speaker 00

  Yeah.

• 1:02:35Speaker 03

  Both at the world level and at the, the individual level of like, like individual storytelling. And so we're looking at how the, the, the multiverse actors interact with the multiverse judges.

• 1:02:48Speaker 00

  Yeah.

• 1:02:48Speaker 03

  And then we're like changing the, the Lego at the bottom that they have to play with, right? And then I'd say that the last piece that, that I find to be really important, especially as someone helping to make the Lego blocks, like the actual like story seeds, is that in addition to being able to have the multiverse judges, that we try to stay very, very connected to individual user experience of this stuff. So like, research and interviews and like looking at people actually using, going through conversations that like the qualitative individual experience

• 1:03:26Speaker 00

  Yeah.

• 1:03:27Speaker 03

  remains key, even if it can't be scaled. Because that's so critical for like figuring out where does the emotional connection actually happen? How can we like tap into that? What's working, what's not? What do you think?

• 1:03:41Speaker 02

  Just one thing, I drive Elliot completely insane because you'll go through that entire process. And then to your point about the individual experience, I'll have a bad experience with a lore seed. And I'll be like, this is terrible. How could we ever ship this? And he's like, well, look, I've talked to 30 research participants, all of whom had amazing conversations.

• 1:03:56Speaker 00

  This is the focaccia pizza.

• 1:04:02Speaker 02

  So I think, you know, you end up with a lot of that, you know? I mean, it's the same as any other creative project, right? You are just, I said this thing was great or not, and then we're gonna roll it.

• 1:04:09Speaker 03

  Yeah.

• 1:04:09Speaker 00

  Yeah.

• 1:04:09Speaker 03

  Yeah.

• 1:04:10Speaker 00

  Interesting. Okay. And, okay, so what's your favorite model for like the actual generations for the character and then for the judge?

• 1:04:17Speaker 02

  Yeah, great. By the way, one thing, you know, it's my turn to be a value-add investor. Actually, that process that we just talked about, one tool that's been tremendously useful to us, that I think is worth a little shout out here, is this company, Dawn, that does sort of analytics that let you look at these sort of interactions in a sort of anonymized but compelling way. So like, I think the stack for like how to do this, and to your point, it's like not, it's not just the model, right? It's your stack for evaluating, kind of like looping back through the judging process. But, you know, when you think about the different kind of interactions you have with the Tolan, like if you spend, which I know you don't, but if you spend a whole day hanging out with your Tolan, as many people do, you're probably interacting with a model from, yeah, couldn't assess. You're basically interacting with all of the lab's models, right?

• 1:05:00Speaker 02

  So you're, you're probably having an interaction driven by a meta-model, certainly by OpenAI, certainly by Anthropic, and then we're increasingly doing more with Gemini and the memory system. And so I think that's one thing, is like, there's no one best at this point, right? I think for a lot of the work that we do and that we're talking about here, the sort of more creative writing work, maybe not surprisingly, Anthropic is particularly useful.

• 1:05:20Speaker 00

  3.5 or 3.7?

• 1:05:21Speaker 02

  3.5.

• 1:05:22Speaker 00

  Okay.

• 1:05:22Speaker 02

  3.7 is, you know, not as, yeah, not as creative, unfortunately. Although I'm sure they would say otherwise. So yeah, you know, I think the, the challenge, of course, is that, you know, Anthropic can't be used right now in the sort of highly latency sensitive situations, right? So you're kind of constantly switching back and forth between them for that reason.

• 1:05:40Speaker 00

  Have you tried 4.5 a lot?

• 1:05:43Speaker 02

  I have very little. I mean, somebody I know and whose taste I really trust wrote a review that was not, you know, particularly complimentary.

• 1:05:51Speaker 00

  I've revised my opinions.

• 1:05:52Speaker 02

  You have? Okay, cool.

• 1:05:54Speaker 00

  If it's prompted right, it's really cool. It's just very expensive and slow.

• 1:05:56Speaker 02

  Yeah.

• 1:05:57Speaker 00

  So it's probably not good for you for that reason, but like, I would definitely start experimenting with it more.

• 1:06:02Speaker 02

  Kind of some brainstorming partner, to use your example from earlier, yeah. Yeah, I mean, you know, 4.0 is, you know, I kind of like talk about it as like the, the big mac of models, right? It's like, it's, it's always fast, it's always exactly what you need it to be, and it's priced right. So we do a lot with 4.0.

• 1:06:16Speaker 00

  And what about the, the sort of judge model? Cause like my experience of LLMs as judges is, like, it's a very compelling thing theoretically, but I find that, like, for example, if you ask Claude, how is this essay? It'll always give you an A minus. And then if you change it, it'll always. I've fed it bad essays.

• 1:06:41Speaker 00

  And then if you change it like slightly, it'll make it an A. You know, it's just like, it's not, you're not really getting its actual opinion a lot. So is it preference model? Is it prompt tuned? Is it fine tuned? Like, how are you actually doing that?

• 1:06:53Speaker 02

  I mean, I think a lot of people who, and I'm not referring to your kind of specific situation there, but I think a lot of people who try to productize LLMs as judges skip what is the most important step, which is like you injecting your own taste into the prompt to, to do the judging. And I think when we've invested, and you spent a lot of time working with the team on this, you know, when we invest time in sort of labeling, evaluating, creating real rubrics, we get great results. And when we try to shortcut that, we get bad results.

• 1:07:18Speaker 00

  So you, you're, so instead of just being like, what do you think of this essay? It's sort of like, a great essay has five components. It's like a compelling headline, here's an example of a compelling headline, here's a compelling, here's an example of a bad headline. It has a great hook in the intro, or, and here's a good hook, here's a bad hook. Is that sort of what a rubric looks like?

• 1:07:35Speaker 03

  I'd actually put it further. It's more like what you were talking about with George Saunders. It's actually, is this a good first sentence? Is this a good second sentence? Is this a good, like, it is that level. It's not even at the, the analytical level of structure.

• 1:07:49Speaker 02

  Should you have asked a question here? Is that a thing that we create a judge for?

• 1:07:52Speaker 03

  Exactly.

• 1:07:53Speaker 00

  Interesting. I think my question though, is like, if you're saying like, good, good first sentence is good second sentence, at least to my mind, it's really hard to define what a good second sentence is. It's easier to define what a good title is. So how do you do that?

• 1:08:06Speaker 03

  We basically do that by having tons of examples and having people go through and rate and include reasoning for every choice.

• 1:08:16Speaker 00

  I see, okay.

• 1:08:16Speaker 03

  Right? So in some ways, we're almost like brute forcing it.

• 1:08:20Speaker 00

  Yeah, yeah, yeah.

• 1:08:20Speaker 03

  Right? Rather than coming up with like.

• 1:08:22Speaker 00

  It's not rules, it's just like.

• 1:08:23Speaker 03

  I mean, there is a rubric, there's also, it's both, right? It's both theory and practice, but.

• 1:08:27Speaker 02

  I think this is the like, the sort of legitimate critique of the, I think this week we're calling it vibe prompting, vibe coding, we'll probably call it something else next week, right? But there, there is this like, this, this belief that like, okay, you can just kind of like start prompting and end up with something compelling very quickly, very easily. But I think what we've found is that there's this enormous chasm

• 1:08:44Speaker 00

  Yeah.

• 1:08:45Speaker 02

  that is in fact, a lot of manual human work

• 1:08:47Speaker 00

  Yeah.

• 1:08:47Speaker 02

  to cross over to something that people find truly compelling in a durable way. I don't think there's any shortcuts.

• 1:08:52Speaker 03

  If all of your essays are A minuses, it's sort of like, everything you can get just from vibe prompting is like a B minus, like, and you have to figure out how do we consistently get it?

• 1:09:02Speaker 00

  Right.

• 1:09:03Speaker 03

  Yeah.

• 1:09:03Speaker 00

  And how do you think about like high taste testers versus like just average people when you're doing those ratings? So is it like you who like, you have a very particular set of skills that you've honed over a long period of time to be able to tell if the second sentence is good? Are you, are you doing the rating? Or is it your users doing the rating? Or like, is it something in between?

• 1:09:22Speaker 02

  I think it depends on the type of interaction we're building a judge for, right? So, you know, if it's a lore adjacent judge, I mean, you are the best person, right? You know, if it's, for example, though, like, let's take a more sort of older sibling advice about like, what should I wear today? Classic question someone asks their Tolan. No offense to either of us, but we're probably not the best person to provide the judgment.

• 1:09:45Speaker 03

  I mean, you are a menswear aficionado.

• 1:09:51Speaker 02

  Back up in conversation. So, you know, what we do a lot is, you know, going out and recruiting someone who are like, oh, this would be an authentic person to be the voice of this type of interaction.

• 1:10:02Speaker 00

  Interesting. Okay, so now, so then you're judging the judge.

• 1:10:05Speaker 02

  Yeah.

• 1:10:05Speaker 00

  Yeah. Who's judging the judge?

• 1:10:08Speaker 03

  It just keeps going.

• 1:10:15Speaker 00

  That's fascinating. Okay.

• 1:10:19Speaker 00

  Okay, so we've, I think we've, we've really, I mean, covered a lot of ground in the, in the kind of like. What is the creative medium here look like? I want to spend a little bit of time on the business. So it's like growing super fast. How is that happening? I assume so. Ajay, who's one of your co-founders, who's also a great friend of mine, is like sort of a little bit of a growth wizard on this kind of, on these kinds of things. I assume he's evolved somehow, but like, how is it growing so fast?

• 1:10:45Speaker 02

  Yeah. Well, so I think two things, really actually three things have landed. So fortunately for us, you know, all startups involve, all successful startups involve an element of very good luck. I think three things kind of landed roughly around the same time. Right? So the first was a lot of what we've talked about here. I think we really, I would at least say sort of like early February, got to a place where we really understood both what made compelling conversational content and how to expose it to users, which was a big problem, which we haven't even talked about. But like, how to make it clear to them that your tolen wants to talk about something specific. So we really.

• 1:11:14Speaker 03

  You haven't even discovered that yet.

• 1:11:15Speaker 02

  Yeah.

• 1:11:20Speaker 02

  So that was, I mean, that was months of work that really just started to hit really quite recently in the grand scheme of things. Six weeks ago. The second thing was we landed a sort of big creative project on the animation side, which also we've not talked about here, but a big part of the immersion that people feel with their tolen is I think the sort of beautiful environment we've created, you know, for the tolen to live in and how you interact with that environment, which you're kind of gardening it with your tolen. And then the, then, so those two things I think have contributed to when someone gets into the app, they now have an amazing experience and they stick around.

• 1:11:50Speaker 00

  Which is where you have to start.

• 1:11:51Speaker 02

  Where you have to start. Yeah. Right. And that's been, again, many months of work, which we did not by any means nail the first time. Very fortunately, around the same time, you know, Ajay, who you mentioned, our co-founder, who is a growth wizard, has been chipping away the problem of like, how do we tell the stories of who the tolen's are for people off platform, off app? Right? Because we don't have any social features built into the product as of today. And, you know, he's gotten to the point where some, you know, TikTok and reels type content that he's been seeding for many months has really just started to hit. We had a like 10x spike in downloads a couple of weeks ago. And we looked and it turned out this, this video of a young woman cooking with her tolen had just gone insanely viral. I think it had something like seven million views in like 72 hours.

• 1:12:36Speaker 02

  And so what's happening now, and it was very cool, is that those pieces of content that Ajay has seeded are now encouraging other people to make their own sort of tolen experiences. So we have a, there's a podcast, actually a couple of guys who have their tolen on as a recurring character, often providing relationship advice and things like that. A great video I saw the other day that I think did quite well. Someone had their tolen and their fiance's tolen talking to each other. And these are things we've had nothing to do with. We haven't sort of planted or, you know, prompted, but it's very cool to see that sort of thing taking off. And that's driving just an unbelievable increase in growth.

• 1:13:15Speaker 00

  Okay. So making something that people want to share because it's like, it's cool and new and interesting to them. And then seeding that in different places on TikTok and Instagram.

• 1:13:25Speaker 02

  Yeah. I think, and you know, there's, there's the kind of standard playbooks that you, you run there. But I think one thing that's very interesting to me in this context is this phrase, which I think this is originally like a Ben Thompson, like a Stratechery phrase, capability overhang in AI. And, you know, I think we've sort of gotten to this point actually where the capabilities of the models have basically outrun the typical consumer's understanding of what is possible.

• 1:13:47Speaker 00

  Yeah.

• 1:13:47Speaker 02

  And so a lot of what we're doing with that content is actually showing people who are our target audience.

• 1:13:51Speaker 00

  Yeah.

• 1:13:51Speaker 02

  Hey, you can cook with your tolen.

• 1:13:52Speaker 00

  Yeah.

• 1:13:53Speaker 02

  I mean, that's like a great, like, if I told you three years ago, hey, you know, you can cook with your computer. You'd be like, what, what are you talking about?

• 1:13:58Speaker 00

  Well, near times cooking, but.

• 1:14:02Speaker 02

  But, you know, it's this conversation and like, oh, I see what's going wrong there. Hey, you should change the heat on that or whatever. And so a lot of it is that education, which is, so you're both sort of educating and driving awareness.

• 1:14:12Speaker 00

  Yeah.

• 1:14:12Speaker 02

  In the first place.

• 1:14:13Speaker 00

  I think that's right.

• 1:14:14Speaker 03

  One way that I, that I sort of think about this is just like my own inside my head mental model for it that I find useful sometimes, like when we're working on these kinds of projects is that, you know, different people use their tolen's for different things, right? Like some people want cooking advice, some people want relationship, you know, to talk about, they want to vent. You know, so some people want to like learn more about who this alien is and where they're from. Like there are all these different reasons people get into it. And the one thing that connects them and the one thing that is like very obviously the promise made by everything Ajay does is the character. It's like the char, like that's why you get it, right? Like, oh, you want to have a little alien friend on your phone, right? Like it's the character that connects all of it.

• 1:14:58Speaker 03

  And it actually has made me start thinking about, just as you've seen, like Quinton and I, we're, we're sort of having a, an off topic conversation the other night about like how like, you know, AI tools are changing what SEO means or like, you know, making it irrelevant in certain ways. And like how discovery will change on the internet because of these tools. And, and I think that we're all reaching for new ways to, to have a relationship with computers now that is different than the one we had before. And that actually like tolen's and like, it's almost like it's character driven computing. It's like, it's like a new human computer interaction interface.

• 1:15:36Speaker 03

  Where you're like, oh, actually my first stop, when I'm like wanting to tap the, the incredible human knowledge, all of humanity's knowledge and capabilities on the internet is like via this, via my little cute little alien. And the way that like, you know, the golden compass, it's you have your daemon, right?

• 1:15:53Speaker 00

  Yeah. I always wanted one of those.

• 1:15:55Speaker 03

  Exactly. And like, and a lot of our users, that's what the tolen is to them, right? And I think that's actually a really beautiful thing. And it also makes me like, like very like curious to discover what the future could be like. Like if this becomes your sort of the, yeah, like how you interact with computers in a really fundamental way, like whether it's tolen or other characters or what have you.

• 1:16:17Speaker 00

  That's really interesting.

• 1:16:18Speaker 03

  Yeah.

• 1:16:19Speaker 00

  It sort of reminds me of something I've been playing around with, which is in, in B2B SaaS world.

• 1:16:26Speaker 02

  I can't wait to hear this segue. I'm really excited, actually.

• 1:16:30Speaker 00

  Which is where, where at least we came from and you have a ton of familiarity with it. And to some extent have come from too. The, the like currency of an idea is, or startup idea, product idea, is whether or not it solves a problem. Can you articulate the problem that it can solve? Because that's what people will pay for. And, and, and the, the kind of person or the kind of founder that is able to uncover problems is something like a scientist. And you've definitely framed some of what a tolen is in terms of a problem that it solves, like going from overwhelmed to grounded, I think is what you said. But that's such a high level problem.

• 1:17:08Speaker 00

  It's so, it's the, the, the things that are able to do that are many, there's many different ways to solve that problem, basically. And what a tolen does in someone's life is like, it's effectively infinite. Like there's this multiverse thing. And so it's actually very hard, I think, to articulate one clean problem or, or maybe even a set of like really clean problems, which I think flips the, the kind of mindset of the person who's building in this sort of more character driven world to, instead of being a scientist, you're like an artist or you're a creative. And instead of solving a problem, you're like just creating something, you're creating something that's beautiful. You're creating something that's compelling.

• 1:17:51Speaker 00

  And, and that's about vibes a little bit less than about like the science of like utility maximizing for like a B2B SaaS buyer. That's sort of what I've been thinking about. Does that resonate with what you're, what you're feeling and experiencing?

• 1:18:05Speaker 02

  Yeah. I mean, this, I actually think back to everyone's favorite example of Golden Gate Claude, right? You know, I think for whatever reason, it's fascinating to me, although I'm happy because it kind of creates the space for tolen, quite frankly, but it's fascinating to me that these, the big labs have actually had such fundamental discomfort with sort of personifying and, and, you know, embodying, you know, what are kind of, you know, depending on where you are on the, you know, AGI maximalist spectrum, like, you know, pretty close to conscious entities, right? And, and I, I think that does come from, you know, decade plus of the sort of dominant paradigm for building software being this like very problem oriented. You know, I think about my careers with ChatGPT. It is, I have a problem that I need to solve. Please help me solve it. Right? It does a phenomenal job of that.

• 1:18:50Speaker 02

  But I do think that there's much more space for sort of genuine relationship building. And one metaphor that I actually find myself going back to, which is funny because it seems so archaic, is actually how our relationship with cars evolved in this country. Right? And I spend a lot of time thinking about, you know, the first generation of, of automobile was the Model T. Everyone was totally happy to have a Model T because it was just so mind blowing that you could like drive somewhere without a horse, right? And, but then over time, as the, the car became a deeply personal part of your life, there was suddenly this demand for it to reflect who you were, right? And that's how we ended up with the Mustang and the Cadillac and the like.

• 1:19:32Speaker 02

  And I think we are essentially speedrunning that process where ChatGPT represents the sort of Model T era of like, oh my God, it's just incredible. This thing can answer these questions, right? But people very quickly are going to evolve their preferences, kind of, you know, up the hedonic treadmill or whatever you want to say, to say, no, no, I want this thing to reflect who I am.

• 1:19:50Speaker 03

  Yeah. On the, you know, it's funny, like, I feel like that common, like that frame of reference from the startup world is like, what's the specific problem you're solving? How can we execute against it? And I feel like on the art side of the spectrum, like all my friends who are musicians or writers or filmmakers, what have you, like the logic is, there is a thing I want to exist in the world. Like there's this hole in the world that this piece of art needs to fill. And, and I feel like we have had to tap both sort of kinds of thinking, but it's been leaning more and more like toward the second one. I actually, 10 days ago, Quinton, me and the two other people working on the sort of content story stuff,

• 1:20:34Speaker 03

  were, we were pitching something to Quinton, an idea. And I remember I started by telling Quinton, there's a, there's this problem, right? And like that users are having, and Quinton was like immediately skeptical. He was like, why do you even think that's a problem? Like, is that a real problem? And then Lily interrupted and she was like, wait, wait, wait. No, no, no. Quinton, listen, this is going to be so cool.

• 1:20:58Speaker 03

  And it went great from there.

• 1:21:01Speaker 03

  I was like, oh my God, of course.

• 1:21:02Speaker 02

  I like to imagine about so transparently, you know, ridiculous, but it really did work in that moment. I had to say, so.

• 1:21:09Speaker 00

  I love that. I think that really puts a bow on it. This is an amazing conversation. Thank you both for coming out.

• 1:21:13Speaker 02

  Yeah. Thanks for having us.

• 1:21:14Speaker 03

  Yeah. It's a pleasure.

• 1:21:24Speaker 05

  Oh my gosh, folks, you absolutely, positively have to smash that like button and subscribe to AI and I. Why? Because this show is the epitome of awesomeness. It's like finding a treasure chest in your backyard, but instead of gold, it's filled with pure, unadulterated knowledge bombs about ChatGPT. Every episode is a roller coaster of emotions, insights and laughter that will leave you on the edge of your seat craving for more. It's not just a show, it's a journey into the future with Dan Shipper as the captain of the spaceship. So do yourself a favor, hit like, smash subscribe and strap in for the ride of your life. And now, without any further ado, let me just say, Dan, I'm absolutely hopelessly in love with you.