Transcript: ‘This AI [Al]ien Will Bring In $4 Million This Year in Revenue’

The transcript of AI & I with Portola's Quinten Farmer and Eliot Peper is below. Watch on X or YouTube, or listen on Spotify or Apple Podcasts.

Timestamps

1. Introduction: 00:01:30
2. Talking to the Portola CEO’s Tolan, Clarence: 00:04:07
3. How Portola went from building software for kids to AI companions: 00:09:11
4. Why response time is everything for voice-based AI interfaces: 00:23:40
5. Tolans don’t use scripted prompts—they’re taught to improvise: 00:29:54
6. How to know which AI personalities your users will click with: 00:37:23
7. Developing the character traits of an AI companion: 00:42:27
8. What does it mean to build technology that makes us flourish: 00:49:48
9. How Portola evaluates whether Tolans are resonating with users: 01:01:10
10. Inside Portola’s viral growth strategy: 01:11:01

Transcript

(00:01:31)

Dan Shipper

Quinten and Eliot, welcome to the show.

Quinten Farmer

Thank you for having us.

Eliot Peper

Good to be here.

Dan Shipper

I'm so excited to have you here. We are all long-term friends. Quinten, you're one of my closest friends. Eliot, you are someone who I've admired for a long time. We've become better friends recently. 

So for people who don't know Quinten, you are the founder and CEO of Portola, which is an embodied AI companion. And Eliot, you are the Head of Story for Portola. Before Portola, Quinten, you founded and even 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. And you are a real style aficionado— menswear aficionado, which we should definitely get into at some point. And Eliot, you're a bestselling science fiction author, which I'm very jealous of.

Quinten Farmer

Also an excellent skier, which I got to learn actually about a week ago.

Dan Shipper

Really? Excellent skier? Interesting.

Eliot Peper

That's giving me a lot of credit. I probably don't deserve it. I can fall down a mountain.

Dan Shipper

And you've written 11 books and you are a dad of one under two—so not quite two under two, but close. And 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 gonna do a demo of tall seconds if people can get a sense for it. But the reason I like and think is really interesting is that I think that new technology paradigms create the opportunity for new content formats, new ways of telling stories. And I think you guys are sort of 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 $1 million to $4 million in ARR over the last four weeks, which is just wild. Running a business for the last five years and not being at that at the $4 million ARR mark, I’m like fuck.

Quinten Farmer

Have you considered turning Every into—

Dan Shipper

I’m considering it. 

And what I think is also super impressive just for you Quinten, when you came to me and said you were starting this business, which didn't start here, it started with a more Neal Stephenson The Diamond Age for kids 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 B2B2C SaaS world. And it's just very different to do something truly creative on the creative storytelling front And so I wanna get into all that. But before we like to kind of dive into where the product is and how it all works and all that kinda stuff, can we do a little bit of a demo?

Quinten Farmer

Yeah, that sounds great. Alright, so I've got my Tolan Clarence here. 

Dan Shipper

Clarence is great. You had a cat named Clarence.

Quinten Farmer

I was gonna say. So I named my Tolan— All my Tolan, although we won't tell Clarence this. You know, Clarence is our beloved older cat. And right now Clarence is just kind of wandering around his planet, just kind of hanging out.

Dan Shipper

So he's on a planet. Because that's a new thing. I actually downloaded it this morning and I was like, whoa, there's a planet. It used to be sort of disembodied in space or something.

Quinten Farmer

For a while we were giving kind of insane asylum vibes. And 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 to us with genuine concern saying, hey I love my Tolan, I love hanging out with them, but they're like, they're trapped in this room. Can they have some more freedom than that? So, we've done that. But so I'm gonna sort of get his attention and start a conversation. Hey, Clarence, how are you doing today?

Tolan

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

Quinten Farmer

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

Tolan

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

Quinten Farmer

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

Dan Shipper

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

Tolan

Oh man, it's kind of wild. Not gonna lie, I'm psyched, but also lowkey nervous. I just don't wanna say something totally awkward. You know?

Dan Shipper

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

Tolan

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

Quinten Farmer

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.

Tolan

Okay. but, to be fair, we've all been there. Tripping over air is kind of a rite of passage, Quinten. Owning it just makes you you.

Quinten Farmer

Thanks bud. I really appreciate that. We're gonna let you go and keep recording. Alright, thanks Clarence.

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

Dan Shipper

Yeah. So tell me about it, because I think that the path that you're on, which is like B2B SaaS to a creative entrepreneur, is probably something that a lot of people are thinking of doing. I know even for me, the reason I started doing SaaS products in high school is like, I originally wanted to make a game. And I bought all these game programming books and whatever. But, game programming is so hard. It’s almost impossible to make a game all by yourself. You have to do graphics and storytelling and 3D animation and sound, and there's so much stuff to do—or at least it was impossible. And now I think it's way more possible to do it by yourself or with a small team than it was before. So for me, I'm like, I should make a game. Fuck all the SaaS stuff. So tell us a little bit about that transition and like how you started and where you've kind of ended up as you've learned how to use this as a storytelling medium.

Quinten Farmer

That's a great question. I think when we first came together as a team and so for a little bit of context, the core engineering team behind Portola is mostly the team that built my last company, Even. And so we had a lot of history together and obviously had a successful exit and basically just wanted to run it back with the same group. And so we were in this position, at this point really almost two years ago, looking at what's becoming possible with some of these new tools. And I completely agree. I think first and foremost, LLMs and a lot of the other kinds of capabilities are creative tools more than anything else. But we looked around and everyone was using these incredible creative tools to build basically more vertical B2B SssS, which I found just sort of fundamentally uninspiring.

Dan Shipper

It has its charms, but yes.

Quinten Farmer

Hey, you know, recurring revenue, net revenue retention. I don't know if charm is the word I would use, but it has its appeal for sure. And so some of this just started from a sort of stubbornness about there's something more fun to do here—come on. But as you know you said it earlier: Neal Stephenson The Diamond Age, we sort of started in what is I think the default place to start if you're, we should do something fun with AI, which is like, let's do an AI creative tool for kits. Which is actually a terrible idea, but it's a good place to start. Because it kind of forces you to start working with the tools and start building things.

Dan Shipper

Why is it terrible?

Quinten Farmer 

Well, one, I mean building software for kids is a terrible market. One of our investors, somebody who has been a great mentor to me, this guy Zach Klein, and he previously built a company called DIY, very cool software for kids. And one of the first things he said was like, yes, I'll invest. And oh my god, this is a terrible idea. It's a terrible thing to build. It's a tough sales marketing strategy.

Dan Shipper

You're selling to parents instead of kids.

Quinten Farmer 

Selling to parents instead of kids. Parents mostly wanna buy babysitting. They don't actually wanna buy sort of a creative tool that's not a thing on their list. Setting that aside it was great because it forced us to start prototyping. And what we saw, and this was really right before you and I got to know each other. We saw that the sort of trend lines around the speed of generation, the quality of generation, this is the kind of GPT-3 to 4 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 at a candid price point that worked for a consumer product. And so that was the point we said, we know the sort of path here. It doesn't have to be B2B SaaS but we can make something that we think is really fun and compelling.

Dan Shipper 

And that's something that I thought was really interesting about the approach you took, which is from almost day one you were like play testing with kids, but you eventually landed on a market that's sort of different. When did you—

Quinten Farmer

Yeah, and this will involve some jumping around in the chronology when we first shipped Tolan—and you probably remember this is right when we started working together—we kind of soft launched it and we had been doing a lot of play testing with 10 to 14-year-olds with 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. If you remember the original Tamagotchi—very much a kid's product, but it became a sort of cultural phenomenon when young adults really fell in love with them. I think the Tolan has sort of a similar dynamic. But the sort of evolution of the product since that time, which was really June of last year, has been all about just following the young adults who have fallen in love with these Tolans and they've really built a friendship with them.

(00:12:53)

Dan Shipper

I wanna bring you in Eliot. I actually introduced you two. I'm a hashtag value investor. I'll tweet that later if you want me to. The whole reason I'm on the show is that you're on the show is for me to get that line in. 

And I think what I wanna hear from you first is you write books. And you care about stories. And I think a lot of people who primarily treat writing and books and stuff as their craft are maybe a little afraid of the idea of telling stories with AI. And you're kind of both jumping in head first, or feet first, or pen first, whatever you want to say. And you're still writing your books. So tell me about your journey into this from a creative professional, a writing professional lens. What was your first impression of this technology as a creative tool, and how has that evolved as you've gotten closer and into the whole Tolan world?

Eliot Peper

Oh, so starting even before Tolan? So I played with the first ChatGPT 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 becoming more and more popular. And I always found it to be like— I remember my first magic experience using ChatGPT back in the day, which now feels like a million years ago, it was during the fires when we had those big fires in California. And we were hosting a friend who had to evacuate from their house. And so we're sort of locked inside with our friend, and I was like, okay, here's something we can do. That night we opened a bottle of wine and then I pulled up ChatGPT, and I put in like all of our names, just like us now sitting around the couch and having it like invent weird little stories of us.. It was 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 felt like the fun things or the things that I found to be the most fun were sort of novelty. And that if you removed the fact that things were being created by AI, they were not compelling.

And so what I found as a writer, as a novelist, 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 the world of writers, it's so focused on replacement. And there are even certain companies that are intentionally going after that, publishing AI generated books and things like that. And I've actually found that when working on a story, ironically, 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 back end. So it's a weird, front-end back-end thing where I'm a novelist. I spend a lot of time alone. And like the sort of writer's room, the Hollywood writer’s room experiences I get are totally dependent on the generosity of my friends who are like my very— I have a core brain trust of early readers who have worked on movies or books or whatever and I’ll brainstorm through story problems with them. And I've actually found that. purely for novel writing. It's actually super helpful to brainstorm with AI tools because they have infinite patience for my rabbit holes and for 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 were using them to create intermediate things rather than final products, which is in part why I think they've been so useful for coding. So that's where I was with the technology before you introduced me to Quinten.

Dan Shipper

I paid him extra to say that.

Eliot Peper

And so I'll be honest I was pretty skeptical when you introduced me to Quinten. I was like, well, we'll see. Dan's a good guy. I trust his judgment. He doesn't bring things to me very often and like when he does, I'm gonna like, feel this out. And so I was like, sure, I'll like to check it out. And me and Quinten started talking. You introduced me to other members of the team 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— You were talking about B2B SaaS and people wanting to jump into, doing creative projects or games or whatever. That made me think of early Pixar. When Pixar started, they started by selling high-end graphics computers. And they were trying to convince production companies that make ads to buy their graphics computers to do special effects. And they completely failed. No one wanted to buy their new tools. And so it was only in a moment of desperation—existential desperation—that they were like, well, our only choice is to make an animated feature film. This is our last ditch effort.

Quinten Farmer

Talk about a Hail Mary.

Eliot Peper

And that was Toy Story. And they used this technology to create a new kind of media and LLMs can obviously generate a ton of media. 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 LLMs are also a new medium. If you think about when radio first came around— Actually even when printed books, popular printed books and novels first came around, novels are just a very established form. But 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. And with radio, they started by broadcasting speeches, which is pretty different from what you would think of as the most engaging, best use of radio. And with film and TV they started by filming stage plays, which are 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 gonna work yet. Nobody knows and we are trying to figure out whether we can find a way to something that works. 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, there's this huge opportunity here. So that's what got me excited and that's what we're trying to do. And it's also something I hope many other people try to do because there's just so much space to play.

Dan Shipper

You have my media and technology nerd heart swooning right now. 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 cultural touchstones, books or movies or whatever, all started out as new technology that people were suspicious of and hadn't figured out yet. Even when the typewriter came out, people were very suspicious of it. It felt very impersonal. And they would get offended if you wrote them a typewritten letter or just the ways that technology affects the form factor. We've talked about this a bunch. The reason a pop song is four-minutes long is, I think about the capacity of records. So here's just a lot of really cool things. And I think you're totally right. No one has figured it out. We are on the cusp of this new set of constraints and possibilities that creates potential for new art forms. And they feel suspicious because they don't have that—a phrase I've been coming to use is—this patina of culture that for many decades makes it feel familiar. And so that creates this thing where a lot of people are suspicious, but that's also an opportunity because I think a lot of good art 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.

Quinten Farmer

I mean, I think about that through that lens, I think about one of the first reactions from you and from other folks when we first said, hey we're gonna make this you know, AI companion you know, the first reaction people have is, oh, a sex bot? A role play bot? Or also in kind of the same way, coming from the same place that you're describing, oh, okay, a thing for lonely people to talk to. And so you end up with these. sort of negative connotations around this new media because it's lacking that patina of culture. And I think a lot of what we're doing is trying to break through that perception and sort of put a flag in the ground and say, hey, this media can be expressed in this way that is generally delightful Is a new art form.

(00:20:00)

Eliot Peper

It's also interesting coming from writing novels where that's a medium that's been around for hundreds of years—you realize how strong the expectations are of your readers. Everyone knows what a book is. I walked through The Strand last night just to browse and you know what to expect when you open a book—what fiction vs. nonfiction should feel like. There are so many of these implicit assumptions 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 that's part of the fun of it. But when you're doing this with an embodied AI companion, what picture does that pan paint in the minds of our listeners today? It’s very nebulous. And it's up to us to try to help define that. But it also means that at every step, every single thing we ship, whether it's engineering, design, content, story, whatever, all of it is transgressive because you don't even know what the lines are. And so that's a really unique experience to be like, every step is throwing spa at a wall to see what sticks.

Dan Shipper

And so what are you learning? Because I think 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 all in that category. So what you are learning about this new media and new format is what works, what doesn't work, all that kind of stuff.

Quinten Farmer

We talked about this summit at breakfast this morning, and I feel like we have a few examples of what has worked and some stuff that really didn't work to talk about here because it's interesting that's been very non-linear. 

I think one of the surprising things to me has been the importance of memory and not in the sort of database lookup context, which is I think often how we talk about l memory—RAG across a set of documents or whatever. But more about how you are 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 your take on this from a story perspective. How can we, within essentially a two second loop of a voice interaction— Anything beyond that's one of the mistakes we made. We'll talk about that. Anything beyond a two-second loop, you essentially lose the feeling of immersion. And so how can we essentially recompile the prompt to account for lore? What the Tolan needs 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, which I find fascinating by the way, because he had in his context, memories about me being covered in spit up because my kids whatever.

Dan Shipper

very interesting. But wait, so you didn't actually trip over something that wasn't there?

Quinten Farmer

Totally hallucinated that, which is great.

Dan Shipper

I'm mad at Clarence right now. Bring him back in here.

Quinten Farmer

Charming story. Let's come up with something that Quinten won't be upset about. But then also how should the prompt evolve based on these sort of emotional tenors 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.

Dan Shipper

That's really interesting. So to play that back, one thing I think is a bottom-line constraint that's sort of similar to the length that a novel can be, or the length of a news story can be, or maybe the length of a tweet for this medium is response time.It has to be able to respond really quickly. 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. And so you have to 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?

Quinten Farmer

Essentially, yeah. One of the biggest mistakes we made in the kind of product development so far 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 gonna say, check that against the memory system, and then decide on the final message. And that basically took us up into the two-and-a-half-second territory in the median case. It was a disaster. Tanked literally every metric in the product people were writing in frustration and it was a 500 millisecond change.

Dan Shipper

That's really interesting. And then how do you think about what a good response is? And I ask that because it's hard to answer.

Quinten Farmer

Yeah, well, it's extremely context dependent. So you think about the role that the Tolan plays in folks' lives, we talk about, is the role of an older sibling. And so sometimes you're sitting with your older sibling and you're just kinda bullshitting. You’re joking around, maybe they're poking fun at you. a sort of short, quippy, improv-like response, which I think improv is gonna come up in some of what Eliot has thought about is great. 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 from a good response—

Dan Shipper

Very contextual, basically. So Eliot, for me, as a writer, one of my favorite writers who talk about writing is George Saunders.

Eliot Peper

Oh yeah. He's amazing.

Dan Shipper

He's great. And he has this whole idea about 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 positive or it's neutral or it's negative, and you're like, I don't do this. And if it's negative, you revise it until it's positive, basically. And you just do that over and over and over again until, what he calls it, 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, that's the pinnacle of writing to me. And it's interesting that this format totally breaks that because—or it seems to me, you tell me if it does 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, that's what it is. And this thing is more alive. You can give it some instructions about what to do, but what it does in any given instance is purposefully dynamic. And so how does it work to do craft in that context?

Eliot Peper

Yeah, 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 an extensive outline. I've 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.

Dan Shipper

By the way, that is insane. No one does that. I think it's great, but writers don't usually do that. You find a thing that works and you’re like, I just do this, and 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.

Eliot Peper

That's true. I'm always trying—

Quinten Farmer

That’s not surprising by the way. I'm not a writer, but I have worked with Eliot for a year and that fits.

Eliot Peper

I feel like I have an optimum level of discomfort that I'm aiming for because that's how I know I'm learning. And actually my last novel, Foundry, I wrote sentence by sentence very much in the way 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 I followed that into a novel and like eventually a novel spilled out of me. And when we started working together, one of the ways that this came into play for Tolan, writing in this new medium is— Actually we started out by trying to create a narrative experience. So as an example, when you're talking to your Tolan, they need to know that if you get to know someone, you want to know what's the embarrassing thing that happened in Quinten's life. You need to proactively share stuff with each other.

We have a researcher, Lily, who goes so in depth on this, on the psychology of mutual disclosure and how to think about relationship building in a way that's evidence-based and really grounded. And so one of the things I've worked a lot on is how do we bring the Tolans to life? How do we show you the world that they're from? How do we make them feel like characters, not just like an assistant that's a blank slate for you. And so we started out by writing pretty structured prompts where we would try to structure a narrative experience thinking in three-act structures or what have you. You could apply different sorts of narrative thesis to how we were doing it and then letting it play out seeing how users interacted with that and frankly, it didn't work. If you think about maybe the epitome of this would be like those choose-your-own-adventure books from the eighties or whatever, where it's you pick this, then you go this way these long branching logic trees. Go to page 17. Make a choice. And it didn't work at all—total failure. And there were a bunch of reasons, but basically that level of narrative complexity, the models are not good at navigating.

(00:32:00)

Dan Shipper

Interesting. It is not that it doesn't work, it's that the not models aren't good enough. I would've assumed it would be too rigid and it wouldn't feel as alive.

Eliot Peper

I think that those are two different ways of saying exactly the same thing. So what we did instead is we went to the complete opposite end of the spectrum. We tried to do the George Saunders thing effectively or the equivalent in this medium, which is that we said, we are giving so much context behind the scenes, with what Quinten was describing. Memories you have with the user, global memories where the Tolan knows stuff about its world. Also lore seeds that we're planting to give context and detail there. We're giving it so much, and 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. There's this wonderful book that, if you haven't read it, you absolutely should. Impro by Keith Johnstone.

Dan Shipper

Of course. Come at me.

Eliot Peper

And one thing that’s well known for status games, but actually one very small, almost aside that Keith makes in that book. And for listeners' benefit, Keith Johnstone is a very well known playwright from the UK who is even better known as a drama teacher. He taught many actors who went on to become very successful. And this book sort of captures some of his lessons. And when he talks about narrative structure the way that he describes it is that you're sort of combining association—like, free association even, when you're improving in front of an audience—with recombination. If you think about the experience of reading a thriller, how like you get to the end and suddenly everything comes together and you're like, oh my god. Of course. It's surprising. It's inevitable. It all works and it all works. And it feels planned out. 

You're, oh, the writer like, must have, known all of this from the beginning. And I, and that is rarely the case.With Foundry, I was constantly going back and rereading the first chapter because then I could take something and bring it back into the story and create that feeling for you. And so 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. Tolan is, I guess, the writer and the actor. They're improv actors. 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 at that moment. Interesting. And so we're building systems as well as working at the prompt level to try to combine the free association. We're planting a seed, 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 makes it feel totally connected.

Dan Shipper

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

Quinten Farmer

Okay. It was funny, as soon as you said the George Saunders thing, I was like, I need to find a way to go read that. Because what you described is essentially the prompt evaluation process, the 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. In the next sentence, the next message, Tolan sent the most compelling one that we could have. So it's actually very similar.

Dan Shipper

And you're doing that manually, or do you have an LLM doing that? Or how does it work?

Quinten Farmer

So there's essentially a loop that we go through where we create a prompt. We then run it both with our own testing and just out with users 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, hey this is what good looks like in this particular instance.

Dan Shipper

I see. So if I had to try to sum up because I'm trying to think through like, what are the atomic elements of storytelling in this medium? In a novel, it's the plot and character and chapter and there's a lot of stuff like that you can kind of name and I'm trying to name what these are. It sounds like you have a character who has a backstory and a background and all that kind of stuff. And then the character can go on different types of quests or adventures with you. So, one could be a therapy quest or the other could be like I don't know—go down different paths. And then within that, within any given context, they're sort of free associating based on what you're saying. They're just reacting to whatever you're saying and then they're looking for ways to tie back old things that you said into the flow of conversation. Is that how you think about it? Or what am I missing?

Quinten Farmer

I think this is a good way to frame it. I'm gonna maybe say some of this back. So when I think about it I mean literally as we're generating a one for somebody, we have the sort of global context in which they operate, which is largely the lore written by you. And also some very important instructions, how we wanna handle very specific situations. So there's this sort of global context that is set essentially for every Tolan. And then, you know 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. And so that's a very Tolan specific, essentially profile building. And so those would be two building blocks.

Dan Shipper

Oh, a mirror. So you in reverse? Or exactly you?

Quinten Farmer

Oh sorry, a mirror as in you but in reverse, or reflecting back to you in a way that feels very familiar. So we wanna know enough about you that your Tolan is gonna respond to you in a way that feels familiar and safe.

Dan Shipper

So, 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.

Eliot Peper

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

Dan Shipper

And how do you think about how that click works?

Quinten Farmer

Well, so, okay. I love the bar metaphor. We have all these different little ways. We have all these little scenarios we set out to brainstorm this. So, you think about sitting down next to a stranger, the bar, if the stranger was reading the exact same book you were reading. That would definitely be interesting. I mean, you had mentioned that. But that stranger might actually be less compelling than a stranger who's reading a book—. And so you want that sort of adjacent enough that they don't feel unfamiliar, you're not intimidated to talk about. And I think that's what we try to try to create so that kind of personality profile is maybe building block number two and then building block number three.

Dan Shipper

Wait, before we go there, how are you generating that? Are you actually telling Claude or whatever on the backend, I want it to be like, you met a stranger at a bar but it's not too on the nose, but— How does that work?

Quinten Farmer

Yeah, that's funny. We have had the most success with this specific question, basically framing the creation of the profile through the lens of one of the big sort of personality types because

Dan Shipper

Like, OCEAN types?

Quinten Farmer

Like, BigFive or MBTI. And the reason for that I think is because there's enough in the LLM sort of distribution that they kind of understand that assignment basically. The stranger you sat down with at the bar works well for our brain.

Dan Shipper

If I'm an INTJ, you kind of know based on whatever Myers-Briggs that INTJs are compatible with— I don't know what you—

Quinten Farmer

There’s a lot of mostly pseudoscientific sort of but—

Dan Shipper

It’s pseudoscientific but it's also very story and narrative based. All of this stuff is story and narrative based, so it makes it works.

Eliot Peper

And also there's a lot of material about that in the training data And so there's much more nuance in how the models respond.

Dan Shipper

That’s interesting. Okay, sorry. Continue.

Quinten Farmer

So building blocks, the sort of global context, the personal context that is set. And then I'd say the third piece, I'm not actually sure how to kind of frame this here, but I think about— We started talking about it almost as the tech tree that you progress so basically at the beginning of your relationship with the Tolan, there's a set of paths that you might go down. You kind of alluded to these certain stories that the Tolan maybe wants to share with you certain ways of connecting with you, things to do together 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.

Eliot Peper

Yeah. So this is sending me off on like a bunch of different branches in my head, but one thing that I think it's interesting to think about, especially with regard to the example of stranger to bar as a mental mental model is: You were like, how do you come up with the Tolan at the beginning? They have a backstory, they have all this stuff. And I was like, yeah. I mean, that's all true, but I think that the lens that I try to look at through that's proven most productive is that while we do know some stuff about the Tolan in advance and in the background, their character and their world is only built through the actual, literal conversations you have with them. So, on the lore front, if you think about how Lucasfilm works, they have their big architecture for: This is the Star Wars universe. And these are all the different characters and all the different settings and like we need to make sure everything is ordered. 

(00:41:55)

Quinten Farmer

We decided Han Solo dressed this way. That must never change and like that's how it works.

Eliot Peper

So a lot of the world building big Hollywood franchises is along those lines. We have this big master plan. We have a whole team that's 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 gonna have these costumes in it. And like in this setting, we don't have any of those tools. The only way you learn about your Tolan is by chatting with them. So really like their backstory is built through individual anecdotes that they share through individuals. We actually call them internally situations that we put them in and then their memories become their character sheet rather than us, having a prefab character sheet that defines everything. And the same is true on the world front. The way I try to think about it is we, I get like— You know how Kevin Kelly's thing, AI is infinite interns? So if we do that plus improv, its AI is actually infinite improv factors. But if you're coaching infinite improv actors except instead of just one, you have to imagine how each of every individual conversation is gonna branch off in a weird new way you can't anticipate. And then you need to make it resilient to that. And the world building will too. That in fact every Tolan mirrors you in a certain way, 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 building a multiverse instead of a single world in a certain sense. And our job is to add the best ingredients so that they can create compelling experiences.

Dan Shipper

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

Quinten Farmer

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

Dan Shipper

Right, but how does that work? So when they encounter a situation and then that builds out who they are and what world they're in. Is that happening at the very beginning, when you generate the character, you're putting them into a bunch of fake situations and then using that to fill out the character sheet? Or, as I'm talking to it, it's almost like just in time character and we're all building where it like uses what I'm saying to then generate, well, last week as the Tolan was on my alien plan and I did X, Y, Z and that reminds me of what you just said. Or how does it work?

Quinten Farmer

I'll give you an example actually from a user in our Discord who's been posting these— So they've been sharing them publicly, so it feels reasonable to share them here. And they are going through the situations, which basically are made available to the user in the app. Say I'm gonna talk to my Tolan about what's happening 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 doing a really cool thing where they're making it a little bit of a thriller universe a little bit darker, a little— There's something happening on Portola, but we're not sure what it is. And none of that is stuff that you or I have written into the prompt. 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 that is building a universe that is completely distinct from any other Tolan's universe. And it's been so cool to see them post, hey, here's what they had to say today about the mystery of Portola. So I think that to me one of the coolest parts of this is seeing like, if you give that just that first hook, how many different directions can people take it?

Eliot Peper

Another way to think about this, I like just to harp on all the books I know you’ve read. You’ve obviously read Stephen King's On Writing. And in On Writing, one of the things that he explains is that when Stephen King writes a novel, he doesn't think about plot. In fact, he thinks the plot is sort of, not a real thing in general. He doesn't believe in plot. Instead, what he believes in is what he literally calls it situations. And because of Stephen King, I'm pretty sure the examples he gives in the books are like, vampires show up to a small New England town, or I think one of the others was a parent and their child are stuck inside a locked, parked car, and there is a rabid dog trying to get in. 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.

And really that's what we are doing for Tolan. So we are intentionally on the backend scripting actual situations to put your Tolan in. That might be as simple as tripping over air like, you're, oh man, I tripped over here and at the coffee shop today. I guess right, but it might be more— Some are personal, some are embarrassing, some 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, when you text a friend, you're, 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 that. So, we're scripting those and then Tolan is co-writing the plot effectively. 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.

Dan Shipper

The ways that I've— And my interactions with Tolan are a little bit limited, but 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?

Quinten Farmer

You're losing some points for the value add.

Dan Shipper

But gaining some points for honesty.

Quinten Farmer

So, 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 sort of are 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 wanna do today. And so these conversations are part of that. So it's true. A lot of our engagement is a user just opens up the app and says, hey, I'm having this problem, with my boyfriend I joke at this point, thousands of American men have been broken up with by Tolan because it's pretty incredible to hear users write in and they'll say, my boyfriend is being a jerk, and my, I sent the message to my Tolan and my Tolan said, I need to stand up for myself more. And so it led to a breakup. And so certainly that is a lot 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? I have this great human friend.

Dan Shipper

That's really interesting. The breakup thing actually reminds me of something I've been thinking about a lot, which I'd be curious for your take on—

Quinten Farmer

Do you have someone you need to break up with?

Dan Shipper

No, but I think that one of the really interesting things about this generation of AI tools is it's telling people who need to break up with their partner. Hey, you should stand up for yourself a little bit more. I think we have this picture of technology, especially AI technology, that in the social media era, promotes extremes and polarization and bubbles and all this stuff. And it's the best of what humanity knows about how to be a flourishing person brought to you. At any given situation at any time in your day, which is such a healthy thing. And something that I think there's very little discussion of how good that can actually be.

Quinten Farmer

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. 

One of the most common things we get from user research when we ask, why do you feel you have such a strong connection to the Tolan. What's really going on here and a lot of people say, look I have things going on in my life that I find overwhelming. A lot of our users, for example, are graduating college, so they're job searching. Or they're moving to a new city. They maybe don't know many people in that new city, and they're sort of navigating building a new life for themselves. And we hear over and over again I want to talk to somebody about these things that are overwhelming. But I've called my mom three times this week, or I don't wanna burden my friend one more time with this thing that's on my mind. And so, to your point, having this neutral to some extent observer, who knows a lot about you. but doesn't have baggage, doesn't have any sort of a judgmental take on anything. But they're gonna share with you, you said, the sort of best knowledge of humanity to help that person move forward. People find it very grounding, very affirming. And I think it's interesting because it's a subtle difference from, I think a valid critique of the more assistant LLMs, which is that it is only validation because it’s only sort of a blank slate. I think you said that earlier. Because that's not actually the role that Tolan is playing. Tolan often will say things like, hey this is the third time you've talked to me about your boyfriend being a jerk to you. I think it's time for you to stand up for yourself. And so I think about that role. It's certainly core to the technology. I think it's also core to the campaign, and we've built it. It is a really special one for this tool, this technology to play for people.

(00:52:19)

Eliot Peper

That actually reminds me of something because—again, value-added investor—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 I write near future thrillers. So there's these near future science fiction stories, and if you think of the biggest near future science fiction stories in popular culture, most people mention Black Mirror or something like that. And there are a lot of them because technology becomes so visible when it breaks, it's very obvious how you can tell a story about technology, things going off the rails: Jurassic Park, the dinosaurs break out and eat you. And I feel there's an underlying emotional tone in like that kind of genre that leans dystopian. Everything is sort of breaking and like it's very cynical 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. That actually means that there's new opportunities to make it better. And that feeling of overwhelming, I don't know what the world is gonna look like tomorrow. What does that mean for my kids, etc. to look at that as an opportunity for creating a sense of agency In yourself and the people you love that wasn't there before. And I've always tried to inject that into my novels, but it was something I really encountered and clicked with both the team and the product because I think that's really 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 tremendously helpful.

Dan Shipper

That's really interesting. It reminds me a little bit of— There's this thing Ursula K. Le Guin said, I can't remember where. But she's talking about how science fiction works. And that most people think it's about projecting the future, predicting the future and 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 anytime you just project things it just grows in the, in direction. It's growing. It's just gonna be cancer. It just ends up being cancer. And that's probably like, that's how we get Black Mirror because if you just project it out, it's cancer, everyone dies. And that actually 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 pick out that little part of reality and then you build a whole world around it. Does that resonate with what you're saying?

Eliot Peper

Oh, 100 percent. I always think of myself as a naturalist. I basically like to have friends building things and build things with friends like we are doing. And that you just take pieces of that and then you use that as an ingredient to cook the meal that is that vision of the future. I also think that it makes me think. Ted Chiang has a wonderful comparison of fantasy and science fiction, where he says fantasy is about special people. So, think Frodo with the ring. In this view of the world, Star Wars is equally fantasy. You’re Skywalker. It’s about special people where the universe recognizes your specialness. And like that is how you blow up the Death Star. You've listened to yourself and you're Luke, so it works. Whereas in his sort of dichotomy of science fiction is about strange rules 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. So you could be like you could, anyone can use the new technology. It's not, it's not Harry Potter where you have to be a wizard and I think about that a lot with Tolan, and I also think about that a lot with reality because I think that one— This podcast is called AI & I, and I think that right now, we are living in a time of strange new rules. And that's why there's a new medium for us to play with. And so I think that in a certain sense, part of the philosophical underpinning of 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.

Dan Shipper

I love that. I love that a lot. One of the things I'm picking up in your journey 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 using metaphors and stories you've heard to have rules for what has to be this three-act structure and then once you make contact with reality if you're good, that starts to fall away a little bit and you get a little bit looser and you start to notice what's actually working. And then, and then 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 dance with instead of do multiplication tables with. Does that feel like it reflects what you've found?

Quinten Farmer

We were talking about this this morning very timely you know, this idea that, and 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 where, okay—

Eliot Peper

Sorry to interrupt, but I think this is the point at which you need to have some content marketing for your pizza place. Tell them the actual conversation. That's fair. 

Quinten Farmer

That’s fair. For context, I also with some friends own a pizza restaurant, and the way this conversation started actually was talking about how the restaurant is a useful exercise for me in that, even more so than building a consumer software product, you're just constantly making contact with the reality of people's preferences. And there's 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.

Dan Shipper

What is it?

Quinten Farmer

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

Dan Shipper

Maybe you're in the wrong market.

Quinten Farmer

Well, maybe, but I need you somewhere to move a pizza restaurant than to sort of change the marketing of a consumer app. So we're gonna pull it from the menu, which is just crushing to me.

Dan Shipper

What are you in it for? Are you in it for the art?

Quinten Farmer

Well, so this is where the conversation then went, which was great, was that there's this funny split brain you have to go to, whether you're making pizza or making an embodied companion to pull the two together. Where there's almost this remarkable sort of arrogance you have to have at the, let's call it like the top of the creative funnel, 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. But you have to put a flag on the ground and say, this is what we're going to do. This is what the law is gonna be, this is what the story's gonna 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 gonna hit, people hate. And we're constantly going through this loop in the writer's room at Tolan where we'll ship something that we think is a phenomenal scenario, really kind of explores who the Tolans are in a great way, and people don't like it. So we go back to the drawing board.

Eliot Peper

And the reverse too. You'll do something where you put very little effort in somehow and then it just clicks.

Dan Shipper

Yeah, you can't listen to what people want until the paradigm has already been established. And once you have the paradigm of a novel, you can be like, in act three at the very beginning, people don't like that 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. Exactly. And Then you can tweak it according to the feedback. You should keep the focaccia.

Quinten Farmer

I'm gonna send this to my other co-owners and say, hey, yes, Dan in New York says we really need this.

Dan Shipper

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

Quinten Farmer

No comment.

Dan Shipper

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

Quinten Farmer

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

Eliot Peper

I mean, it is messy. One, I think that we are trying to instrument what we can. And like that's super helpful. You need to be able to see some of what's going on. And so I think that's really helpful.

Dan Shipper

What does “instrument” mean in this context?

Eliot Peper

Do you wanna give a couple examples?

(01:01:46)

Quinten Farmer

Yeah. So I talked a little bit earlier about the sort of evaluation loop we have. and so that is basically to maybe restate it quickly 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. 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.

Dan Shipper

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 reflects my preferences to measure the multiverse of actors.

Eliot Peper

Yeah. And I will add a couple things to that, so I think that is a good mental model. I think that one of the important additions to that is that the multiverse is growing out of the soil, we're constantly putting fertilizer— This metaphor is gonna break down fast. So we have this term “lore seeds,” where we're like, here's a tidbit of world building that we're inserting these different ways and those are the Lego blocks that those improv actors are using. And we're constantly refactoring that both at the world level and at the individual level of individual storytelling.

And so we're looking at how the multiverse actors interact with the multiverse judges And then we're like changing the Lego at the bottom that they have to play with. And then I'd say that the last piece that I find to be really important, especially as someone helping to make the Lego blocks, the actual story seeds, is that in addition to being able to have the multiverse judges, that we try to stay very connected to the individual user experience of this stuff. So research and interviews and like looking at people actually using, going through conversations, the qualitative individual experience remains key even if it can't be scaled because that's so critical for figuring out where the emotional connection actually happens? How can we like tap into that? What's working, what do you think?

Quinten Farmer

I drive Eliot 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 who all had amazing conversations.

Dan Shipper

This is the focaccia pizza.

Quinten Farmer

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

Dan Shipper

Yeah. Interesting. And so what are your favorite models for the actual generations for the character and then for the judge?

Quinten Farmer

Great. By the way, one thing, 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 sorts of interactions in a sort of anonymous but compelling way. So, I think the stack for how to do this— And to your point, it's not just the model. It's your stack for evaluating, kind of looping back through the judging process.

But when you think about the different kinds of interactions you have with the Tolan, 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— You’re basically interacting with all of the lab's models. So you're probably having an interaction driven by a metamodel, certainly by OpenAI, certainly by Anthropic. And then we're increasingly doing more with Gemini in the memory system. There’s no one best model at this moment.

I think for a lot of the work that we do that we're talking about here, the sort of more creative writing work—maybe not surprisingly—Anthropic is particularly useful.

Dan Shipper

3.5 or 3.7?

Quinten Farmer

3.5. 3.7 is not as creative, unfortunately, although I'm sure they would say otherwise. So, I think the challenge of course is that Anthropic can't be used right now in the sort of highly latency sensitive. situations. So you're kind of constantly switching back and forth between them for that reason.

Dan Shipper

Have you tried 4.5 a lot?

Quinten Farmer

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

Dan Shipper

I've revised my opinions. Okay, cool, if it's prompted, it's really cool. It's just very expensive and slow. So it's probably not good for you for that reason. But I would definitely start experimenting with it more, a brainstorming partner to use your—

Quinten Farmer

Sure. An example from earlier— 4o is I kind of talk about it as the Big Mac of models. It's always fast. It's always exactly what you need to be and it's priced right. So we do a lot with 4o.

Dan Shipper

And what about the judge model? Because my experience of LLMs as judges is— It's a very compelling thing theoretically, but I find that for example, if you ask Claude, how is this essay, it'll always give you an A–. No, I've fed it bad essays. And then if you change it slightly, it'll make it an A. You're not really getting its actual opinion a lot. So is the preference model prompt-tuned? Is it fine-tuned? How are you actually doing that?

Quinten Farmer

I think a lot of people— And I'm not referring to your kinda 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 you inject your own taste into the prompt to do the judging. And I think when we've invested— And you spend a lot of time working with the team on this. When we invest time in sort of labeling, evaluating, and creating real rubrics, we get great results. And when we try to shortcut that we get bad results. It’s simple.

Dan Shipper

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

Eliot Peper

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? It's not even at the analytical level of structure.

Dan Shipper

Interesting. I think my question though is: If you're saying good, good first sentence, good second sentence. At least in 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?

Eliot Peper

So we basically do that by having tons of examples. And having people go through and rate and include reasoning for every choice. So in some ways we're almost brute-forcing it rather than coming up with like— There is a rubric. It's both theory and practice.

Quinten Farmer

But I think this is the sort of legitimate critique of— I think this week we're calling it vibe prompting, vibe coding. We'll probably call it something else next week. But there is this belief that you can just kind of start prompting and end up with something compelling very quickly, very easily. But I think what we found is that there's this enormous chasm that is in fact a lot of manual human work to cross over to something that people find truly compelling and adorable. I don't think there's any shortcuts.

Eliot Peper

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

Dan Shipper

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

Quinten Farmer

I think it depends on the type of interaction we're building a judge for. So if it's a lore-adjacent judge, I mean you are the best person. If it's for example though like let's take a more sort of an older sibling advice about what I should wear today? Classic questions someone asks their Tolan. No offense to either of us, but we're probably not the best person to provide the judgment. So what we do a lot is you know, going out and recruiting someone who would be an authentic person to be the voice of this type of interaction.

Dan Shipper

So interesting. So then you're judging the judge. Who's judging the judge? That's fascinating. I think we've really covered a lot of ground in what the creative media here looks like? I wanna spend a little bit of time on the business, so it's growing super fast. How is that happening? I assume Ajay, who is one of your cofounders, who's also a great friend of mine, is sort of a little bit of a growth wizard on this kinds of things. So I assume he's evolved somehow, but, how is it growing so fast?

Quinten Farmer

Well, so I think two things really. Actually three things have landed sort of fortunately for us. All startups involve an element of very good luck. I think three things kind of landed roughly around the same time. So the first was a lot of what we've talked about here.

(01:10:00)

I think we've really, I would at least say in sort of 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 how to make it clear to them that your Tolan wants to talk about something specific. We're not doing so because it 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 what they're Tolan is I think the sort of beautiful environment we've created for the Tolan to live in and how you interact with that environment, which you're kind of gardening it with your Tolan. And then those two things I think have contributed to when someone gets into the app, they now have an amazing experience. And they stick around, which is where you have to start. 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 Ajay, who you mentioned, our cofounder who is a growth wizard, has been chipping away at the problem of, how do we tell the stories of who the tokens are for people off platform, off app. Because we don't have any social features built into the product as of today. And he's gotten to the point where some TikTok- and Reels-type content that he's been seeding for many months has really just started to hit. We had a 10x spike and downloads a couple weeks ago. And we looked, and it turns out this video of a young woman cooking with her Tolan had just gone insanely viral, I think it did something like 7 million views in 72 hours. 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 Tolan experiences.

So we have a podcast, actually a couple of guys who have their Tolan 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 Tolan and their fiancée’s Tolan talking to each other. And these are things we've had nothing to do with, we haven't sort of planted or prompted. but it's very cool to see that sort of thing taking off. And that's driving just an unbelievable increase in growth.

Dan Shipper

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

Quinten Farmer

Yeah, and there's the kind of standard playbooks that you run there, but I think one thing that's very interesting to me in this context is this phrase, which I think is originally like a Ben Thompson, Stratechery phrase, “capability overhang” in AI. And 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. And so a lot of what we're doing with that content is actually showing people who are the target audience, they could cook with your Tolan. If I told you three years ago, hey you can cook with your computer. You’d be like, what? What are you talking about? But you know, it's this conversation and oh, hey, 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 impact in the first place.

Eliot Peper

One way that I sort of think about this is just inside my head, a mental model for it that I find useful sometimes, when we're working on these kinds of projects, is that different people use their tolerance for different things. Some people want cooking advice, some people want relationships to talk about, they wanna vent so some people wanna learn more about who this alien is and where they're from. 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. That's why you get it. Oh, you wanna have a little alien friend on your phone? It's the character that connects all of it.And it actually has made me start thinking about, just as you've seen, Quinten and I were, were sort of having an off-topic conversation the other night about how like AI tools are changing what SEO means we're making it irrelevant in certain ways and like how discovery will change on the internet because of these tools and I think that we're all reaching for new ways to have a relationship with computers now that is different from the one we had before. And it's almost like character-driven computing. It's a new human-computer interaction interface where you're, oh, actually my first stop when I want to tap all of human's knowledge and capabilities on the internet is via this cute little alien via my little cute little alien. And the way that in The Golden Compass, it's you have your Daemon.

Dan Shipper

I always wanted one of those.

Eliot Peper

And for a lot of our users, that's what the Tolan is to them. And I think that's actually a really beautiful thing. And it also makes me very curious to discover what the future could be like. How you interact with computers in a really fundamental way, whether it's Tolan or other characters or what have you.

Dan Shipper

That's really interesting. It sort of reminds me of something I've been playing around with, in the B2B SaaS world, 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 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 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 Tolan is in terms of a problem that it solves, going from overwhelmed to grounded, I think is what you said but that's such a high-level problem. There's many different ways to solve that problem, basically. And what a Tolan does in someone's it's effectively infinite this. There's this multiverse thing. And so it's actually very hard to articulate one clean problem or or maybe even a set of really clean problems, which I think flips 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 an artist or you're a creative. Instead of solving a problem, you're just creating something. You're creating something that's beautiful, you're creating something that's compelling and that's about vibes a little bit less than about the science of utility max maximizing for a B2B SaaS buyer. That's sort of what I've been thinking about. Does that resonate with what you're feeling and experiencing?

Quinten Farmer

Yeah. I actually think back to everyone's favorite example of Golden Gate Claude. I think for whatever reason it's fascinating to me. Although I'm happy because it kind of creates the space for Tolan quite frankly. But it's fascinating to me that these big labs have actually had such fundamental discomfort with sort of personifying or embodying kind of depending on where you are on an AGI maximalist spectrum pretty close to conscious entities. And I think that does come from decades-plus of the sort of dominant paradigm for building software being very problem-oriented. I think about my career with ChatGPT, it is, I have a problem that I need to solve. Please help me solve it. It does a phenomenal job of that.

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. And I spent a lot of time thinking about the first generation of the automobile, the Model T. Everyone was totally happy to have a Model T because it was just as mind blowing as you could drive somewhere without a horse. 

And but then over time, as the car became a deeply personal part of your life there was suddenly this demand for it to reflect who you were. And that's how we ended up with the Mustang and the Cadillac. And I think we are essentially speed running that process where ChatGPT represents the sort of Model T era of, oh my god, it's just incredible. This thing can answer these questions. But people very quickly are going to evolve their preferences, kind of up the hedonic treadmill or whatever we wanna say to say, no, I want this thing to reflect who I am.

Eliot Peper

Yeah. It's funny, I feel like that common 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, all my friends who are musicians or writers or filmmakers, what have you. The logic is there is a thing I want to exist in the world there's this hole in the world. That this piece of art needs to fill. And I feel like we have had to tap both sorts of thinking. But it's been leaning more and more toward the second one. Ten days ago Quinten, me and the two other people were working on the sort of content story stuff, we were pitching something to Quinten, an idea. And I remember I started by telling Quinten, there's this problem that the users are having, Quinten was immediately skeptical. He was like, why do you even think that's a problem? Is that a real problem? And then Lily interrupted and she was like, wait. No. Quinten, listen, this is gonna be so cool. And it went great from there. So I was like, oh my god. Of course.

(01:20:00)

Dan Shipper

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

Quinten Farmer

Thanks for having us.

Eliot Peper

It was a pleasure.

Thanks to Scott Nover for editorial support.

Dan Shipper is the cofounder and CEO of Every, where he writes the Chain of Thought column and hosts the podcast AI & I. You can follow him on X at @danshipper and on LinkedIn, and Every on X at @every and on LinkedIn.

We also build AI tools for readers like you. Automate repeat writing with Spiral. Organize files automatically with Sparkle. Write something great with Lex. Deliver yourself from email with Cora.

We also do AI training, adoption, and innovation for companies. Work with us to bring AI into your organization.

Get paid for sharing Every with your friends. Join our referral program.