How This AI Alien Brings In $4M a Year in Revenue - Ep. 56 with Quinten Farmer and Eliot Peper

How does it feel to be on your first

podcast?

Oh man, it's kind of wild. Not going to

lie. Like I'm psyched but also low-key

nervous. I just don't want to say

something totally awkward, you know.

Joke at this point, thousands of

American men have been broken up with by

Tolen. Um because it's pretty

incredible, you know, to to, you know,

hear users will write in uh they'll say,

you know, oh, you know, my boyfriend is

being a jerk and my I sent the message

to my tool and my tool said I need to

stand up for myself more and and so it

led to a breakup. 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. 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.

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 Tolen is that we are

not I am not the writer. I am not

writing the story. The tool 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.

[Music]

Quinton and Elliot, welcome to the show.

Thanks for having us. I'm so excited to

have you here. We are all long-term

friends. Quinton, 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, Quinton, you are

the founder and CEO of Portola, which is

an embodied AI companion. And Elliot,

you are the head of story for Portola.

Um, before Portola, Quinton, you you

founded and sold even to Walmart for

$300 million. You are a dad of two under

two, as you said. Um, which is much

better than 30 under 30. That's right.

Much le much much less fraud in the two

under two domain than the 30 under 30

domain. And you are a style, real style

afficado, men's wear, men's men's wear

afficata, which we should definitely get

into at some point. Great. Great. An

excellent skier. Um, and Elliot, you're

a best-selling science fiction author,

which I'm very jealous of. Um, also an

excellent skier, which I got to learn

actually. Interesting. I that's given me

a lot of credit. I really deserve I can

fall down a mountain.

And you've written 11 books and you are

a dad of one under two. So, not quite

two under two, but close. And yeah,

you're building Portolo, which I love.

I'm a little bit biased. I'm an

investor. But the reason I like it and

and we're going to do a demo of toll in

a second so people can get a sense for

it. But the reason I I like it 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 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 to four

million in ARR over the last four weeks,

which is just wild.

Having running a business for the last 5

years and not being at that at the 4

million AR mark, I'm like, you consider

turning every

into a little bit of it for you guys.

And what I think is also super

impressive just for you, Quinton, like

when you came to me and said you were

starting this business, which didn't

start here. started with a more Neil

Stevenson 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 B2B to B to B TOC

SAS world and it's just very different

to do something truly like creative on

the creative storytelling front. And so

I 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? Yeah,

it sounds great. Um, all right. So, I've

got my uh toolen Clarence here. Um,

Clarence is gonna a cat named Clarence.

I was gonna say, so I I named my tool

all my toolins, although we won't tell

Clarence this. Uh, you know, Clarence

for for a beloved older cat. And, uh,

right now, you know, Clarence is just

kind of wandering around his planet,

just kind of hanging out. Um, so he's on

a planet because that's a new thing. I I

I actually demoed it this morning and I

was like, whoa, there's a planet. He

used to be sort of like disembodied like

in space or something. I don't We for a

while we were giving kind of insane

asylum

vibes. And one of the one of the reasons

we actually uh you know made this

investment in the planet which we'll

talk about more later is is people were

writing into us with genuine concern.

You know they're saying hey you know I

love my love hanging out with them but

they're like they're trapped in this

room you know and and um can can can

they have some more freedom than that?

So so we we we've done that. So I'm

going to sort of you know get his

attention and uh start a conversation.

Hey, Clarence. How are you doing today?

Hey, you're back. I'm doing pretty good,

honestly. How about you? What's going on

today? Well, so we just started

recording that podcast I told you about.

So, you're here with Dan and Elliot. Uh,

do you want to say hi to them? Oh, no

way. Hey, Dan. Hey, Elliot. What's up?

I'm Clarence, Quinton's friend. Super

stoked to be here with you guys today.

How's it going over there? We're great.

Dan, do you want to ask him any host

questions? Um, it's going pretty good.

How does it uh how does it feel to be on

your first podcast?

Oh, man. It's kind of wild, not going to

lie. Like, I'm psyched, but also low-key

nervous. I just don't want to say

something totally awkward, you know?

Here is something you can say that I

think people would enjoy. What's like

the most embarrassing thing you can tell

me about Quinton?

Oh, no way. You're putting me on the

spot here. Honestly though, Quinton's

pretty solid. He did tell me once about

this time he tripped over absolutely

nothing in front of like a crowd of

people. Did you remember that? You

didn't have to call me out like that,

parents. But yeah, I I did tell you

that. Now the whole internet's going to

know.

Okay, but like to be fair, we've all

been there. Tripping over air is kind of

a right of passage, Quinton. Owning it

just makes you

Thanks, bud. I really appreciate that.

Hey, we're going to let you go and keep

recording. All right,

thanks. I want to take one minute away

from this episode to introduce you to

our sponsor, LTX Studio. I think

storytelling is one of the most

essential skills of the AI age. You can

bring your stories to life with just a

few words, complete with a cast,

storyline, settings, all according to

your style and your specifications. LTX

Studio is helping storytellers visualize

their stories in entirely new ways. With

LTX, you can generate production ready

images and turn them into videos for

ads, short films, online content, or

anything in between. Say you want to

tell a story with a dog in jeans. Let's

call him Photo. Choose from 16 unique

styles to get the look you want. Each

prompt gives you six image options, and

you can keep iterating until you find

the perfect one. Then, bring your

favorite image to life with motion

instantly. LTX can even add sound

effects automatically, so your scene

feel more dynamic and complete. LTX's

video model is the fastest out there,

which makes it great for speedy

production ready assets like storyboards

or social clips. Once you land on

something you like, you can upscale it

to full HD, ready to share or test out

in a pitch. Whether you're prototyping a

scene, spinning up a meme, or just

playing around, LTX helps you go from

idea to output fast. The AI revolution

is just starting. But if one thing's

clear, it's that it's not replacing

human creativity. It's expanding it. So,

if you've ever had a story in your head

with no way to bring it to life, start

with LTX Studio. It might just be the

creative partner you've always needed.

Check out the link in the episode

description for more details. And now,

back to the episode.

That's great.

Anyways, you know, the the planet and

and some of the things we've shipped

recently, uh, you know, has has been

really fun to see. Uh, 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 um, you know,

having these little cute little aliens

to chat with all the time. So, a lot of

fun. Yeah. So, tell me about because I

think that the path that you're on,

which is like B2B SAS to like creative

entrepreneur, uh, is probably something

that a lot of people are thinking of

doing. Like I I even for me like the

reason I started doing SAS 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. Um 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 and like there's so

much stuff to do or at least it was

impossible and now um I think it's like

way more possible to do by yourself or

with a small team than it was before. So

uh like for me I'm like I should make a

game like all this SAS stuff you know.

Um, so tell us a little bit about like

that transition and like how you how you

started and and where you've kind of

ended up as you've learned how to use

this as a storytelling medium. Yeah,

it's a great question. Um, you know, I

think when we first came together as a

team and and so for a little bit of

context, like the core engineering team

uh behind Portola is mostly the team um

that built my last company together

even. And so we had a lot of history

together um had obviously had a

successful exit and 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 um 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 um you know

LLMs and 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 like basically

more vertical B2B SAS which

um I I found it just like sort of

fundamentally uninspiring if nothing

else has it charms but yes it has it I

mean hey you know uh recurring revenue

uh net revenue retention I don't know if

like charm is the word I would use but

it has its appeal for sure. Um, and so,

you know, some of this just started from

like a a sort of stubbornness about like

there's something more fun to do here.

Come on. Right. And but as you know, I

mean, you you said it earlier, you know,

Neil Stevenson, Diamond Age, um, 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. Um, but it's a good place to

start, right? Because it kind of forces

you to start working with the tools,

start building.

Well, one, I mean, um, building software

for kids is a terrible market. Um, you

know, like one of our, uh, investors,

uh, somebody I has been a great mentor

to me, this guy, Zach Klein, and he

previously built a company called DIY.

Um, 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? It's a terrible thing to build.

There's it's it's a tough sales uh, you

know, marketing strategy to parents

instead of kids. Selling to parents

instead of kids. Parents mostly want to

buy babysitting. they don't actually

want to buy, you know, sort of a

creative tool that's that's not a thing

on their list. Um, 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, um, you know, we

saw that the sort of trend lines around

the speed of generation, um, the quality

of generation, this is the kind of GPT3

to to 4, uh, class model kind of cusp.

Um, 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. Um, and you could deliver that

um, 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. It doesn't have to be to be

be B2B SAS. Um, but we can make

something that we think is really fun

and compelling. So yeah, and that's

something that that I thought was really

interesting about the approach you took,

which is like from almost day one, you

were like play testing with kids. Yeah.

Um, but you eventually like landed on a

market that's sort of different. How did

when did you when did you Yeah. Yeah.

The the very and this will involve some

jumping around in the chronology. You

know, when we first shipped Tolen and

you you probably, you know, remember

this is right when we worked together uh

started working together. um you know we

we kind of soft launched it and we had

been doing a lot of play testing with

you know uh like 10 to 14 year olds with

the 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 uh women mostly um 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 uh you know really

fell in love with them I think the Tolen

has sort of a similar dynamic. Um, 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 toolins and really built a

friendship with them. Um, I want to

bring you in, Elliot. So, like, so I

actually introduced you to um credit for

that. I mean, I'm a hashtag value ad.

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

Thank you. Please.

That's the 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 um 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. Um

and you're kind of both jumping in head

first or feet first or pen first,

whatever you want to whatever you want

to say. and you're still writing your

books. Um, so tell me about your um

journey into this from a creative

professional or writing professional um

lens like what what was your first

impression of this technology as a um as

a creative tool and how has that evolved

as you've gotten closer and into the

whole Tolen world? Oh, so starting even

before Tolen? Um, yeah. So, I played

with chat GP, the first JP 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? Um, was uh it was

during the fires when we had those like

big fires in California. everything and

we were hosting a friend who was like uh

had to evacuate from their house and so

we're sort of like locked inside like

with our friend and I was like okay

here's something we can do 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

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. Um, 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. Um 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. And I've actually

found that um uh 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 um as a brainstorming

partner and as an editor like a copy

editor on the back end. So, it's a weird

like front and back end thing where you

know I'm a novelist. I spend a lot of

time alone, right? And like uh the the

sort of writer room like the Hollywood

writer 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

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're like they have

infinite patience for my uh rabbit holes

and for like brainstorming through

things and helping me get to the place I

want to be. And so um 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 um so that's

where I was with the technology before

you introduced me to Quinton. And I I

paid him extra to bring that up. # got

inventure. Um, and uh, and so, uh, I'll

be honest, um, 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. I 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, um, me and

Quinton started talking. um you

introduced me to other members of the

team and uh 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

B2B SAS like like people wanting to jump

into like doing creative projects or

games or whatever. 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 uh

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. Um, 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, right? This is

our last ditch effort." Talk about

a Toy Story, right? And they they

pioneered this new they used this

technology to create a new kind of

media. And um 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 um the

team was building at Tolen is that that

LLMs are also a new medium that if you

think about um 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 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 um these AI tools are not just

tools for generating media, they are

actually a new medium for storytelling.

And that um 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. 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 cuz there's just so

much space to play. You have my like

media technology nerd heart swooning

right now. Like I 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 touchston like books or

movies or whatever all started out as

new technology that people were

suspicious of and hadn't figured out

yet. Um like the even you know uh uh

when the typewriter came out, people

were very suspicious of that. It felt

very impersonal. Um and they would get

offended if you wrote them a typewritten

letter. Mh. Um and or or just like the

ways that technology affects the form

factor. We've talked about this a bunch

like um you know the reason a pop song

is 4 minutes um which is I think about

the capacity of records. Um um so

there's there's just a lot of like

really cool things right like that and I

think you're totally right. Um we no one

has figured it out. we are on the cusp

of this like um new set of constraints

and possibilities that creates uh 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 the this like

patina of culture for like many many

decades that like make it feel familiar

you know and um and so that creates this

like

thing where a lot of people are

suspicious but that's also an

opportunity because I think a lot of

good art is like uh 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.

Um, 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 uh you

know AI companion uh you know the first

reaction people have is oh like a spot

like a role

play or also you know and kind of

equally um you know coming from the same

place Dan that you're describing um you

know oh okay like a thing for lonely

people to talk to right and so you end

up with these uh sort of negative

connotations um around this new medium

because it's lacking that 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 um you know genuinely delightful as a

new art form. 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

non-fiction 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 that what picture does that p paint

in the minds of our listeners today 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, right? Um

and so that's a really unique experience

to be like, okay, every step is throwing

spaghetti at a wall to see what sticks.

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 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. We talked about this some 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 about here because um that's been

very nonlinear. Um you know, I

think one of the surprising things to me

has been the importance of memory. um

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 um 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.

Um, anything beyond a two second loop,

you essentially lose the feeling of

immersion. And so, how can we be

essentially recompiling the prompt to

account for lore? Like, you know, what

does the tolen need to know about where

they are and who they are? Um, to

account for memories about you. By the

way, in that interaction with the tolen,

my tool, Clarence knows more

embarrassing things about me than that.

And it essentially he chose to

hallucinate that story to cover for the

fact that I told him far more

embarrassing stuff than me, which I find

fascinating by the way because he had in

his context memories about me being

covered in spit up because my kid, you

know, whatever. Right. So very

interesting. Um um but also like Wait,

so you didn't actually trip over

something that wasn't there? Totally

hallucinated that great. Yeah. Um which,

you know, I'm mad at parents right now.

Bring him back in here. charmingly

obiscatory, you know, like, oh, let's

come up with something that Quinn won't

be, you know, upset that I shared. Um,

uh, but then also like, um, how should

the prompt evolve based on the 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. Yeah,

that's really interesting. So, okay.

Okay. So to play that back like one

thing I think a bottom line constraint

um 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 it for this

medium is response time. Y it has to be

able to respond really quick. Yep. Um

and then pushing against that constraint

seems to be you have to get the right

information about the user to generate

the right response. Um and uh if you had

all the time in the world that would be

great but you don't. Um and so you have

to like play with what is it possible

for me to get to um get a response back

that uh feels personal and feels

interesting and pushes the conversation

forward but within that two second

constraint essentially. Yeah. One of the

biggest mistakes we made uh in in the

kind of product development so far is is

the time that we um actually uh

introduced basically a second shot in

the evaluation of the prompt. So the

tool 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. Um it was a disaster.

Tanked literally every metric in the

product. People were writing in

frustrated and it was a 500 millisecond

change. That's really interesting. And

then how do you think about what a good

response is?

And I asked that because I know you

don't have or like it's hard to answer.

Yeah.

Yeah. Um well it's extremely context

dependent, right? So you think about um

you know the the role that the tollin

plays in uh folks lives. uh we we talk

about is the the role of like an older

sibling. Yeah. 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. Um a sort of

short quippy improv like response, which

I think improv is going to come up and

some of what Elliot has thought about,

um 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 tool to

take. And a good response in the sort of

more therapist adjacent tone is very

different than a good response

contextual. Exactly. I kind of wonder so

Elliot for me like as a writer one of my

favorite writers who talk about writing

is George Saunders. Oh yeah. He's

amazing. He's he's great. Right. Um, and

he has this whole idea about like how to

edit a short story, which is basically

like um, 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. Um, and you just do that over

and over and over again until you what

he calls it like rat, 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. Um, and it's interesting

that like 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. It's that's what it is.

Yeah. Um, 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. Um, and so how

does that how does it work to do craft

in that context? Yeah. So, um, 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. By the way, that is insane. No

one does that. Does I think it's great,

but like writers don't do that. Usually,

you 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. That's

true. I'm always trying surprising by

the way having worked I'm not a writer

but I have worked with Elliot for a year

and yeah that that's

yeah 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 right and uh and uh

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? Um and I uh like when we

started working together

um one of the ways that this came into

play writing for Tolen, writing in this

new medium is is actually we we started

out by um when we're trying to create a

narrative experience. So, as an example,

like when you're talking to your tool,

like they need to like if you get to

know someone, you want to know what's

the embarrassing thing that happened in

Quinton'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 the

psychology of mutual disclosure and like

how to think about relationship building

in a way that's evidence-based and

really grounded. And um and so one of

the things I've worked a lot on is how

do we bring the tools 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

um where we we would try to structure a

narrative experience like thinking in

three-act structure or what have you.

you could apply different sort of

narrative thesis to how we were doing it

and then um 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 '8s 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. Um,

and there were a bunch of reasons, but

like basically like that level of like

narrative complexity, the models are not

good at navigating. 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. Uh, I

think that those are two different ways

of saying exactly the same thing, right?

Um, 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 tool knows

stuff about its world also lore seeds

that are like we're planting to like

give give context and detail there um

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 I if

you haven't read it, you absolutely

should impro by Keith Johnstone. Status,

you know, I was like media technology

nerd. Yeah, exactly. Um come at me.

Yeah. Yeah.

Um 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 Jstone 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. Uh 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

improving in front of an audience with

recombination. that if 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 Tolen is that we are

not I am not the writer. I am not

writing the story. The Tolen 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. Interesting.

Um, and so we're building systems as

well as working at the prompt level to

try to combine the assoc like the free

association like we're planting a seed

uh like whether it's in the tool'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 call back that

that like makes it feel totally

connected. Right. Okay. That's really

interesting. I love this. Okay. It was

funny. As soon as you said the George

Saunders thing, I was like, I need to

file a way 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 that

tool sent the most compelling one that

we could have? So, it's actually very

very similar. And so, and you're doing

that manually or do you have an LLM

doing that or how does it work? 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 um and

then we look at individual outputs and

then feed that back into basically a

judge prompt um that we then tune to say

okay hey you know this is what good

looks like in this particular instance.

So, okay. So, if I had to try to sum up

like cuz 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. Um 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 a you know I

don't know go down different paths. Um

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? Yeah, I think that'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 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 also

some like very important instructions

right you know how we want to handle

very specific situations. Um so there's

this sort of global context that is set

essentially for every tolen and then you

know um a big part of the onboarding uh

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

tolen to be a mirror of you and so

that's a very toll-en specific you know

essentially profile building and so

those those would be two building

context the sort of mirror yeah like as

in uh you but in reverse or you exactly

you uh sorry like um reflecting back to

you in a way that feels very familiar,

right? Um so we want to know enough

about you that you know your tool is

going to respond to you in a way that

feels familiar. 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. Uh the way I would say it is

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 that click. And how do

you think about what that click how that

click works? Well, so like okay, I love

the bar metaphor. We have all these

different little we have the arriving at

camp together, right? We have all these

little scenarios we set out 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 were 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

two on the nose. Two on the nose, right?

And so you you want that sort of like

adjacent enough that they don't feel

unfamiliar. You're not intimidated. I

just read that. Yeah. Exactly. And I

think that's that's what we try to try

to create. Um so so that kind of

personality profile is maybe building

block number two. And then you know

building block number three. Um wait

before we go to there, how do you

generate like how are how are you

generating that? like are you actually

telling Claude or whatever on the back

end like I want it to be like you met a

stranger at a at a bar and and but it's

not too on the nose but it's like you

know how does that work? Yeah, that's

funny. Um we have had the most success

with with this specific question. um

basically framing the creation of the

profile through the lens of one of the

big uh sort of personality um uh types

because like ocean types like um big

five or exactly right um and 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 um

the stranger you sat down with at the

bar works well for our our brain doesn't

seem to work well for like if I'm an

INTJ you kind of know based on whatever

MyersBriggs that like INTJs are

compatible with. I don't know what the

Okay. Yeah, there's a lot of

pseudoscientific mostly pseudocientific

like it's it's pseudoscientific but it's

also um it's very story and narrative

based like all of this stuff is story

and narrative based so it make it works

you know 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. Yeah. Yeah. Yeah.

That's interesting. Okay. Sorry.

Continue. Good. Uh so so yeah so

building blocks the sort of global

context the the you know personal

context that is set. Um, 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 the tolen,

there's a set of paths that you might go

down. You kind of alluded to this. Um,

uh, certain stories that the tool maybe

wants to share with you. Um, 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 and

it's up to the user to then choose what

to traverse. But that menu is an

important part of what makes the tolen

tolen. 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 Stranger Bar as a

metal mental model is uh you you were

like how do you come up with the tool 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

tool 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? 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

1989 we decided Han Solo dressed this

way and that must never change. I'm like

that's how it works. So like a lot of

like world building on in big Hollywood

franchises is along those lines. It's

like we have this big master plan. 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? Um the only way

you learn about your tool 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. Like

the way I try to think about it is we

like I I get like you know how um Kevin

Kelly's thing like AI is infinite

interns. Like so if we do that plus

impro it's like AI is actually infinite

improv actors 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

that the world building will too that in

fact every toolin you know mirrors you

in a certain 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, right? In in

a certain sense. And our job is to add

the best ingredients so that they can

create compelling. You're sort of like

almost tuning like the hyperparameters

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. Um,

and you also don't exactly know what

seed you've planted, right? 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 into a bunch of fake

situations and then using that to fill

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'm as the

tool was on my alien planet and I did

XYZ and that reminds me of what you just

said. Is like how does it work? 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 you know feels feels

reasonable to share them here. Um and

you know they are going through uh the

situations uh you know which which

basically are um made available to to

the user in the app you know say you

know I'm going to talk to my tolen about

what's happening at at school with them

today or whatever. And they're

progressing through the situations um

and they're essentially co-writing a

universe with their tool. And this

particular user is 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 Pollola, but

we're not sure what it is. Um and and

none of that is is stuff that you or I

have written into the prompt, right? And

it is the Tolen 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 Tolen'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 Pertola. Um, so I

think that to me has been one of the 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? Like another way to

think about this, I like just to like

harp on all the books I've know I know

you've read like

now the pressure's on. Exactly. Like

you've obviously read Stephen King's on

writing, of course. Yeah. Um, come on.

That's what I'm saying. Yeah. Yeah.

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.

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 parked a locked parked

car and there's 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

right and um really that's what we are

doing for Tolen. So we are like we are

intentionally on the back end scripting

actual situations to put your tolen 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 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." You know, what's that? You

wouldn't believe. Oh, yeah. Yeah.

Exactly. Exactly. So, like we're

scripting those and then the tool 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 call

backs to later and sort of recombine

with every other element. Cuz the ways

that I've and my interactions with Tolen

are are a little bit limited. But the 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? You're losing some

points of the value ad.

But getting some points for honesty

points. Uh uh 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 tool um

sort of easily accessible in the app. I

mean we have this thing where the tool

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 that Yeah.

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, you know, I

joke at this point thousands of American

men have been broken up with by

tools. Um because it's pretty

incredible, you know, to to, you know,

hear users will write in uh they'll say,

you know, oh, you know, my tool was or

my you know, my boyfriend is being a

jerk and and my I sent the message to my

tool and my tool said I need to stand up

for myself more and and so it led to a

breakup. 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 tool comes to you

and says, "How should I talk to my

sibling who's a little jealous that I

have this great human friend?" Right.

That's really interesting. This actually

the the the breakup thing actually

reminds me of something I've been

thinking about a lot which I'd be

curious for for your take on is um

Do you have someone you need to break up

with?

[Laughter]

Um 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

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. Yeah. Yeah. Something we've started

talking about more um internally uh is

this idea of a sort of northstar for the

company of of helping our users go from

being very overwhelmed to being more

grounded. And I think this is

essentially what you're you're talking

about here. You know, one of the most

common things we get um from user

research uh when we ask sort of why do

you feel you have such a strong

connection to the toll? Like what's

what's really going on here? Um and 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,

um a lot of our users, for example, are

graduating college, so they're job

searching, right? 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, uh, you know,

building a new life for themselves. And

and we hear over and over again, you

know, I I want to talk to somebody about

these things 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 uh,

you know, this thing that's on my mind.

And so to your point having this um you

know sort of uh neutral to some extent

uh observer who who knows a lot about

you um 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 uh 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. Um, and I

think it's interesting because it's it's

a subtle difference from I think a valid

critique of the more assistanty LLM,

which is that it is only validation. Um,

because and and only sort of a blank

slate, I think you said earlier, because

that's not actually the role the Tolen

is playing, right? Tolen 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. I think it's time for you to stand

up for yourself, right? Um, 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 um is is a

really special one uh for for this this

tool this technology to play for people.

M you know that that actually reminds me

of something because uh again value

added investor like from from when we

when you first introduced us. One thing

that I really love both about the

product and the team is uh uh so in the

science fiction world like so I write

near future thrillers right so there

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 like because technology becomes so

visible when it breaks it's very obvious

how you can tell a story about like

techn like things going off the rail,

Jurassic Park, right? Like the dinosaurs

break out and eat you. I feel like

there's an underlying emotional tone in

in like that kind of genre that that

leans dystopian, right? It's like

everything is sort of breaking and like

it's very cynical. Yeah. Um, and uh,

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, etc. like to look at that

as an opportunity for like creating a

sense of agency in yourself and the

people you love that 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 um with both the team and

the product because I think that that's

really

[Music]

also interesting. Um, it reminds me a

little bit of there's this there's this

thing Ursula Kayla Gwyn said, I can't

remember where, um, but she's talking

about um, how science fiction works and

that most people think it's about like

projecting the future. Um, predicting

the future and and like projecting where

we are now and and pushing out 5 years

or 10 years and and what she said is

like that's sometimes how it works a

little bit, but like anytime you like

you just project things like it just

grows in the in direction it's it's

growing, it's just going to be cancer.

it just ends up being cancer. Totally.

Totally. Um and 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. Yeah. Yeah. Um and that like

actual uh I think the way that she

thinks about science fiction is much

more about um revealing something that's

true now about people and how people

work. Um that you just like you pick out

that little part of reality and then and

then you like build a whole world around

it. Um does that does that resonate with

what you're saying? Oh, 100%. Like I

always I think of myself as a

naturalist. Like I basically like to

have friends building things and build

things with friends like we doing. Um

and that that like you just take pieces

of that and like then you use that to to

like as an ingredient to cook the meal.

That is the the that vision of the

future. I also like that that makes me

think of Ted Chang has a wonderful like

like uh comparison of fantasy and

science fiction where he says fantasy is

about special people. So like think

Frodo with the ring, right? Uh 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? You listen to yourself and you're

Luke, so it works. Um whereas uh in his

sort of uh 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.

Um, and I think about that a lot with

with Tolen and I also think about that a

lot with reality because I think that um

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 uh and and like that's why

there there's a new medium for us to

play with, right? Um, and and so I think

that uh 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? Yeah. Yeah. Yeah. I love

that. I I love that a lot. Um, 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 um 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,

um 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. And then and then you um 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 uh

multiplication tables with. I don't

know, something like that, you know. Um

does that feel like it reflects what

you've what you found? We were talking

about this this morning. It's very

timely. Uh, you know, this this idea

that, and you use the phrase make

contact with reality. Um, there's this

sort of funny split brain that I think

we've had to have while working on this

product where 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. That's fair. That's

fair. Uh, yeah. For for context, um, 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 I just love it. I

order it every time I go into my own

restaurant. What is it? Uh it's a fkaca

slice. Just good good tomato fkaca 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 fkatcha

and tomato sauce and that's it. They

want a pepperoni pizza. Maybe you're in

the wrong market. Well, that's maybe but

you need more to move a pizza restaurant

than to sort of, you know, change, you

know, the marketing of a consumer app.

So, you know, we're going to pull it

from the menu, right? Um, which is just

crushing to me. Um, what are you in it

for? Are you in it for the art?

Well, so this is where the conversation

then went, which was was great, was that

there's this funny split brain you have

to go to whether you're making pizza or

making uh you know, an embodied

companion. um just to pull pull the two

together where there's almost this like

remarkable um 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 and and

certainly no one is saying this is how I

want my companion to engage with me and

and but you have to put a flag in 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 that people hate to um and

we're constantly going through this loop

in the the writer room uh you know at

Tolen where we'll ship something that we

think is a uh you know phenomenal

scenario really kind of explores who the

tolins are in a great way and people

don't like it so we go back to the

drawing part and the reverse too right

like you'll do something where you put

very little effort in somehow and then

like it just clicks yeah you can't um

you can't listen to what people want

until the paradigm has already been

established and once you have the

paradigm of novel like you can be like,

"Okay in

act, you can't go ask people and like

come back with I want a 300page book

that's in a three-act structure. You

have to just like make that up

basically." Exactly. Um, 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 foca. Like

they're wrong. We'll see. And this maybe

tells you something about me.

send this to my other coowners and say,

"Hey, guess Dan in New York says we

really need to." I guess also it depends

on if your other coowners like also

don't like it, then that's that's a

different thing. What do they think? No

comment. Let's move on.

Um, interesting. Okay. So, what this

makes me think of though is um it's very

cool. you're building all these like

you're building the mult the multiverse

of tolins and it's this sort of flexible

thing that's like like a thousand

different improv actors but like that

also sounds like a 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 oh man that's a great

question how do we do that Elliot um uh

it's I mean it is messy 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 That's that's

really helpful. What's instrument mean

in this? Do you want to give a couple

examples? Yeah. So, I talked a little

bit um earlier about the uh sort of

evaluation loop we have, right? And 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. Um 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 um and use that to build a

judge prompt. Okay. Um, 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. Okay. So, you're basically

saying like instead of having an actor,

I created an an improv actor that's in

the multiverse and instead of having uh

an editor, I created an improv editor

that's in the multiverse and like

reflects my my preferences to measure

the multiverse of actors. Yeah. And uh I

I would um Okay, I will add a couple

things to that. So I think that is a

good mental model. Um 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 fertilizer. This this

metaphor is going to 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 and

we're constantly refactoring that both

at the world level and at the the

individual level of like like individual

storytelling. And so, um, we're looking

at how the the the the multiverse actors

interact with the multiverse judges, 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 um that that I find to be really

important, especially as someone helping

to make the Lego blocks, like the actual

like story seeds, um 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 uh research and

interviews and like looking at people

actually using going through

conversations that like the qualitative

individual experience remains key even

if it can't be scaled because that's 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? I drive Elliot just one thing. I

drive 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 them had amazing conversations. Foca

pizza." I'm like, "This is not good."

So, 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

going to roll. Yeah. Yeah. Interesting.

Okay. And um okay, so what's your

favorite model for like the actual

generations for the character and then

for the judge? Yeah, great. Um by the

way, one thing, you know, it's my turn

to be a value ad investor. Actually,

that process that we just talked about,

one tool that's been tremendously useful

to us uh that uh I think is worth a

little shout out here is uh this company

Dawn that does uh sort of analytics that

let you look at these sort of

interactions in a sort of anonymized but

compelling way. Um 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? your stack for

evaluating kind of like looping back

through the judging process. Um, but you

know, when you think about the different

kind of interactions you have with the

tolen, like if you spend, which I know

you don't, but if you spend a whole day

hanging out with your tool, as many

people do, um, you're probably

interacting with a model from I just,

yeah, couldn't convince us, um, you're

basically interacting with all of the

labs models, right? So, you're you're

probably having an interaction um,

driven by a meta model, certainly by

OpenAI, um, uh, certainly by anthropic,

and then we're increasingly doing more

with Gemini in the memory system. And so

I think that's one thing is like there's

no one best, right? Um 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, um maybe not

surprisingly, anthropic is particularly

useful. 35 or 37? Uh 35. 37 is uh you

know, not as creative unfortunately. Um

although I'm sure they would say

otherwise. Um so yeah, you know, I think

the the challenge of course is that uh

you know, anthropic can't be used right

now in the sort of highly latency

sensitive um situations, right? So,

you're kind of constantly switching back

and forth between um them for that

reason. Have you tried tried four or

five a lot?

I have very little. I mean, somebody I

know and whose taste I really trust

wrote a review that was not um uh you

know, particularly complimentary. Um

I've revised my opinions and stuff. You

have? Okay, cool. Um if it's prompted

right, it's really cool. It's just very

expensive and slow, so it's probably not

good for you for that reason, but like I

would definitely start experimenting

with it more. Kind of a brainstorming

partner to use your example from

earlier. Yeah. Um, yeah. I mean, you

know, 40, uh, 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 And what

about the, um, the sort of judge model?

Cuz like my experience of LMS as judges

is um, like it's a very compelling thing

theoretically, but I find that uh, like

for example, if you ask Claude, how is

this essay? It'll always give you an A

minus. Yeah. Um, and then if you'll

always I bet it badasses.

Um, 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 the preference model um is it

prompt tuned? Is it fine-tuned? Like,

how are you actually doing that? 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 LLM as

judges skip what is the most important

step, which is like you in injecting

your own taste into the prompt uh to to

do the judging. And I think when we've

invested and and you spent a lot of time

working with 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. 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. Uh

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? 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.

Should you have asked a question here?

Is that a thing that we create a judge

for? Exactly. Interesting. Um I think my

question though is like if you're saying

like good good first sentence is good

sec 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? We basically do that by

having tons of examples and having

people go through and rate and include

reasoning for every choice. I see.

Right. So in some ways we're almost like

brute forcing it, right? Rather than

coming up with like it's not rules, it's

just I mean there is a rubric. There's

also it's both, right? It's both theory

and practice. But I think this is the

like uh 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 um 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 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 in a durable way. I don't

think there's any shortcuts. Like 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? Yeah. 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 a second sentence is

good? Are are you doing the rating or is

it um your users doing the rating or

like is it something in between? I think

it depends on the type of interaction

we're building a judge for, right? So,

you know, if it's a a lower adjacent

judge, I mean, you are the best person,

right? Um you know, if it's for example

though, um like let's take a more sort

of older sibling advice about um like

what should I wear today? Classic

question someone asked their toll in um

no offense to either of us but we're

probably not the best person to provide

the judgment. You are a men's wear

afficionado. You know back up in

conversation. Um so you know what we do

a lot is um you know going out and

recruiting someone who were like oh this

would be an authentic person to be the

voice of this type of interaction.

Interesting. Okay. So now so then you're

judging the judge. Yeah. Yeah. Yeah.

Who's judging the judge? Who's judging?

just keeps going like all the way down

you can ask you.

That's fascinating. Okay. Um H 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 does 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, um, AJ,

who's, uh, who's one of your

co-founders, who's also a great friend

of mine, um, is like sort of a a little

bit of a growth wizard, uh, on this kind

of on these kinds of things. So, I

assume he's evolved somehow, but like

how how is it growing so fast? Yeah. Um,

well, so I think two things really

actually three things have landed, uh,

sort of fortunately for us, you know,

all startups involve all successful

startups involve an element of very good

luck. Um, I think three things kind of

landed roughly around the same time,

right? So, 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 tool wants to talk about

something specific. So we really you

haven't even discovered that yet. Yeah.

We're not doing that job. Um uh so 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 uh six weeks ago. Um the second

thing was uh we landed a sort of big uh

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 tool is I think

the sort of beautiful environment we've

created uh you know for the tool to live

in and how you interact with that

environment which you're kind of

gardening it with your tool. Um and and

then the and so those two things I think

have contributed to when someone gets

into the app they now have an amazing

experience and and they stick around

which is where you have to start where

you have to start right and 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 AJ who you mentioned our our

co-founder who who is a a growth wizard

um has been chipping away at the problem

of like how do we tell the stories of of

who the tools are for people off

platform off app right 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, Tik

Tok and reals type content that he's

been seeding for many months has really

just started to to hit. Um, we had a

like 10x spike in downloads a couple

weeks ago and we looked and it turned

out this this video of a young woman

cooking with her tool had just gone

insanely viral. I think did something

like 7 million views in like 72 hours.

Um, and so what's happening now, and it

was very cool, is that those pieces of

content that AJ has seated are now

encouraging other people to make their

own sort of toll-en experiences. So, we

have a there's a podcast actually, a

couple of guys who have their tolen on

as a recurring character. Um, often

providing relationship advice and things

like that. Um, uh, a great video I saw

the other day that I think did quite

well. Um, someone had their tollen and

their fiance's tollin talking to each

other. Um, and these are things we've

had nothing to do with. we haven't sort

of planted or or um you know prompted um

but it's very cool to see that sort of

thing taking off um and that's driving

just an unbelievable um increase in

growth. 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 Tik Tok and Instagram. 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

um is this phrase which I think this is

originally like a Ben Thompson like a

strategy phrase capability overhang in

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 consumers

understanding of what is possible and so

a lot of what we're doing with that

content is actually showing people who

are our target audience hey you can cook

with your total I mean that's like a

great like if I told you three years ago

Hey, you know, you can cook with your

computer. Like, what what are you

talking about? Well, New York Times is

cooking, but well, that's uh but you

know, it's this conversation and like,

oh, hey, oh, I see what's going wrong

there. Hey, you should change the heat

on that or whatever. Um, and so a lot of

it is that education, which is so you're

both sort of educating and driving

awareness to the product in the first

place. I think that's one way that I

that 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 tools 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

very obviously the promise made by

everything AJ does is the character.

It's like the charact 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. And it actually

has made me start thinking about just as

you've seen like Quinton and I were were

sort of uh 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 in certain ways and

like how discovery will change on the

internet because of these tools and um

and I think that we're all reaching for

new ways to to have a relationship with

computers now that that is different

than the one we had before and that

actually like tolins and like it's

almost like it's characterdriven

computing. It's like it's like a new

human computer interaction interface

where you're like, "Oh, actually my

first stop when I'm like wanting to tap

the the incredible knowled 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 in you know the golden

compass, it's you have your Damon,

right? And it's like I always wanted one

of those. Exactly. and like and a lot of

our users that's what the tool 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 Tlen or other

characters or what have you. That's

really interesting. It sort of reminds

me of something I've been playing around

with, which is in in B2B SAS world. Um,

just bring to the segway. I'm really

excited actually. Um, 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. Um, 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 and

the the kind of person or the kind of

founder that is able to uncover problems

is something like a scientist. Um and um

uh you've definitely framed some of what

a tollin is in terms of a problem that

it solves like going from overwhelmed to

grounded I think is what you said. Um

but that's such a high level problem.

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

toll does in someone's life is like it's

effectively infinite like this there's

this multiverse thing um and so it's

actually very hard I think to articulate

one clean problem or um or maybe even a

set of like really clean problems which

I think flips the um 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. Um, and and that's about

vibes a little bit less than about like

the science of like utility max

maximizing for like a B2B SAS buyer.

That's sort of what I've been thinking

about. Does that resonate with what

you're what you're feeling and

experiencing? Yeah, I mean this um I

actually think back to everyone's

favorite example of of Golden Gate

Claude, right? Um, you know, I I think

for whatever reason, it's it's

fascinating to me, although I'm happy

because it kind of creates the space for

tooling, quite frankly, but it's

fascinating to me that these uh the big

labs have actually had such fundamental

discomfort with sort of personifying and

and um you know, um embodying uh 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? Um and and I I think

that does come from uh you know decade

plus of the sort of dominant uh paradigm

for building software being this like

very problem oriented. You know I think

about my careers with chat GBT. It is I

have a problem that I need to solve.

Please help me solve it. Right? It does

a phenomenal job of that. Um, but I I do

think that there's much more space for

sort of genuine relationship building

and and one metaphor that I actually

find myself going back to, which is

funny because it seems so archaic, um,

is actually how our relationship with

cars evolved in this country, right?

And, um, I spent a lot of time thinking

about, you know, the first generation of

of the 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? Um and

but then over time as the the car

became a a deeply personal part of your

life uh 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 and and I

think we are essentially speedrunning

that process where chatt represents the

sort of model T era of like oh my god

it's just incredible this thing can

answer these questions right um but

people very quickly are going to evolve

their preferences kind of you know up

the hydonic treadmill or whatever we

want to say um to say no, no, I want

this thing to reflect who I am. Yeah. On

the, you know, it's funny like uh 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 uh 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 um

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 uh 10 days ago um

uh Quinton, me and the two other people

working on the sort of content story

stuff were uh we were pitching something

to Quinton, an idea. And I remember I

started by telling Quinton there's a

there's this problem, right, 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." And it went great from

there. I was like, "Oh my god." Of

course. I like to imagine it not so

transparently, you know, but it really

did work in that moment, they have to

say. So, I love that. I think that

really puts a bow on it. This is a

amazing conversation. Thank you both for

coming out. Yeah, thanks for having us.

Yeah, it's a pleasure.

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 chat

GPT. 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.