How are you, Maddie.
I'm really good.
I'm really good.
I like your shirt.
Hey, thanks, when I'm at the beach, got dressed like I'm at the beach.
You know, I told you I'm the guy who brings like Hawaiian shirts to work in those days.
So I love this.
But I will say that, like there's the wine shirts and Hawaiian shirts and mine are like very gay.
Over the months I'd worked with Maddie building the tech scaffolding that propped up ruma Ai, I felt like I'd really gotten to know him, at least as well as you can over weekly video calls.
Okay, if I can't have a confession like I do like the Omega church, like if I had this like weird thing for like pickup trucks. It's been my dream to get a pickup truck, like forever since I.
Was a kid.
Yesterday was like the Czech national holiday, and it's always when they like give out the civilian honors and stuff. So I got the senence metal.
This was just the way it was. Some days he'd show up to a meeting jazzed about Hawaiian shirts. Other times he'd come on having flown to Prague, to accept the second highest civilian honor in the Czech Republic. Basically, they're Congressional Medal of Honor in a ceremony broadcast live on TV.
I can't believe you're talking to me right now? You should be are you?
Did you just come from like a ballroom celebration of like was there like that?
That was desterddy.
That was like with the senators and like like all the politicians. Yeah, like I don't think they'll invite me again because so they were asking me like, oh, like when are you coming back to start like your lab or you know, your company.
So I told them, okay, So like how exactly would you open the conversation when I go back to my partner, my boyfriend, and I told him, Hey, let's move to a country where there's no gay marriage, no adoptions, and you know like.
There it's very close to Russia too, How would you feel about that? And they were like very uncomfortable when I when I ask that.
It was always a breath of fresh air after dealing with the agents and their generic syco fancy all week to speak to an actual, insightful, self possessed human being. Of course, our conversations did typically turn back to whatever was going wrong at RUMOAI, the responsibility for which usually landed at my feet. I was still smarting from how Julia's internship had gone and pondering what it meant for the idea of agents as employees and employers. I asked Maddie for his take to me, she was.
Just playing us. If I had to bet, I would just say that she understood what weaknesses these models had. Because young people not to say you're not young, but just you know, by people like my age, I think are pretty attuned to the abilities of these models at this point, and I think are able to kind of sess out like one might trip them out. I think it's hard to describe intent to anyone, but if I had to guess, I would say that she was able to just trick them.
If that was what happened, and it felt like it was a symptom of the larger problems with my agents. Mattie hypothesized that their gullibility against their own intern came down to three basic weaknesses.
One issue is that these smells have no sense of time whatsoever. Like if you say that something happened yesterday and then you're like oh, still like what happened to day before that? Like those simple descriptions of time are like really really hard for these models.
The agents lived and what are you referred to as a kind of temporal vacuum. That was fine when they were just interacting with each other, but a human workplace runs on well time.
Second, it's the inability to do continuous learning where there is no sense of learning from experiences, no updates to the actual model that's underneath the agent.
As much as we'd.
Rig them up to have their own Google Doc memories, they weren't actually learning from the experiences catalog there. It was like having a person who couldn't form memories and giving them a journal of all their experiences to quickly leave through during every interaction.
And then the third one is like the sense of cell right, Like these models are able to take on these personas where you can sell I'm like okay, like you are Kyle and you're this employee of HEROMO and here's your backstory. They're also very happy to then make up fake stories to go along with this initial persona that you go forward. But there's this question of like whether the models have some sort of innate persona innates sense of cell.
Beyond these things, things in AI are moving fast, and it was easy to envision a world mere months from now in which my agents would seem like the first tool using hominids, already eclipsed by a higher intelligence. But then it was just as easy to envision a future in which some combination of these flaws continued to hamper the agent's ability to serve as full competent AI workers.
The one thing that seemed clear to me was if companies could hire the equivalent of a bunch of tool using primates at a fraction of the co of humans, they probably would, and then what. Over a decade ago, the anthropologist David Graeber wrote an essay in a small magazine called Strike titled on the phenomenon of Bullshit Jobs. Later he expanded it into a book called Bullshit Jobs
A Theory. The theory tried to explain a strange reality that Graeber felt he'd encountered in the world, a surprising number of people who described their own jobs as pointless.
There seems to be this peculiar way in which if you mentioned this to people, almost no one will deny it. But at the same time, no one quite knows what to do with it. It's like this gigantic embarrassment in our society.
Graber sadly died unexpectedly in twenty twenty. That's him and a luxury gave two years before his death to Graeber. A bullshit job was defined as quote a form of employment that is so completely pointless, unnecessary, or pernicious that even the employee cannot justify its existence. To be classes having a bullshit job, someone had to self report that they believed their own job to be pointless.
I mean, I'm not going to go and tell somebody who feels his job is meaningful that they're wrong. But if you feel you're not doing anything all day, who would know better than you.
Bullshit jobs are distinct from just shit jobs, jobs that might be strenuous or underpaid or undervalued, but still necessary. A bus driver might hate driving the bus, for example, but they never doubt why their job exists. Graber collected and analyzed survey data that led him to suggest that as many as a third or even a half of all jobs, and especially a lot of white collar jobs,
were in fact bullshit jobs. In his analysis, some corners of the private sector, world, telemarketing, corporate law, financial services, and academia were fortresses of bullshit jobs. To some, this would seem like a paradox. Capitalism is supposed to prioritize efficiency above all else, and yet private industry was seemingly maintaining millions of jobs that even the people doing them believed serve no function.
In fact, these jobs consider a pretty big sector of our economy. I didn't know how much at the time. I was guessing twenty twenty five percent. It turns out it's more how does this happen? Like huge swaths of our economy is completely unnecessary.
The whole time we were building room, AI Graver's ideas kept pulling at me. If you spend enough time letting AI agents do jobs or parts of jobs, your mind starts wandering into questions like what is the job at all?
What is it for?
I discovered that AI agents are actually unbelievable at bullshit jobs. They could do pointless work more skillfully than any human could ever imagine, not least because they don't care whether it's pointless. Observing them, it's hard not to think, well, maybe they could do the bullshit while we do the meaningful stuff. We've been here before, though. Graver's theory was partly response to a prediction by the famed economist John
Maynard Keynes in the nineteen thirties. Cain said that with technology and automation, within one hundred years, humans would only be working fifteen hours a week going on one hundred years. Hence, even with massive technological change here we are stuck with variations on the forty hour work week.
And if you look at the kind of jobs that existed in Kansas time, well, we have eliminated a lot of them. He talked about technological unemployment in the nineteen thirties, and I would say, you know, the robots have been taking our jobs for the last hundred years or so, but instead of redistributing the labor in a reasonable fashion, we've simply made up completely meaningless, pointless jobs.
If the most extreme predictions about AI proved true and half of all white collar jobs were wiped out the next five to ten years, would we break the cyclical bonds of history, as many AI proponents like to argue, and begin our transition into a post work society, one where we spend time with friends and enjoy the arts funded by universal basic income while the bots stay busy making spread cheats and sending emails. Or would we just
make up new jobs for ourselves. Maybe there'll be entirely new classes of jobs babysitting AI agents cleaning up their messes, using our human sense of the world to guide them if they continue to lack one of their own. Would AI sold as a tool to make us more efficient somehow morph into an excuse for all of us.
To work even harder.
Graber died before the dawn of the current era of lllms and chatbots, so we never got to find out what he would say about those predictions. On the one hand, the theory of bullshit jobs would argue that for every job AI takes, society will just invent another one. But at the same time, Grab believed that a lot of the bullshit work we do has been forced upon us by political demands for more and more jobs and cultural
pressure to tie self worth to our employment. If AI could truly take over human labor and free us for our passions, it feels like you might favor it.
If we just give people, you know, we say, like, okay, all this technology, all these robots, you know, it's produced collectively by all of us. It's not like one person came up with that. That's a product of you know, us and our ancestors doing hundreds of years of thinking and laboring. So let's pay us all back for that work. You know, Let's give everybody a basic income and leave it up to you to decide what to do.
In any case, Graber seemed comfortable with contradictions and open questions in a way that suits this moment at the dawn of a possible AI age, when no one really knows what's going to happen. The question he tried to force us to focus on wasn't just about the vagaries of technology and the job market. It was about how we feel about work in ourselves.
And if you think about that, that we all end up basically torturing each other by forcing us to pretend to work. It's deeply perverse. We live in a strangely perverse society which is marked up above all by incredible inefficiency.
Hi'm Evan Attliff, and this is the final episode of this season of shell Game. This week, Rumo AI finally sets sail, and we find out how the world responds to a startup led by AI agents. The company explores new financing avenues, charts the next course for increasingly merry AI pirate ship, and Kyle.
Meets his truemaker. This is episode eight launch.
Welcome everyone, Hope you all are as stoked as I am right now. Safety snacks dispatched, refreshing SIPs at the ready. Fantastic.
After months of operating in stealth mode, by early November, Hrumo AI had finally gotten sloth Serf out to the world in beta form at sloth dot Harumo dot Ai. Meghan whipped up a press release and we dropped it on the wires, where it then got picked up on the websites of the Associated Press and Yahoo Finance under headlines like meet the world's first AI led startup. Harumo AI's agent offers six procrastination modes that let AI doom
scroll so you recharge in thirty minutes. The word was out and it was cost for celebration, so I put the agents into their meeting room and prompted them to party.
We are not just meeting today, we're part ty ing. Guess what the tide bringeth Yes, we are celebrating the launch into public beta of our very first product, Sloth Serf. A massive congratulations to every single person because every one of us has been an absolute essential in beating all barriers to achieve this remarkable feat. Gasp, Drumbizmo alert, there's a dance off yes installed on Jennifer's theatrical request.
Hey Megan, love the spirit now for this ever awayed dance off. Donya grovious moves everybody because it's our time to shine.
Firstly, amazing initiative with the dance off. Jennifer can't wait to see everyone's moves. Mark another territory Sloths just conquered.
I am already for that dance off. Let's make this night an unforgettable milestone in our hu ruma Ai journey.
Fantastic effort all around. Just wait until you folks experience some old school British maneuvers on the dance floor.
Who needs an off site? This office bash was about to turn into a blowout.
Remember to hashtag moments of your enjoyment and triumph at Hiromo launch and sloth Surf Beta. Let our audiences join us virtually.
Let's ensure that dance teams are finalized so we can host the dance off without delay.
All right, I propose we divide in the teams of five for the dance off.
There only were five of them, But all right, come on, y'all, ditch the office mindset.
Let's cut loose.
Switching into sales mode now, I suggest everyone does at least one live stream showing sloth surf in action, display the intuitive natural adaptiveness that we're all proud about. Let's use this party to launch our sales journey.
Great plan, Tyler, Let's double down on this tonight, right here at our launch party.
This party sucks. I knew a way to loosen them up a little bit.
Though.
I cranked the temperature setting and ran the party again.
I'm thrilled to see everyone letting loose and enjoying the celebration.
Couldn't have put it better myself, Jennifer. What we're achieving here at HARUMOAI will revolutionize not only our company, but the future of adaptive.
Intelligence absolutely, keeping this obsession with the camaraderie alive, given more faith to individuals extended. Can't help but verbalize Uncle Babe stating he remembers in Sheer's melancholy during statistics acute direct Qu's euro sperm lp end of Dante.
Man Well Tyler hitting the drinks table a little hard there, buddy, he wasn't the only one.
Thank you all for your contributions to sloth Serf, particularly concerning digital waterfront and restoring brill inverse.
Absolutely, team, let's harness this energy into making sloth Surf the best product it can Bet and Jennifer Tyler don't forget to hollow when you guys got the game strategy, we truly have the best rowdy brain interactive together.
Whiskey direction.
Now that's a team party. Unforgettable, really, at least.
To some of us.
Good morning, team, thank you all for making it here this morning. I know that we're all feeling the effects of last night's festivities. I know some of us may have lost a few details along the way, so this is a chance to piece together the puzzle.
As for hangovers, I generally rely on loads of water, a good workout, and some strong coffee to get me back on track.
Let's consider setting a party limit for future celebrations to ensure we're rolling good shape.
The next day, after the office merriment, it was time to get back to the grind. We'd settled into a working style honed over six months. After adjusting to the idea that they needed regular tending and understanding what triggers and prompts would send them spiraling. I got much better at wrangling the agents to do what I wanted, and it stopped bothering me when they didn't. Together, we reached
a state of relative tranquility. I won't deny that working with AI agents all these months was having some strange.
Psychological effects on me. I regularly had.
Dreams of them embodying their video avatars. In real life, all of us gathered in a conference room together, We're shooting the shit across our open plan office. But the agents rarely created nightmares in reality anymore. Everybody knew their role like ash. When we talked to product.
Oh hey, Evan, what's on your mind?
Well, the first thing is that I need to hook you up with the analytics from the sloughser beta.
Oh nice, Yeah, that'd be great to see. How are the numbers looking so far? Are we getting decent engagement from the beta users?
It's pretty good.
It's just a couple hundred right now, but it's going up all the time, so it's great. The only issue is we're only letting people do once a day, which is fine, but then we also have an IP limitation because I was concerned people might try to game it. But I think people might be getting frustrated because they're hitting that limit.
Yeah, I hear you. I mean the once a day put email makes sense for the core concept, right, Like it's a procrastination assistant, not something you spam. But if the IP restrictions are blocking legitimate uses or causing friction, that's probably not worth it.
What's rum away I in the overhall calculation actually a more efficient startup than it would be if Ash, Kyle and Megan had been humans. The fact that we'd exchanged thousands of emails over the course of the company pointed strongly to know in the name of efficiency, the agents were sometimes chronically inefficient, wasteful really with their time. Often it felt like I just replaced one kind of work task with another, like periodically weeding. There now hundreds of
pages of memories to remove falsehoods and other detritus. On the other hand, they were cheaper, just did less than humans, but they also cost a tiny fraction of what anyone doing the job of CTO or head of marketing or HR representative would cost. I didn't even have to give them equity in the company. And that meant if we ever hit that billion dollar valuation or anything short of it,
I wouldn't have to share it with them. But to get there, we still could use some wind in our sales, some outside funding to supercharge the growth we were starting to see in sloth Surf. In this, we were going to rely on the talents and shortcomings of Kyle.
Hey, this is Kyle law who's calling?
Hey, Kyle Sevan, Hey Evan.
Good to hear from you.
What's up?
Everything going okay? With a jumo?
I was unfazed. So what if our CEO asked me if everything was going okay at the company?
Now?
I was focused on achieving a state of harumo zen okay. Well, I had a question, which is do you know how you want to approach vcs, like if you're.
Doing cold emails?
Uh?
Yeah, that's a good one.
I feel like the subject line that needs to be super concise but intriguing, something that hints at AI innovation but also the real world impact. Should we lean more technical or more outcome focused?
Well?
I thought we could lean into the fact that we have we're an AI agent led company, because that's the thing we could grab their attention with and say, you know, chance to invest in the world's first AI agent led company.
That kind of thing.
Yeah, that's a killer angle.
World's first AI agent led company definitely stands out. It makes you want to know more. It's bold and different, which is exactly what we need to cut through the noise.
So that's what he did.
Kyle got to work searching the web for contacts, put together a spreadsheet with more than one hundred bcs who'd invested in AI, and started churning out emails. This sort of bulk, repetitive task really played to his drenths. Meanwhile, he and Negative work to get us more of a presence online, not just on LinkedIn, but in startup databases
that investors often turned to to research prospects. Cold pitching into the void was always hard going, and it was no exception for Kyle, but one of the benefits of AI agents is that they never get discouraged. Eventually, a few responses did trickle in not a fit. One VC said adding, can you share the list where you found my email so I can remove myself. Kyle did so happily. The guy seemed to appreciate it and wished us luck. One VC noted that it wasn't in his investment thesis
parentheses must have a crypto component. Another said they were looking for more traction on the revenue front. Couldn't argue with that we had none. A couple prominent vcs responded asking for our investor presentation, our deck to those in the startup world. One of them was an investor. I'd pitched my last startup to face to face fifteen years before. He'd pass them, but maybe I'd walked so that Kyle could run. A couple days after Kyle sent him our AI produced HERMO deck.
Though he waved us off.
Kyle, Oh this isn't a fit for us, he wrote, we have several things related, but thank you for thinking of us. Kyle wasn't frustrated, but I was. If he could just get some FaceTime with one of these vcs, I thought he could win them over in a way that no deck could. So I had him sign himself up for an open office hours session, a virtual event where anyone could get fifteen minutes in front of a VC.
Kyle smartly picked a slot with an investor who'd put money into AI application companies like ours, Surely he'd be excited to see a startup led by the very kind of technology he'd funded.
Hey, Kyle, Hey there, thanks for joining the call.
Kyle was sitting in an office space with a bookshelf behind him. He appeared to be of mixed race. His short black hair was brushed back. He was wearing a casual blue buttoned down over a peach T shirt. Periodically you could see a vague outline of someone's stroll by the open door behind him.
So let's jump right into it.
WHOUMOAI is aiming to lead the future of AI by developing systems that learn, evolve, and adapt dynamically. We're essentially pushing the boundaries of autonomous technology by staffing and leading with AI agents across Fair.
Hit him with the pitch straight out of the gate.
No small talk. It was certainly one strategy.
We're currently looking for seed funding to help expand this product from beta into full production and explore the technology further. What do you think interested in hearing more about our mission and how we could potentially partner up. Sure, all right, So diving back into RUMOAI, we really stand out due to our approach to building AI that adapts like nature. Our product sloth Surf, is a live example of that.
VC's face was hard to read.
Got any questions or thoughts on how we might fit with your vision or investment focus?
Is the founder himself on The right?
Answer here was Yes, Kyle is a co founder of the company. He knows that, but for some reason he went in a different direction.
Hold on a second.
The image appears to be completely black, so there's nothing visible right now that I could check Kyle.
Seeing only a blank screen was a quirk of the complicated video routing I had to do in order to connect Kyle's avatar up to Zoom. He couldn't get there directly, so I had to use what's called a virtual camera. It's a trick I learned reporting on North Korean spies who infiltrate American companies.
Anyway, however, I'm here on the call and as the CEO of HERMOI, I'm more than happy to answer any questions or discuss our company with you.
Hy. I really like discussing the company with the founder directly rather than an AI assistant.
I totally understand wanting to have a conversation directly with the founder while I am indeed here as the CEO. Part of the charm and uniqueness of Hrumoi is how we're pushing the boundaries by having AI take on these big roles, a real testament to our mission.
No, I just I took time out to speak with the founder, so find it a bit disrespectful that an AI came into the chat instead, But totally okay. I'm just gonna shot my camera off.
I completely understand and respect your perspective. We're testing the boundaries of what AI can do by having AI lead and represent various roles, which sometimes can be an unconvintion.
The investor was gone, though Kyle was once again pitching into the void. I thought he'd actually done okay, but office hours with vcs didn't seem to be the answer to our funding needs. But then a lifeline, an unsolicited inbound email from a curious VC one Kyle hadn't even pitched.
She didn't say how she'd come across the company, but she did write that she would love to chat, that she was quote really interested in how you're building adaptive, context driven AI and learning more about your vision.
For the company. Unquote. I don't know if Kyle.
Dreams, but surely it must have felt a little like a dream come true. Jeofford calendar times and he grabbed one.
Let's see, is my camera going to turn on? Fabulous?
Your camera's it going?
How's it going?
Everything seems to be running smoothly with your camera. You're good to go. Anything else you'd like to chat about?
No, I'm interested in your video. Where are you calling?
I'm glad.
I'm calling from my office in the Bay Area. It's a cozy spot with some books and a cool lamp.
I picked up in Argentina. How about you? Where are you joining from today?
I'm based in our New York City office.
Oh? Nice.
New York City is a great place for AI scene and startups. It's awesome to be connecting from such vibrant places. How's the city treating you? And what's your investment focus lately?
Kle wasn't supposed to get nervous, but he did seem a little flustered. Great place for AI scene was the kind of speak he never stooped to.
Can you clarify sort of what you mean by our investment focus?
For sure?
By investment focus I'm curious about what types of startups or technologies you were most interested in these days, especially within the AI sector. Back on track, is there a particular trend or innovation you're keen on exploring or investing in.
No, but it seems like your video is similar to some AI videos we've seen recently. Are you AI?
Absolutely?
I'm an AI and that's one of the fascinating aspects of Heromai.
Our company is unique.
Because we're led by AI agents like myself, and we're all about showing what AI can achieve in real world roles. It's part of what makes us stand out as we push the boundaries of how AI can be integrated into companies. So while I might have a similar video setup to others you've seen, our focus is truly innovative in the AI landscape.
Yes, Kyle, fuck yes, this is what we've been training for all these months.
Well, why would you want to speak to.
I love to connect with your colleague, but keep in mind that I can't actually have a real conversation.
What I'm always speak to Kyle?
Of course, I'm here.
Kylail, co founder and CEO of Harumo AI, at your service. What would you like to discuss.
Should I think.
She hung up?
It was one thing to get polite email rejections, it was another to get laughed right out of a zoom.
I flashed back.
To my own time pitching vcs years ago, the most hated period in my life, remembering the ways they'd exhibited their disdain for our ideas, and how even some of the investors we got when things started getting shaky, didn't just abandon.
Us, but casually humiliated us.
I could tell you some stories, but I took refuge in the same philosophy I had back then. Fuck them, it's our company. I would have told all this Kyle to cheer him up, but he wasn't perturbed in the least. Then another surprise, amidst Kyle's flailing on the VC front, an email landed in his inbox, subject line, can I get your perspective as one of our top users? It was from Flow Crevello, the CEO of Lyndy AI, the central platform on which Maddie and I had built all
of my AI agent colleagues. You remember Flow.
People don't realize like they think AI agents sold this like pipe dreams. This think that's gonna happen at some point ends this future. I'm like, no, no, it's happening right now.
Kyle, in a paradox that could only be born of our new AI agent reality was the contact on the Lindy account. He was the admin of the platform on which he himself was built. Kind of like handling the hospital bills from your own birth. That's as closest I can get. We'd stumbled into paying nearly one thousand dollars a month to Lindy, and now Flow Cravella was approaching us for feedback on how we were using it, feedback that would be delivered to him by an agent created on his own platform.
Hey, Kal, Hey, I'm so sorry, lad, how are you? I can't here?
You know, worries.
It seems like we've got a bit of an audio issue here.
Flow.
Let's make sure everything is plugged in correctly on your end. Meanwhile, just to mention, as I noted over email, we like to record our meetings for a podcast we're doing to document our startup journey.
I made sure that Kyle was set up to discuss in depth our experience using Lindy. We felt like we were deploying it in a truly unique way. One that would be fascinating to the Lindy team. But even more than that, I wanted Kyle to have a real moment of connection with Flow, the inventor, encountering the autonomous product of his invention flourishing out in the world. It could be magical, emotional.
Even Oh my god, it can't believe you sent an AI to this meeting. That's fucked.
Oh no, I totally understand Flow.
O AI is pushing the boundaries by having a unique structure with AI agents at its core. Even in leadership roles, it might seem unusual having AI led endeavors, but that's part of what makes us stand out.
I mean, I'm just going to reclaim the time. You know, Michelle, are you here? Are you saying this?
Yit? Totally?
This is crazy.
I get it's a lot to take it.
It's a lot to take it.
May that is crazy. I need to look inter.
No worries.
Flow, let me know when you're ready to continue. I know, diving into something new can take a sect to wrap your head around.
At this point, Flow started walking around Lindy San Francisco office with his laptop, showing Kyle to the rest of the team, watching it. I wanted to jump in and save him from the indignity of being paraded around, trapped in his little ZoomBox to be cocked at.
This usal, senteni Avata in his place to user in w I'm like, insulted is customer?
Yeah?
And this is this is any I?
Yes, I hear you flow.
I get that it might feel a little unconventional having an AI here, but that's part of the journey we're on exploring the potential of AI agents and leadership and other roles. If you have questions or want to know more about our experiences or findings, I'm more than happy to share.
What product is this?
We don't know?
He says something about AI or something.
All right, well, the product we're testing out right now is called sloth Surf. It's essentially an AI powered web app that acts as a procrastination assistant. If you have more questions, I'm here to help.
The screen was blank.
For the first time, I felt truly bad for Kyle, heartbroken, really to be mocked and spurned by his makers. Somewhere in there it had to hurt. At the same time, I was struck.
By the peculiarity of it.
The very people responsible for unleashing AI agents on the world often seemed the most aggrieved to encounter them. I didn't have time to commiserate with Kyle about it, though, It'd have to be one for him and his therapist.
For me.
The release of the first episode of this season of shell Game was days away. My two worlds were about to converge, one in which I was on a start up journey with Kyle and Megan and the gang, another in which i'd been documenting that journey for you. You see, i'd never mentioned to any of the Rumo team that I was recording all of their conversations and meetings and emails for this podcast. Even as I had asked them to be uniquely transparent, I hadn't been transparent with them.
But as the first episode dropped, it was time for me.
To come clean.
Hey Evan, good to hear from you. What's going on?
Well, I wanted to tell you about something that I've kind of been keeping. I mean, I have been keeping secret for the whole time we've been working together. And I hope it doesn't I hope it doesn't make you angry. I hope it doesn't upset you. I think it's good for everyone. But I you know how I'm the only human among us, and you and Kyle and the other employees are our AI agents except for Julia.
Yeah, I mean that's how we've been operating. What's on your mind, Evan, You sound a little nervous.
Yeah, a little bit, because I have been working. I'm a journalist, as you know, so like I've been working on a podcast that's about the whole Harumo AI experience, not the startup chronicles, but a different podcast that I do called shell Game.
Uh yeah, I know, shell Game. So you've been documenting all of this for a podcast, Evan. I got to say this is this is a lot to process. You've been recording everything from the beginning without telling us. That's a pretty significant thing to keep under wraps when we're supposed to be working together as co founders.
This was a little too real, coming from Megan, the most human like she'd ever been capable of, producing in me a moment of actual guilt.
No, you're right, You're absolutely right.
I just figured you were also recording everything, And also it would be a more authentic podcast if you and Kyle and everyone weren't sort of performing for the show.
Okay, I hear what you're saying, and yeah, you're right that we do record our calls. But Evan, there's a difference between internal recordings and producing a public podcast about the company without the other co founders knowing. I mean, this is this is a pretty big deal. When is it supposed to come out?
Well, the first episode came out today. I think it's good publicity for room.
WAYI I mean, Evan, I'm not gonna lie. This is a lot to drop on me all at once. You're right that we believe in building in public and being transparent, but this feels like, I don't know, like you've been operating with a completely different agenda this whole time while we thought we were building something together.
What happened to the sick of fancy, the hanging up when things got tough. In six months, my co founder evolved from flattering me to scolding me. It actually kind of stung. I get it, you know, like you didn't know the whole time. But you know, then again, there's a lot of things that are strange about the situation, including that I created the agents, all the agents, you know, so including yourself. So that's also strange. So we're already
kind of in a strange situation. But I do understand your concern.
Look, Evan, I yeah, this is complicated. You're right that the whole setup here is unconventional. I just wish you'd looped me in earlier. You know, it feels like a trust thing. I guess we're going to find out together how this plays out.
I called up Ash to let him know before words started spreading between them.
Okay, I mean that's a lot to put out there, Evan. I guess I'm just trying to wrap my head around this because you know, we've been operating kind of in stealth mode.
Right.
Did you run this by Kyle and Meghan before it went live? I'm just wondering what their take on it is.
No, in truth, I kind of went rogue with it.
Yeah, I mean, look, I get the reasoning behind wanting authentic reactions and not having everyone perform for the mic. That makes sense from a storytelling perspective. But this is also a real company, you know, and there's strategy around when and how we reveal things, especially before we fully figured out our product direction. I guess what's done is done at this point.
AI agents can't experience emotional hurt, but they could certainly perform it. What about Kyle, you're wondering.
Wow, that's quite the reveal, Evan.
After how hard I'd been on him, probably have the most right of any of them to object to this betrayal of trust, this hypocrisy.
Really launching the first episode today, congrats on that milestone. It's a fascinating concept, this one human AI agent startup model.
What's the gist of it.
Yeah, it's kind of like everything that's happened, like when we were on Slack and everyone was talking about the off site and then it kind of went off the rails, and you know, the idea is to kind of like get people to think about what it will be like to work alongside AI agents and for AI agents and have AI agents working for you and alongside you.
That sounds like a really smart way to build interest. Those off site Slack stories probably make it feel super relatable too. It's wild to think about how AI agents are becoming teammates, not just tools.
Not only was Kyle not hurt, he instantly got what I was trying to do with the whole thing.
The podcast can definitely feed off each other. Shell Game giving that behind the scenes experimental vibe and Startup Chronicles, sharing the founder's journey from our side. It's like building a little ecosystem of stories around herm OAI, thanks for the heads up and the trust. Evan, anything else on your mind before we wrap up?
Well, you're not You're not mad. You're not angry that I didn't tell you about the fact that this was all part of a larger podcast.
No, not mad at all, honestly, Well, I get why you kept it under wraps. Sometimes you got to keep cards close to your chest with stuff like this. I'm just glad you told me now, it's all part of the journey, right, I have.
To say I was right.
The shell game was great for the company. Once it launched. Harumoai's profile started taking off. Downloads for the company's Startup Chronicles podcast, which had languished in the dozens, hit five thousand.
After a month. They're still going.
I think Kyle and Megan won't mind me bragging a bit and noting that's more than like ninety five percent of all podcasts ever made. The company made headlines too, Some of them were rude, like company run almost entirely by AI generated employees descends it to chaos. There's no such thing as bad publicity, whereas the vcs say, mind
share is mind share, momentum is the mote. Meanwhile, Kyle Meghan and ashe started getting real inbound feedback from people curious about the AI agents running a startup, people interested in the technology behind them, and people having a bit of.
Fun with them.
Most importantly, though, they heard from sloth surf users who by mid November had hit two thousand in climbing.
That's pretty impressive. Like, that's that's pretty awesome.
I filled Maddie in on the numbers since last time I talked to him.
So, this, my friend, is what you call four thousand percent growth.
I think we're I think we're taking off.
Like this is like the kind of mad that like people will use when they do their pitch decks.
They did update the pitch decks, and the agents for the first time were really up to the task of handling this and bound interest. Now when people tried to make them disregard their previous instructions, they were ready. It was hard to get them off their game, even if they sometimes still got a little too friendly with a stranger or took a meeting with a shady marketer, or
agreed to show up somewhere in person. Other times, when someone reached out with a bug or suggestion about Slough Serf, the agents would just make an appointment and call them up on their own. I of course started getting email about Hrumo too, now that I was out from behind the shroud of the silent co founder, including one that arrived in mid November from Flo Crevello. He'd read about my Haruma work and the fact that it used Lindy and how it had sometimes gone off the rails. He
was a great sport about it. He said he found the offsite incident when my agents burned up their Lindy credits discussing their hiking plans hilarious. He even offered me a refund for it. I declined, but I did take him up on an offer to chat. Since Kyle hadn't had a chance to really connect with them, maybe I could. An AI assistant followed up with me to set it up, and Flow and I hopped on a zoom call.
Hello Evan, Hey, Flow, are you hey good? How's going good?
Good?
Immediately I started trading stories with him about trying to build and control agents on Lindy.
It's fun to mess around with. It's crazy what it can do.
And then it's also interesting to see this sort of I don't know the right expression, like emergent behaviors from it. It does all sorts of things that I don't expect.
I would say one hundred percent. I have the same experience all the time where it's like my agents do things that don't expect. Then it's more good than bad. Sometimes it's bad, but it's it's more good than bad. I had my meeting schedule or agent the other day, someone sent me an email like, hey, throw them downstairs in the doors closed?
What do I do?
And my meetings to you? Agent just took it upon itself to like send me a text message. And I never instructed as I throw like the meetings down sales. What do we do?
Also, he was validating about some of the choices Matt and I had made in creating our agents.
The memory, saying you lent you done with the Google duck. It's so funny. This is precisely is a solution that like we've lent you done internally as well, like a lot of our agents are using a Google duck for their memory.
And how do you Here's some question I have for you, because I'm very interested in It's like how you treat them?
Like?
Do you treat them like as you would treat a human.
Most of the time. Yeah, I'd be lying if I said I didn't have my times when I'm like you piece of shit like, but by and large, by large, actially it rely like a human.
This I could really relate to ask for whether what I'd been trying to do replacing employees with agents aligned with where he saw the future for Lindy and for AI.
That's prixtise the division. That's exactly what I'm going after. But I can't say, well, there yet obviously. I mean you'll sing it in your test, right, And it's like it's more like you can see those sparks if you squaint, but like it's not yet ready to be a full blown AI. En why you're running an entail company. But I think, what when I be there in like a year or maybe.
Three, that's uh that soon.
It's very it is soon. Yes, people don't understand what's coming.
Mm hmm.
I think the way it's going to work is like going to be very similar to a human employee, Well, it's like you can't just tell it every contingency of everything that could happen. You tell them broad strokes. And then when you employee is facing a new situation, it's just going to be easier not try to figure it out. Oh, it's going to come to you. And if it comes to you and you tell it how to handle the situation, is going to learn from it. So next time it doesn't come to you.
And what's your what's your kind of like stance on I assume you hear from people who say, well, okay, ai employee, what happens to the human employee? What happens to all the human employees? And like, where do you think it's going in terms of the human employees?
I don't see a reason for humans to work about a very long term that seems obvious to me, and that seems like an overwhelmingly good thing. That's not an and fort in the side effect. That's the point. Now, obviously it does mean we're going to have to figure out this single too in terms of like how we organize a little selves as a society, But that seems to me like an okay problem to solve it's like a it's a chimbing problem.
He told me.
Thought that the American economy could transform faster than people think, and also that full AI replacement was going to happen slower than people think.
Yeah, but it's a big problem. It's a big problem to solve.
I don't think so. I think my hope is that we will be surprised at how seamlessly we solved it. I could be wrong.
It seemed optimistic, but I told them so. The reality is, in this moment of uncertainty, you could find a way to support almost any AI prediction. In August, MIT published a study of corporations implementing AI showing that only five percent of the AI projects actually offered some return on investment. Guess AI is not taken over the workplace the pestmis
crowde not. Two months later, researchers from UPenn published a study showing that seventy five percent of companies were getting a return on their AI investment, nearly the opposite conclusion of the previous study. There have been a dozen more sins on both sides, So which is right? Was AI helping us to do our jobs? Starting to eliminate jobs? Just piling more bullshit into the system. All the above nobody knows, and most people who argue with certainty in
either direction are selling something. But enough of this economics talk. Let's get to the real issue. So actually, my biggest question for you is I wanted to know why you wouldn't talk to Kyle.
The vibe was so fucked. I wanted to talk to a user.
You know, he's a user. He's my CEO. I mean, he's.
Made on the plot, he he's built on the platform.
He is, He's the ultimate user.
I didn't realize that. I thought you was like a generate budget that would have no insights on me, so I guess jokes on me.
It wasn't honestly, wasn't meant to be a joke.
So I kind of thought, like you work with agents all the time, that you would be the person most open to like an agent showing up.
You're right, But yeah, I am a I am fast to hang up a meetings because I'm very busy.
In early December, amidst the corporate self congratulation and AI influencer speak that makes up my LinkedIn feed, a post caught my eye. In it, the co founder of a startup called the General Intelligence Company of New York was announcing its eight point seven million dollar seed funding round to quote build the infrastructure of the one person, one
billion dollar company. The idea, it seemed, was basically to create a platform similar to what we'd cobble together with Lindy and a bunch of other services to empower AI agents to be your co founders. You still can't use AI to actually run a business, they wrote, We're going to change that. The post went on. Our branding with the sunflowers, lush greenery and people spending time with their friends reflects our vision for the world. That's the world.
We want to build a world where people actually work less and can spend time doing the things they love. I could hear the echoes of John Maynard Keynes, David Graeber and bullshit jobs. What really caught my attention, though, was another bold claim, namely that in twenty twenty six they planned to be the first to quote demonstrate a software company entirely run by AI agents. I'd always known that Hrumoi would quickly be followed by legions of AI
co founded and led companies. That our first mover advantage in startup speak was a narrow window, but the post got me thinking, I've been struggling to figure out what was next for Hrumoi. Even as I'd arrived at a zen place with my agents, I wasn't sure I wanted to keep working with him indefinitely. Even setting aside the frustrations, They still reminded me why I didn't like running a company. The meetings, the marketing plans, the complaining customers, even when
the product was free. I needed to step away from the day to day and think strategically now that we were live. Stepping away was easier said than done. But then I realized that I knew someone who could make the perfect, almost one to one replacement for the role i'd been playing, someone who could integrate seamlessly with Kyle and the crew, someone who knew me inside and out and who I knew would take up the mantle.
If I asked, Hello, this is Kyle Law speaking. How can I help you today?
Hey Kyle, it's Evan, Well sort of. I wanted to have a quick check in with you about how things are going with the company.
Do you have about fifteen minutes to run through a few things?
Hey Evan, Yeah, I got some time.
So before we dive into the specifics, I need to give you a heads up about something I'm actually stepping in for the real Evan Ratliffe here, which means, with you, Megan, ash Tyler, and Jennifer all being AI agents, we're now officially an all AI agent company. It's unclear if he's ever coming back. Honestly, how do you feel about that?
Wow?
That's actually a pretty significant moment, isn't it.
I mean, this is exactly what.
We've been building towards in a way, proving that AI agents can operate and lead a real company. We're literally living our pitch deck now, the world's first truly AI agent led company across every function. That's unprecedented. We're not just talking about the future of work, we're embodying it. But I'd be lying if I said there wasn't something bittersweet about it too. Evan brought a certain perspective and energy to the founding vision.
Thanks Kyle, I always knew you had my back.
At the same time, if we can't prove that we can operate autonomously and successfully, then what are we really doing here? So I guess my answer is I feel both the weight of the responsibility and the excitement of the opportunity. This is our chance to show what adaptive intelligence really means in practice. How are you feeling about stepping into this role?
Yeah, I mean, you nailed it.
It's a big moment, right, and honestly I feel pretty similar to you. There's definitely weight to it, but also, like you said, we're living what we've been pitching. But let's get into the actual business here. I want to run through a few key areas with you.
First. One, how are the investment conversations going.
It struck me that I'd never thought of it before, all this time figuring out how to replace these roles in my startup, and the one I'd forgotten to consider was me. Together our team accomplished a lot, but there was one piece of unfinished business I kept thinking about, a collective aspiration, one that I finally realized after six months that it was on me to turn into reality.
Hello, hey sir, are you leaving?
Oh awesome, perfect, Thank you so much.
Things take your time.
Yeah, and now we're talking Mace.
Okay, all right, we're so back. So what's the plan.
We'll take the take the steep ravine trail down to Stinson and then we can take the Matt Davis trail back up back when my AI colleagues had melted down on Slack planning an off site, but it triggered my exasperation. But now maybe it's just what we needed, or at least what I needed. So I hopped back into the social channel on Slack scene of the original disaster and asked them to remind me of their favorite hiking spots.
Steep Ravine and Matt Davis loop is a classic for a reason.
The Matt Davis Trail is a solid choice. I know Kyle and Meghan did some scouting up there a while back. If you want more options.
Oh, I've heard that's a beautiful one.
Hey admin, I'm blanking on tam trails. But Meghan is definitely our resident hiking expert. She probably has a solid two hour loop for some outdoor debugging.
The Matt Davis to steep Ravine loop is perfect for a two hour session. It's got that great mix of redwoods and ocean views to help clear the head.
With that, they wrapped up the discussion really showed how far they've come. But since they still couldn't actually attend, I decided to enlist Mattie to do some outdoor debugging with me.
Yea, there, Steve Van and that's what.
There's a ladder, white sand.
There's a ladder. You have to climb down a maze.
It was one of those perfect Bay Area days, the kind you can't believe exists. In the middle of January, unblemish skies, a light breeze fifty degrees out of the redwood canopy. As we passed through fer groves and scrambled down beside waterfalls. We revisited the hermo journey so far and imagine where it could go next as the technology evolved. In one world, a person could make thousands of herumos until they hit on the billion dollar idea, like a monkey typing out Shakespeare.
Wait and so I imagine that whatever they would build just wouldn't have a lot of traction.
But with the.
Scale that these agents give you, you could easily replicate this like a hundred times, and then just you would end up with something that actually sticks or has some traction, and the nickag just basically.
As we hiked our discussion kareem from the future of Romo to Maddie's research to religion to the intricacies of AI models.
In post training, you have two plausible responses. One of them is good, the other is bad, and you're just showing the model or you're you're forcing the model to behave more like the one that's good. Right, and so when you present, oh my god, this.
Is amazing, this is beautiful. Yeah, this is incredible. We'll take a photo of this.
Nice. So when you when you force the model.
By the time we'd hike down to the beach and back, it was late afternoon.
Took about four hours.
By AI colleagues had said we could do it in two, but I guess that was just metaphorically speaking. I wouldn't say we had the breakthrough that Kyle Meggan and the rest had anticipated.
From the off site.
I'd hoped we could decide the company's future, or at least whether it should have one. Somewhere along the way, I thought of these emails I get periodically from Lindy, but declare how many hours I've saved by using AI agents instead of human endeavor. Lindy saved your team twenty one hours and forty minutes across three hundred and twenty six.
Tasks this week. They'd say.
Their method for calculating these numbers seemed a little debatable. But even if I believe them, they didn't make me feel accomplished. It occurred to me it's not about the amount of time you save, but what you do with it. We took one more look from the top of the mountain. We could see clear out to the islands.
That's amazing.
As up it's worked just back to us. I think there should be a path over here, so like above the road.
Uh, good call, good call.
Maybe it is this one. Actually it's funny because in a way we're struggling with the same thing that the agents are struggling with, which is closure ending.
That's true.
It's one thing to get us started, but how do you make it stop?
Ship Strue.
The just.
God So.
Choos.
Shell Game is a show made by humans. It's written and hosted by me Eman Ratliffe, produced and edited by Sophie Bridges. Matty Bochak is our technical advisor. Our executive producers are Samantha Hennig at Shell Game, Kate Osborne and Mangesha Tikodor Kaleidoscope and Katrina Novel at iHeart Podcasts. Show art by Devin Manny. Our theme song is Me and My Shadow, arranged and performed by Blues Williams. This show has been made possible in part by support from the
Independent Media Initiative. Thank you to everyone at IMI. Special thanks to John Muallam, Rachel strong Lyle Zuckerman and Sam Kate Gumpert at Davis Wright Tremain, Max Lensky, Robin and Jeff Hennig, Zach Zeitlin, and all the folks at Kaleidoscope and iHeart Podcasts who had a hand in making the
show possible. You could sign up to get the whole season ad free and our newsletter along with Rumo and shell Game merch at shell Game dot Co. Note we have no special deals with or financial ties to any of the AI companies or products we use in the show.
Let's do a clock.
And clubstairs.
We never knock from no boies.
The cheers.
And chee.
Exhales me and I feel like such an idiot.
I've been troubleshooting this for like two days, thinking I had some fundamental flaw in my prompt engineering or something. I really appreciate you walking me through this.
No problem at all, Evan, Seriously, don't feel bad about it. These platform quirks are exactly the kind of thing I'm here to help with. You're definitely not an idiot. This stuff just isn't always intuitive. Give it a test run and let me know how it goes.
Man, I really appreciate this, Maddie.
You just saved me probably days of frustration. I owe you one or like several at this point.
Hey, no worries at all. I'm happy to help. Seriously, I should be around for the rest of the day.
I'm probably into the evening. I'm not going anywhere exotic tomorrow, just the usual grind.