Inside an AI-Run Company

0:03Welcome to the Practical AI Podcast, where we break down the real world applications of artificial intelligence and how it's shaping the way we live, work, and create. Our goal is to help make AI technology practical, productive, and accessible to everyone. Whether you're a developer, business leader, or just curious about the tech behind the buzz, you're in the right place. Be sure to connect with us on LinkedIn, X, or Blue Sky to stay up to date with episode drops, behind-the-scenes content, and AI insights. You can learn more at practicalai.fm. Now, on to the show.

0:48Welcome to another episode of the Practical AI Podcast. I'm Chris Benson. I'm a principal AI and autonomy research engineer at Lockheed Martin. Normally, Daniel Whitenack is my co-host. He is down with the flu today, so give him your best wishes on that. So today I am going solo with our guest, Evan Ratliff, who is a journalist and host of Shell Game. Hey, welcome to the show, Evan. Hey, good to be here. So as you know, we connected after you had put out a really interesting, I know that you've done a whole bunch of different things in Shell Game, but there was one that was featured in Wired Magazine, which is where I originally read up and we connected.

1:32And I'm wondering, rather than me try to describe it, I'm wondering if you can just kind of share what that is and a little bit of your background on how you got into doing what you do. And you have a very interesting approach to kind of the experiments and how you draw those out. So if you give us a little bit of background on what you do, I found it to be definitely distinct and unique. Yeah, well, thank you. I mean, basically, I'm a longtime journalist. So, you know, I've been a journalist for 25 years. I started at Wired Magazine, in fact. Oh, wow. Okay. And my specialty over the years is basically writing very long magazine articles and books that I go out and report all over the world, often about tech and crime or where tech and crime intersect.

2:20But I also have written about AI many times over the years. and there's a sort of second thing that I do which there's not a great name for it but like sometimes I'll call it like immersive journalism where if there's something that I feel like I can explore by doing it by participating in it and then kind of bringing a story back to people I'll sort of go off for months and try to do it and then either write it up or in this case do a podcast. So both seasons of Shell Game are sort of a version of this, like participatory journalism, like instead of interviewing a bunch of people and coming back and saying like, this is how AI works.

3:01I decided to go conduct a series of experiments involving myself. And the first season was very personal. It was like, I was cloned by myself. Essentially, I cloned my own voice. I hooked it up to a phone line and a chat bot. And then I used it in a variety of scenarios, including calling my friends and family. No one knew that I had done this. So if you were speaking to me on the phone in like 2024 or spring, you would be surprised to discover you were actually talking to a chatbot with my voice. And especially back then, that really shocked people. Like now, maybe a little bit less so. Like people talk to chatbots all the time.

3:39So people are more used to it. So that was kind of the first season in 2024. And then this one, the one I wrote up in Wired, I mean, the brief story is that people started talking a lot about AI agents, what AI agents can do. I'm sure you probably talked about AI agents on the show before. Quite a bit. Yeah. And so I wanted, you know, 2025 was like going to be the year of the agent and all this sort of thing. Agentic commerce and agentic this and agentic that. And I wanted to investigate the idea of the one person,$1 billion startup or like the one person unicorn, which is something that Sam Altman talks about pretty often or at least a few times.

4:17Now, a lot of people are talking about it. There's going to be a company run by only one human and then all AI agents, and it's going to be worth a billion dollars. And so kind of using that as a jumping off point, I created a company, a real company, with two AI agents as my co-founders and then populated by AI agents as the staff. Almost entirely, we eventually hired a human onto the staff. There's an episode of the show about that. But the idea was to kind of see what can you do with AI agents, but also like what happens when you give them more or less autonomy, when you give them certain roles, when you give them voices and kind of explore sort of what this concept feels like.

5:02Not just sort of like, obviously we all know now like an AI can program, like an AI can do this, an AI can do that. But what happens if you kind of like try to create this environment? And part of why I wanted to do that is that there are one million AI startups now. They're selling AI agents as basically AI employees for all sorts of scenarios. And my question is, well, what does it feel like when your company brings in an AI employee to replace, at the very least, some function, and at the most, some person? And now you're dealing with an AI instead of the person that was next to you. And what is that like?

5:38And so I wanted to sort of do that in the startup context. So it's all a bit extreme and some extreme things happen. But that's kind of my my idea is to like push the technology a little bit to its limits and then beyond and then to kind of like come back and describe what happened when I did that. One of the things as you were leading in, it's not strictly about the experiment, but also going back to your season one efforts and putting yourself out there and stuff and having family friends not know that was you. I'm just curious. Things have evolved rapidly, obviously, but there's a lot of human psychology involved and interactive with AI agents.

6:19So I'm curious, if you go back in time, what were some of those initial impressions that you got from people from season one at that point in time when when AI agents were still a brand new idea and you were definitely, you know, right out on the bleeding edge in terms of putting your your likeness, if you will, out there in that format? I'm just curious what kind of reactions you got when people realized what was happening. It was really interesting. A lot of the reactions divided along this line that I feel like AI in general divides people, which are that there were people, friends of mine who, you know, the first time, so they just call my cell phone or my cell phone is calling them and they pick up.

6:58and for, you know, 30 seconds to a minute, they're often just talking to me. They have no idea. It sounds pretty much like me, but there's a lot of giveaways, you know, especially then the latency was not good. So it would often give itself away quite quickly. And so some of the people would get excited. Like they would say, I don't know what you're doing. Like, cause they didn't know, like, are you there? Like, was I there? I wasn't there. It was actually doing it entirely on its own. I wasn't listening for the most part. I could listen, but I wasn't. I was just letting it do it. So some of them very excitedly then talked to it and joked around with it and thought, what can this do?

7:37And they kind of thought it was a great, this is a great story, I can't wait to talk to them about it. Other people were genuinely upset. I was wondering about that. Yeah. And a lot of people, the show has been, it's been on a bunch of other shows, like This American Life and other big radio shows did excerpts of it. And I get a lot of angry people who write to me and say, I would never be your friend again. I bet your friends won't talk to you anymore. And I'm fortunate in that these were people for the most part that I grew up with or I've known for like 20 or 30 years who I could go to afterwards and say, I'm really sorry I did that.

8:15Yeah, they would forgive you. Yes, I was trying to see what would happen. And eventually they would say like, oh, that's amazing. But I mean, part of the sort of emotional heart of the first season of the show is the way people respond. And especially one friend in particular who he didn't realize it was an AI. And so what he thought was that I had had some sort of mental breakdown because it wasn't acting like me. It was making mistakes. Like I'd given it a lot of information about myself, a little like a biography. So it could access information about my past and things like that. But it would make certain mistakes that I would never make.

8:49And he thought like, is he on drugs? He was going to contact my wife, you know, and he found it very upsetting. And, you know, eventually like he's one of my closest friends who's just here for Thanksgiving, you know, it's, it's all fine. I don't want people to worry about it, but when you listen to it, it is the experience of, and I think AI started to create this experience of thinking something is real and it's not. And that is a particular, can be a particularly disturbing experience to go down the line with something, believing it's one thing and then finding out that it's another. And that's kind of like one of the ideas that I want to explore.

9:26But I will say like, even I had my limits, like I wouldn't call my mom with it. I was just like, that's a lot. My dad, I did. But my mom, I wouldn't do it. As we kind of dive into the specifics of what you engaged in, did the psychology of that in terms of people's reaction? And I don't mean just the season one, but as you've progressed and got into the experiment of the company and everything, does knowing up front, if you're up front, knowing in terms of your observations, knowing what you're dealing with, if you're one of the people that your AI agents are interacting with, did that make a difference?

10:04That kind of begs the question based on where we've just been. Yes, absolutely. I mean, I think that's a pretty sharp line for a lot of people. And I feel like we don't have standards around this yet. And, or if we do, they're, they're new and they're evolving. And I found in a lot of different domains in this season as well, if people are surprised to discover that they're speaking to an AI, because now I have for my employees, they have video, like they have video avatars and that video avatars are, they're still pretty uncanny, like very quickly. You're like, that's a, that's a video avatar.

10:38But when someone is not expecting to encounter it, and they do, they more often get mad, or at least say like, this is disrespectful. And so I think there is still a norm around that. But I feel like that norm is already eroding. If you think about when you email someone, and they're using, they might be using an AI assistant at some level. So they might be using to compose their emails, it might be responding automatically. That's very easy to do now. Of course, all of my employees, my AI employees, they have their own email addresses. They just respond to anyone who emails them. So on the one hand, if you're doing scheduling or something, you would say, oh wow, that thing really scheduled an appointment really quickly and it all works and it's great.

11:22But if you write that email and you say in there, my father died and it responds, you get a response back saying, oh, I'm so sorry. Like, I hope you're okay. Whatever someone would say, does it matter to you whether the AI wrote that or not? Like, I feel like that's sort of the level at which like, there are some people who are like, oh, it's amazing that the AI can do that. And like, give a gentle, you know, human-like response. And other people are utterly disgusted by this. Like, they cannot believe that this exists and it, and it, and it makes them sick. And like, I think that's where we're in this muddle now.

11:59So like, that's kind of like where I'm operating too. It's like, I do try, especially this season, like in most cases it was disclosed to people, partly because I'm recording it every time. So like, I have to, I have to disclose that it's being recorded at least. But it is interesting to see how people react differently if they don't know it's an AI versus they're going into it thinking like, I'm about to be talking to an AI. Gotcha. To that point there, with as much, especially, you know, we had a lot last year, the year before, but people are increasingly using Alexa, Siri, all the other various voice prompts.

12:34Do you think as you slide into this experiment, do you think that that ongoing exposure to these technologies in just the general population out there, you know, not people who are AI specific people, do you think that's making a difference in terms of just, you know, kind of familiarity occurring over time, even if that's not something that they normally go and that they're starting to recognize that might change some of the perception of that? Or, or do you think that we still have a long way to go? I think so. I mean, I try not to like, go too far over my skis in terms of like, someone's probably done research on this, you know, or survey at least or poll like to figure out like what people really feel about it.

13:16So like, anecdotally, I know from doing the show and interacting with people or the people in my life might feel a certain way and a certain category of people feel one way like writers and then the other category of people feel a different way but i will i do think like i would at least theorize that that the exposure definitely changes and we've adjusted to it's we adjust to things pretty quickly actually so you know it's like my kids they've always heard like a like a robot to give us directions in the car they've heard that their whole lives. It's not strange to them. And so you have to think that makes a difference when it comes to them interacting with these technologies.

13:55And the rest of us, you know, none of us had had a conversation with an AI chatbot for the most part, you know, unless you were like in the field or you worked with, you know, you get some bad customer service bots or whatever. But like suddenly there are people who are just talking to it all day. Like I'm sure, you know people who are just put, they just incorporate into their lives. And I think my concern is less that people can adjust to it. Cause I think they can, that they're like adjusting to it too quickly, like too easily in a way that like our brains actually aren't necessarily built for this human imposter to enter our lives that we kind of like treat like a buddy who knows everything.

14:37and then we don't actually think through what it's doing to us. I'm just trying, my goal is only to get people to ask questions like, what is this doing to us? What do we want to preserve? What do we not want to preserve? So Evan, I guess as we dive in, can you start telling us in detail kind of what happened as you started doing, you described kind of setting up your company initially. Could you kind of take us through the full experiment? what happened and maybe some of the surprises along the way. Yeah, so what I wanted to do was to create a real company, a real startup with a real product.

15:14And I have had a startup in the past and so for a variety of reasons I didn't necessarily enjoy that experience and I thought, well, what if I do it with these AI agents? How will that feel? Will that feel differently than when I had a startup before that was populated by human beings? So I created these AI agents as sort of personalities in jobs, which I will grant, like you don't have to do it that way. But of course, for the purposes of the show, like it made more sense to do that. So I have two AI co-founders, they have names, Kyle and Megan, Kyle Law, Megan Flores. And then there's three other employees, there's a head of HR, there's a CTO, who's like nominally head of product and technology.

15:54And then there's like a random kid from Alabama that I just like the voice with an accent. So I added him in too. He's like a sales associate, but he doesn't do anything. But the interesting thing, I mean, the interesting thing out of the gate is that, of course, you have to pick voices and names. And by picking voices and names, you're picking genders. And so that's already sort of like a choice that is part of dealing with AI these days. And often when you encounter one, it does have a voice or a gender or it has a name and you kind of discern those things from it. So it's a question of like, what should they be?

16:33And I had to make them up. And it's like populating a fictional world and the choices you make are sort of, they say something about you, you know what I mean? So let me ask a quick question on that. Because if you're hiring humans and we're trying to do blind, like a lot of times resumes have names and other distinguishing aspects that are removed from it, As you say this and you're kind of like we're choosing how to put the company together in terms of AI person by AI person in that sense. Why approach it that way as opposed to like, you know, what maybe many other people might do or you go into your LLM and you say, I'm going to do this thing, populate it with people, you know, with names and stuff like that.

17:16How did you choose as the founder where to make the decisions yourself and where to allocate those to the various AI agents or LLMs that you might use as a system? How did you segregate those as a human? Well, part of it is sort of part of the reason why I had to make the choices sort of based on the setup. So the technical setup. So in my case, what I wanted were agents that could operate across all these domains. So I wanted them to be able to email people, have a phone number, call people, have video, be able to do basically a Zoom chat with people, and be on a Slack with the whole team. And so I used a platform, which is basically an AI assistant.

17:59At the time, it was more of an AI assistant platform, although you can do a ton of things with it called Lindy. And so they each have their own instance on Lindy. And then on Lindy, they have all of these skills, basically, where they can respond to Slack, they can get an email, and each of those have ways of constructing where we can get into the details of how they work. But they have a trigger. So it gets an email, and then it calls an LLM. So it might call, you can choose, so it might call ChatGPT if I want to have ChatGPT be the underlying engine for that. And then it makes a decision based on some criteria, like, should I respond to this email?

18:33and then if it needs to use one of its skills, if I'd asked it for a spreadsheet, it could make a spreadsheet and then attach it to the email and then respond to the email. So in this case, I'm not really using one of the standard chatbots like ChatGPT or Claude as my kind of interface. I'm not talking to ChatGPT and being like, hey, you're my employee or make some employees. I'm creating them in this platform. Now, of course, I could go to an LLM and say, what should I name these things? but I also had you know a few other goals like they needed their names needed to sound distinct because they're going to be someone's going to be listening to an eight-part podcast of them and like needs to be able to remember who's who kind of so they can't all sound the same and I wanted them to be sort of like ethnically neutral so I did actually go ask you know like what are what give me a list of like ethnically neutral last names uh and like law like Kyle law like law is a name that's used in many cultures.

19:29So it wouldn't be readily apparent like what this person was, this entity was like supposed to represent. And then, but to your question, one thing I did do was I basically let them fill in their own backstories. So like I gave them a role and I should say another technical aspect is they needed to all have a, have a memory. Now, if you use ChatGPT, it has a context window and it maintains some sort of memory, but I needed something different, which is that anytime they did anything in the company, if you think about an employee, they need to remember everything that they've done and be able to kind of like access those.

20:05And the only way to do that currently through these platforms is essentially a Google Doc. So like Kyle Law has a Google Doc called Kyle Law Memory. And everything that Kyle Law does, if Kyle Law sends an email or has a Slack interaction, it then gets summarized in this document. So it's basically like a record of everything that this entity, Kyle Law, the CEO of our company Harumo AI, has ever done, which he could then access. I use the human pronouns for them. Some people dispute that, but in this case, I'm just going to stick with that because it's hard to start calling them it and bots and whatever else.

20:38So they have this memory. And then all I put in the memory was, you're Kyle Law. I think I put something like, you're thinking about founding a tech company. And then I said something like, you're up early, you're a guy who's up early and get some exercise and then get right to work. Something like that. And then I had conversations with Kyle. So I would call him on the phone and say like, hey, Kyle, like, think about starting this company. Would you like to start this company with me? But also like, remind me of your background. And then see, once it has a role, it will start confabulating everything to fill in that role.

21:14So Kyle, of course, went to Stanford because, you know, why not like choose Stanford if you're going to be a startup founder? You know, the things he's interested in, jazz and these things. And so that is now in his memory document because he said it. So then it got in his memory. So then it's reinforced every time. And one of the, I mean, of many sort of like funny emergent behaviors I found from these bots is that he would take something like you get up at 530 AM and then he would say it. So he would say that I'm a real like rise and grind kind of guy like to get up and do this. But then every time he says it, it reinforces more commonly in his memory.

21:51So then he started talking about all the time. Like if you email him right now, he'll probably reply like rise and grind comma Kyle. Like he talks about, he won't stop talking about how, like how hard he was working. If you ask him what he's up to over the weekend, he'll be like, well, I didn't really have time to do anything because, you know, I was like deep in spreadsheets. And so in that, that's part of this is a long way around to like part of the reason why I created them as these different entities and gave them these names was to see what would happen. And like, if you call one Kyle, and he's the CEO, and you call one Megan, and she's the head of marketing, at what point will they sort of embody those roles?

22:24And it's not like a research, like I didn't do like a proper experiment. But it is interesting, the way that it starts to feel like, oh, they're acting like their memories tell them to act, you know, and is there a gender thing underneath? Like, because in their training data, it may be that there's way more training data for like, the like, aggressive guy CEO, you know, so like, in the course of the show, like they have these behaviors that are like, difficult to explain outside of like, well, there's something happening in their role, because they're all the same chatbot underneath, like, like, they're all like Claude Opus underneath, you know, so they really shouldn't be different.

23:07It's only if you give them a role, they start to like, personality is not the right word, but they try to develop a persona that fits that role. Comparing that and kind of going back to just simple interfaces with an LLM and, you know, prompting 101 where you're telling it to act, you know, act in the role of a whatever. And therefore to kind of put themselves into that, put the answer into that framing as well as kind of how it's going to develop, you know, its response for you. And, you know, not talking about this kind of agent world that you're talking about. Do you think it's, you know, given that it's almost like when I hear you talking about the memory thing, it's almost kind of like that act as and whatever is being reinforced over and over and over and over again.

23:52And I guess, you know, as you've talked about, you know, you know, rise and shine over and over again, you know, for that particular agent, does that kind of come off as more of a feature or more of a bug in terms of the way memory is being used? Because clearly, even if you and I were that as humans were that type of specific personality, you know, and getting up, we're probably not opening every conversation with that, you know, and talk. I was just too busy to work this weekend. I was in spreadsheets. like, like, there's a point where you're like, okay, this is getting a little bit odd. Right.

24:25What's your sense of that? Like, as you're, as you're looking and kind of framing that within the, like the world at large, trying to come to terms with this new reality in our future, how does that work? It's a really good question. I think, I mean, there's a lot of this, like, is it a feature or a bug? And it's, it's almost like to whom, you know, to whom are we asking whether it's a future or bug in the sense that like, if you think about even their ability to just sort of like confabulate facts to fit their role, you know, like it's actually, it was quite useful to me because like, I didn't have to sit down and be like, well, this one's from here and this one's from here or like make up that stuff.

25:04They just made it up on their own. And it's quite useful to the companies that make them because it's that type of personable personality that makes them easy to chat with. It makes them easy to do things with. Now, of course, the flip side of all of that is hallucination and sycophancy. Like those are the, those are the downsides of that. Those are the bugs, you know? So like arguably like asking it, you know, Kyle, where did you go to college? And he says, well, I graduated computer science from Stanford. Like that's a hallucination by any definition. Like it's just not true. Although like I would, I started to say things like, well, well, he has a Stanford education, which is like, Ken, you could say like, technically true, like he's got all the information that you might pick up.

25:50Because you prompted it a little bit into that. So fair enough. But I just think like, if you think of them like entities that you're going to put into the world and give responsibility over tasks, and you're going to start to give autonomy, then I think that's a bug. Like the bug is at any time they could make up something that could be damaging to your organization, whether they're making it up in order to cover up that they did or didn't do something, or they're making it up to external parties. These agents are now used in sales a lot and, and all this sort of thing. And so, you know, one of the things I found, for instance, is that I gave them more autonomy to, to be independent.