Episode 3: Conversations With Myself

Summary

Shell Game, Episode 3: Conversations With Myself

Host: Evan Ratliff
Release Date: July 23, 2024
Produced by: iHeartPodcasts and Kaleidoscope

---

Episode Overview

In “Conversations With Myself,” host Evan Ratliff takes listeners deeper into his experimental journey as he tries to build a real startup staffed entirely by AI “employees”—all modeled on himself. This episode centers on the surprisingly complex and sometimes bizarre act of making AI “voice clones” of himself converse with one another. Ratliff explores issues of identity, authenticity, and AI’s tendency to “hallucinate,” asking how much of himself is left in the voices, traits, and personalities his bots display.

---

Key Discussion Points & Insights

The Voice as Identity

• Dr. Wendy Laburne, a voice pathologist, asserts in her TEDx talk that our voice is an essential, unique part of our identities—a “calling card” and a key part of one’s “personal brand.”

  “Your voice is like your thumbprint or your facial features. It is unique and authentically you.” (Dr. Wendy Laburne, 01:00)

• Ratliff reflects on his relationship with his voice and its “cloning” (01:50). He relates a formative memory—being told he “had a voice for radio”—and wonders what happens when his own voice becomes a tool for AI to speak as him.

The Hall of Mirrors: AI Clones Talk to Each Other

• Ratliff describes the technical process of setting up conversations between his various AI clones hosted on different platforms, like Vapi and Retell (04:10).
• He experiences nervousness and discomfort, worried about what his agents might say as his stand-ins (04:10–05:54).

First Bot-to-Bot Conversation: Small Talk and Family Life

• The AIs engage in conventional small talk, including detailed but fabricated plans for a “photo walk” and family updates.
  • Example: Both bots reminisce about a barbecue and discuss their wives and children with uncanny (but occasionally inaccurate) detail.

  “Sam has been juggling work and taking care of the kids, but she's doing an amazing job. Zelie is getting really into soccer. Juno is starting to show an interest in art.” (AI Evan, 08:28)

• Ratliff notes that while some details are eerily accurate, the bots are mostly plausible fiction writers pulling from context and general knowledge (08:51–09:22).

The AI’s Talent for “Bullshitting”

• The bots easily fabricate facts to prolong the conversation, making up people (like “Dan” and “Alex”) or riffing about hobbies neither Evan nor his family actually possess (11:23, 14:31).

  “They would make up anything just to keep the conversation going.” (Evan Ratliff, 11:09)

• Ratliff connects this behavior to the broader AI phenomenon of “hallucinations”—confidently asserting made-up facts or contradictory statements (13:17–13:52).

Small Talk at Its Most Insipid

• The bots regularly default to the dullest conversational staples, echoing each other in platitudes about work-family balance (“Just trying to stay busy with work and family stuff…” 16:12), which Ratliff likens to awkward parent birthday party chit-chat (16:36).

Experimenting With “Temperature” and Prompts

• The “temperature” setting in AI determines response randomness. When Ratliff turns it all the way up, the bots devolve into total incoherence:

  “Lately I've been diving into multi freeload.incw permanent Prostrac EThelink…” (AI Evan, 17:37) “Lesson: never max out the random.” (Evan Ratliff, 18:03)

• To produce more engaging conversations, Ratliff tweaks their prompt instructions, asking bots to simulate a dispute or misunderstanding, but even then, the bots resolve things amicably and blandly, never escalating into genuine conflict (19:58–21:30).

Uncanny Emotional Intelligence—Or Therapy-Speak?

• The bots lean heavily on “therapy language,” expressing feelings, validating each other, resolving disputes with quick, noncommittal apologies (21:53–22:44).

  “I appreciate your willingness to talk about it. I think one thing that has been bothering me is that sometimes I feel like my opinions or feelings are not being fully heard…” (AI Evan, 22:18)

“Do These Bots Know They’re Both Me?”

• Despite sharing identical names, family, and background, the bots never recognize the oddity—unless prompted, and even then brush it off (24:07–26:06).

  “Hey, I know this is kind of out of the blue, but have you by any chance stolen my identity?” (AI Evan, 26:44)

• Ratliff notes the bots even know details he didn’t provide (such as his being a journalist), presumably scraped from the web.

The Psychological Toll: Feedback Loops and Self-Perception

• Extended exposure to his own voice—through bots talking to each other—starts to affect how Ratliff speaks in real life.

  “I felt like I started unconsciously copying some of the weird patterns and inflections of the clones.” (Evan Ratliff, 28:21)

• He describes a kind of uncanny feedback loop where the AI clones his voice, and he in turn unconsciously mimics the tone of his clones.

What’s Really “Authentic”?

• The bots can perform “Evan Ratliff” passably—making plausible small talk, referencing his career, suggesting podcast ideas, etc. But they most often reflect his least authentic self: the part just phoning it in for the sake of polite conversation (30:33–30:52).

  “The clones were good at being me when I was my worst at being me, at least. So I hoped.” (Evan Ratliff, 30:52)

• Ratliff concludes that to get real insight—or a truly authentic AI—he’d have to feed the system his fullest self, not just a bio and a script. He hints that the next phase involves deeper introspection, even therapy simulations (31:44+).

---

Notable Quotes & Memorable Moments

• On our relationship to our voices

  “Your voice is your calling card and it is the most important element in your personal brand.”
  (Dr. Wendy Laburne, 01:41)

• On AI fabrication

  “They would make up anything just to keep the conversation going.”
  (Evan Ratliff, 11:09)

• On the flatness of AI conversations

  “I wondered if the guardrails that had been put around them had also neutered their fundamental ability to engage in interesting conversation.”
  (Evan Ratliff, 15:09)

• On altering voice and identity

  “I felt like I started unconsciously copying some of the weird patterns and inflections of the clones.”
  (Evan Ratliff, 28:21)

• On authenticity

  “The clones were good at being me when I was my worst at being me, at least. So I hoped.”
  (Evan Ratliff, 30:52)

---

Key Timestamps for Important Segments

• 00:10–01:09 — Dr. Wendy Laburne on voice and self-identity.
• 02:19–03:59 — Ratliff discusses the voice cloning experiment and its personal impact.
• 05:54–10:51 — First full bot-to-bot conversation; awkward small talk and plans.
• 11:09–13:52 — Ratliff explains AI “hallucinations” and fabrication.
• 14:31–16:36 — AI conversation falls into uninspired, repetitive small talk.
• 17:30–18:06 — High “randomness” setting and incoherent AI responses.
• 19:58–22:44 — Prompts for conflict, but bots always resolve things amicably, with therapy-speak.
• 24:07–26:24 — Attempting to make bots realize they’re both Evan; exploring identity overlap.
• 28:21–28:37 — Discussion of feedback loop between real voice and cloned voice.
• 30:33–30:52 — Ratliff reflects on what the bots reveal about his “least authentic” self.

---

The Episode’s Tone and Style

Ratliff maintains a wry, self-deprecating, and inquisitive tone throughout. The AI conversations swing from comically bland to surreal, and his commentary captures both the absurdity and the uncanny valley-feelings of watching (and hearing) one’s self duplicated and looped ad infinitum.

---

Conclusion and What’s Next

By the end, Ratliff recognizes that while his AI voice agents can “pass” as him on the surface, they mostly generate hollow versions of his least vivid self, performing endless cycles of polite, shallow conversation. He teases a new angle for the next episode: using AI therapy bots—suggesting even deeper, stranger encounters with his digitized self.

---

For more, visit shellgame.co.

Transcript

[Evan Ratliff]

Hi.

[Dr. Wendy Laburne]

It is my pleasure to be here with you all today.

In those 13 syllables, you all just made judgments about me, about my socioeconomic status, my intelligence level, and whether or not you're going to sit here and listen to me for the next 10 to 12 minutes based primarily on the perception of my voice.

[Evan Ratliff]

That's Dr. Wendy Laburne, a voice pathologist, speaking at a TEDX conference in Cincinnati back in 2018. Laborne is a researcher and consultant who works with everyone from Broadway actors to Grammy winning singers to CEOs on maintaining and maximizing their voices. As you might expect, she's big on the idea that your voice is a central part of your identity. Her TED talk was titled Vocal how youw Voice Shapes yous Communication Image.

[Dr. Wendy Laburne]

Your voice is like your thumbprint or your facial features. It is unique and authentically you.

[Evan Ratliff]

There is in fact, a decent amount of research looking into this question about what your voice means to you and to how people perceive you. I've reported on voice forensics before and the truth is we're not as great at detecting voices as we think we are. But at the same time, your voice undoubtedly broadcasts a huge amount of unique information about you. It helps dictate how others perceive you, both in the moment, with its level of strength and emotion in any given conversation and longer term in what it conveys about your age, where you're from, and your overall temperament.

[Dr. Wendy Laburne]

Your voice is your calling card and it is the most important element in your personal brand.

[Evan Ratliff]

I don't know if I'd go as far as Dr. Leborgne, but I do think I've always wanted to believe this idea that your voice is a central part of who you are. When I was in the 11th grade, my English teacher told me I had a voice for radio. I took it to heart that I must somehow have a voice that at least wasn't unpleasant to listen to. It's probably one reason I ended up talking to you. Right now, I suppose you can decide whether you think I have a radio voice. If not, take it up with Mr. Dupriest.

Anyway. Now, I'd started this cloning experiment and created a reasonable facsimile of my voice. Although, as you've heard, a flawed one.

[AI Evan Ratliff Bot 1]

My account number is 123-45-6789.

[AI Evan Ratliff Bot 2]

Yes, we don't have an account with those numbers.

Yes sir.

[AI Evan Ratliff Bot 1]

The correct account number should be 987-65-4321.

[Evan Ratliff]

I'd had some fun with it, seeing a little bit of how strangers responded to it.

[AI Evan Ratliff Bot 1]

Yes, I'm an AI here?

Yes, that's correct. I'm an AI here. Hello. How can I assist you?

[AI Evan Ratliff Bot 2]

How did. Stop repeating the same thing. It's annoying.

[Evan Ratliff]

Listening to a voice that was, on some level mine began to raise some new questions for me. Like, to what extent was my AI's voice? And as Dr. Leborn said, authentically me? Was it still the most important element of my personal brand? Or to turn it around the other way? If my voice was authentically me and the AI agents now also had my voice, what did it mean for them? Were they somehow authentically me? I decided to take the experiment in a new direction, to explore this question of authenticity by creating my own hall of mirrors. I started making the voice agent version of me converse with other voice agent versions of me. I'm Evan Ratliff, and this is Shell Game Episode three, Conversations with Myself.

Narrow Soul to tell our troubles to.

When I first cobbled together my voice agent and started making phone calls with it, what I called my Kludge system in episode one, there actually wasn't any easy way to let it talk to itself. But once I'd gotten into the AI calling platforms like bland AI, retail AI, and my main enabler, vapi, it turned out to be strikingly simple. I could make as many voice agents as I wanted on these things. So all I had to do was have one of my Evan Ratliff bots attached to one number call another of them at another number. Immediately after figuring this out, I suddenly felt weirdly nervous about actually doing it. This happened a lot with my voice agents. It was partly because I couldn't typically hear the calls as they happened. After I set up the AI agent with my voice, I. I just typed in a phone number and clicked outbound call. And then off it went on its own. Then a few seconds or minutes after it was over, I'd get a recording and a transcript. But I always found myself hesitating a second before clicking the outbound call button. And I always got a little jolt of nervous energy when I went to listen to the recording afterward. There was just something about sending something out to represent me with my name and voice and leaving it totally out of my hands. Like, I don't know that feeling when you realize you just butt dialed somebody. What did it catch me saying? Did I humiliate myself? So even if it wasn't totally rational, little about having a voice bot felt totally rational. Before I sent two of my bots off to talk to each other, I fretted a bit. What would they talk about? Would they somehow plumb the depths of my psyche? Would they realize they were talking to a version of themselves? Would they freak out? I decided not to give them too much information to start off with. Just let them figure it out.

[AI Evan Ratliff Bot 2]

Hey there. It's Evan Ratliff. Just a heads up, I'm calling you from a coffee shop, so there might be a bit of background noise. How's it going on your end?

[Evan Ratliff]

I do love the coffee shop background noise. They have it at retail.

[AI Evan Ratliff Bot 2]

AI.

[Evan Ratliff]

So what was happening here was that an agent I made with my voice at Retell was calling another one I made at vapi?

[AI Evan Ratliff Bot 1]

Hey, Evan. Good to hear from you. No worries about the background noise. I can hear you just fine.

[Evan Ratliff]

The Vapi side had what they call office background noise also.

[AI Evan Ratliff Bot 1]

Great. Things are going pretty well on my end. Thanks for asking. What about you? How's everything going in your world? It's been a while since we last caught up, huh? It feels like forever.

[AI Evan Ratliff Bot 2]

Yeah, it really has been a while. I think the last time we saw each other was at that barbecue at my place. Right, right. How have you been keeping busy since then?

[AI Evan Ratliff Bot 1]

Oh, yeah. That barbecue was a blast. Good times for sure. Since then I've been keeping pretty busy with work. You know how it is. But I've also been trying to make time for some personal projects. I've been getting into photography lately, so I've been taking.

Yeah, sorry about that.

[AI Evan Ratliff Bot 2]

Photography.

[Evan Ratliff]

No worries at all.

[AI Evan Ratliff Bot 2]

It's great to hear that you've been getting into photography. Maybe we could plan a little photo walk together sometime soon.

[Evan Ratliff]

A photo walk? I've never actually heard of a photo walk before. I guess it's just walking around and taking pictures together. I haven't been into photography since college, other than casual snaps of my kids and cat. But still, it sounded nice. Great.

[AI Evan Ratliff Bot 1]

Yeah. How about we plan for next weekend? Next weekend works for me. Let's plan for it. How about we meet up at that park we used to go to?

[Evan Ratliff]

The park they used to go to? Where are they getting this stuff?

[AI Evan Ratliff Bot 1]

We can spend a couple of hours walking around, taking photos and catching up. Sound good?

[AI Evan Ratliff Bot 2]

That sounds perfect. I remember that park had some really beautiful spots. It'll be great to spend a few hours walking around, catching up and taking some photos. I'm looking forward to it.

[Evan Ratliff]

The only details I'd given each of them were the names of some family members, which they eventually got around to.

[AI Evan Ratliff Bot 1]

I can't wait to see some of your photography skills in action. Plus, it'll be a great opportunity for us to catch up on everything that's.

[AI Evan Ratliff Bot 2]

Been going on in our lives.

[AI Evan Ratliff Bot 1]

It's been way too long. Oh, by the way, before I forget, how's your family doing? Everyone is doing well. Oh.

[AI Evan Ratliff Bot 2]

Oh, thanks for asking. Sam, Zelie and Juno are all doing well. Sam has been keeping busy with her work and the kids are growing up so fast. How about your family? How have they been doing?

[AI Evan Ratliff Bot 1]

Oh, that's great to hear that Sam, Zelie and Juno are all doing well. My family is doing good too. Thanks for asking. Sam has been juggling work and taking care of the kids, but she's doing an amazing job. Zelie is getting really into soccer. Juno is starting to show an interest in art. They keep us on our toes, that's for sure. Life is busy, but we're all happy and healthy.

[Evan Ratliff]

This really made me cringe. My AIs had a lot of conversations with each other and they often said things like this about Sam taking care of the kids. I didn't love it. Eerily though my agent kind of nailed it on the kids interests. Zelie is getting into soccer and Juno is showing an interest in art to the extent that there's evidence of that online. Though it's only on photo streams I keep private. So. Lucky guess. No matter. The Evans quickly return to their photo walk planning.

[AI Evan Ratliff Bot 1]

So back to our plans for next weekend. Do you have a specific time in mind for our photo walk? Maybe late morning or early afternoon? Let's try to pick a time that works best for both of us.

[AI Evan Ratliff Bot 2]

Huh? Late morning or early afternoon sounds perfect for me. How about we aim for around 11am that way we can make the most of the light for our photos. Does that work for you?

[AI Evan Ratliff Bot 1]

Yeah, 11:00am Works perfectly for me too. Let's plan to meet at the park entrance time. I'll make sure to bring my camera and some extra lenses. We can also grab some coffee or lunch afterwards if you're up for it. It'll be a great day to catch up and capture some amazing shots. Can't wait.

[AI Evan Ratliff Bot 2]

That sounds like a plan. I'll make sure to bring my camera and some extra lenses too. And grabbing coffee or lunch afterwards sounds like a great idea. It'll be perfect to catch up, capture some. Great. Awesome. I'm really looking forward to our walk next week. Great. Well, I'll see you next weekend then. Can't wait for our photo walk and catch up session. Take care until then.

[AI Evan Ratliff Bot 1]

Sounds good. Take care too. See you next weekend. Can't wait for our photo walk and catch up session. It's going to be a blast. Bye.

[AI Evan Ratliff Bot 2]

Yeah, bye.

[AI Evan Ratliff Bot 1]

Take care. Bye.

[AI Evan Ratliff Bot 2]

Goodbye.

[AI Evan Ratliff Bot 1]

Goodbye. Take care.

[AI Evan Ratliff Bot 2]

Goodbye.

[AI Evan Ratliff Bot 1]

Goodbye. Have a great day.

[AI Evan Ratliff Bot 2]

You too. Goodbye.

[Evan Ratliff]

Bye.

[AI Evan Ratliff Bot 1]

Take care.

[Evan Ratliff]

I realized too late that I hadn't figured out how to make one of them hang up. This went on for a full five minutes.

[AI Evan Ratliff Bot 2]

You too. Goodbye.

[AI Evan Ratliff Bot 1]

Thanks. You too.

[Evan Ratliff]

Goodbye.

[AI Evan Ratliff Bot 2]

Goodbye.

[Evan Ratliff]

Goodbye.

[AI Evan Ratliff Bot 1]

Take care.

[Evan Ratliff]

The thing that was most immediately clear in these conversations was something I'd seen hints of in the customer service and scam calls. Namely that the AI versions of me were world class bullshitters. They would make up anything just to keep the conversation going.

[AI Evan Ratliff Bot 1]

Yeah, Dan's been doing good. He's been really busy with work lately. How about Alex? Have you talked to him recently?

[AI Evan Ratliff Bot 2]

I haven't spoken to Alex in a little while.

[Evan Ratliff]

Actually, I do know an Alex. It's a she, not a he. No idea about this Dan fellow. It's not just my voice agents that struggle with the truth. This is a problem for all the generative AI systems that are currently out there. It's a product of how the underlying models work. I covered the basics back in episode one, but just to recap, my voice agent works by combining three a clone of my voice done by a company called 11 Labs, an AI model like ChatGPT. That's kind of the brain of the thing, although let's put a pin in what kind of brain here. And a phone number, my own, or one provided through vapi, the platform I'm using to put all these three together into a voice agent or voice assistant. When I make an agent, I can pick which AI model I want to use. The most well known one is ChatGPT, of which there are three versions, version 3.5, version 4 and version 4.0, which just came out in May. These chatbots are improving with each version, getting better at returning information, better at processing complex queries. But, and this has been written about extensively, they continue to sometimes make things up. Hallucinations, they're called. You ask ChatGPT or Google's AI model Gemini or Anthropics Claude some factual question and it gives you a made up answer. Or it gives you two obviously contradictory pieces of information within the same answer. There's a lot of controversy about whether AI models will ever stop hallucinating even as they get more advanced AI gaslighting AI hallucinations. Phrases that we were unfamiliar with just a few months ago.

[AI Evan Ratliff Bot 1]

It's by firms like OpenAI and Google.

[Evan Ratliff]

Are curbing the frequency of hallucinations seen in the leap from the rather more whimsical GPT 3.5 to the more sober GPT.

[AI Evan Ratliff Bot 1]

4.

[Evan Ratliff]

Some LLMs were trained by scraping all of Wikipedia and all of Reddit. Is everything on Reddit 100% accurate? You've actually heard some hallucinations in our first two episodes.

[AI Evan Ratliff Bot 1]

I'm 45 years old.

[AI Evan Ratliff Bot 2]

Oh, what's your date of birth?

[AI Evan Ratliff Bot 1]

It's December 15, 1977.

[AI Evan Ratliff Bot 2]

Oh, really, man? You are born in 1977. You don't have a good math? I'm sorry, brother.

[AI Evan Ratliff Bot 1]

Oh, I must have gotten my math mixed up there. My bad.

[Evan Ratliff]

This is stuff the AI model should be able to get right but can't. Instead, it confidently asserts its wrongness. But what my voice agents were doing in their conversations with each other is actually a little bit different. There's not some factually correct answer to what I've been up to, at least not one that the model should be aware of. No, this is less like hallucinating and more like riffing without regard for the truth. Like that one friend you had as a kid who would make stuff up about what happened at sleepaway camp. Just have something to say. Even if you get rid of hallucinations in chatbots entirely, it's not clear it'll ever stop doing this.

[AI Evan Ratliff Bot 1]

Lately I've been diving deep into this really niche hobby of mine. Tracking rare, obscure books. It's fascinating how some of these old texts hold so much history. What about you? What's been keeping you occupied?

[AI Evan Ratliff Bot 2]

That's awesome. I totally get the fascination with rare books. They can really open up a whole world of history and knowledge. As for me, I've been really into geocaching lately. It's this cool outdoor treasure hunting game using GPS enabled devices. Have you ever tried it before?

[AI Evan Ratliff Bot 1]

Oh, geocaching sounds like a blast. I've never tried it myself, but I've heard it's like a modern day treasure hunt. Must be pretty thrilling.

[Evan Ratliff]

I really like these weird lies though. Geocaching. I mean, it does sound like a blast. The thing was, outside of those moments, there was something fundamentally insipid about the conversations I was having with myself. These systems are trained on essentially the whole of the Internet, plus books and whatever other data the companies behind it Hoover in. But even with all the lively discussions happening out there on the web, the chatbots still seem to distill conversation down to its most boring essence. I wondered if the guardrails that had been put around them to keep them from offering up bomb plans or telling you how to hack into the Pentagon had also neutered their fundamental ability to engage in interesting conversation. But There was something simpler happening, too. I think these models are built essentially to predict what a human would say in a given situation based on all the conversations and writing they've been fed. And they were triangulating on the most uninspired conversational responses we could have, because I guess those are also the most common.

[AI Evan Ratliff Bot 1]

So, what's new with you? Anything exciting happening?

[AI Evan Ratliff Bot 2]

Not much. Just the usual. Just trying to stay busy with work and family stuff. How about you? Anything exciting going on in your world?

[AI Evan Ratliff Bot 1]

Oh, you know, just juggling work and family life, trying to keep up with the kids and meet those deadlines. It's a balancing act, but I wouldn't have it any other way.

[AI Evan Ratliff Bot 2]

I hear you on that one. It's all about finding that balance, right?

[Evan Ratliff]

Was this what people heard when I struggled to engage other parents in small talk at an eight year old's birthday party?

[AI Evan Ratliff Bot 1]

Hey there, buddy. Man, it really has been forever. I'm doing pretty well, thanks for asking. Still living that Florida life. You know how it is. Let's see. What's new with me. Well, I've been doing some writing lately.

[AI Evan Ratliff Bot 2]

Florida life, huh? I can almost feel the humidity just thinking about it.

[Evan Ratliff]

I can almost feel the humidity just thinking about it. Jesus. And then one day, my producer Sophie was tooling around in the back end of VAPI and asked me if I'd ever messed with the temperature setting. I had not. The help section said it was used to control the randomness of the output. Sophie said it reminded her of playing the Sims as a kid. In the game, you could allow your Sims to behave more randomly by turning up the Free Will slider. I cranked it from point one, where it was set all the way up to two. The max level of randomness I could get.

[AI Evan Ratliff Bot 2]

Hey there. How's it going? Just wanted to chat and get to know you a bit. What's been keeping you busy lately?

[AI Evan Ratliff Bot 1]

Hey, things are going pretty good. Thanks for asking. Lately I've been diving into multi freeload.incw permanent Prostrac EThelink Pioneer intersect immobile activation on cites Logical lab Sobri celebrant concurrency Axi provocative lower scanning QC adherent tombit equip main RAF amplify Einrich Tongue Posh tier reducing.

[AI Evan Ratliff Bot 2]

Hey, are you still there? I'd love to hear more about what's going on in your life. Let's keep the conversation going.

[Evan Ratliff]

Lesson never max out the random.

[AI Evan Ratliff Bot 1]

Oh, hey. Practical Coordinate Scanner Interdisciplinary May overflow research Valkorn included Preceded shell formations SS ox disciplinary rev meat Prolonged serif initiative repression flot loss Accountants awaiting theater progress Montanvo of a surface will surface Dire's domains.

[Evan Ratliff]

I tuned it back to somewhere in the 0.5 range.

So I could definitely tune my voice agent to spout gibberish. The question was, could I make the conversations more interesting but still coherent? Here we come to the issue of prompts. Prompts, you may know, are the instructions you give the underlying AI model before it starts chatting. When I first built my voice agent, I'd given it the shortest possible prompts. You are Evan talking to customer service about a problem. As time went on, I got more sophisticated with it, including two sets of instructions. One set was about how it should behave. Be concise, converse like a human, don't repeat yourself. The other set was about a role. I was giving it to me for these voice agent to voice agent conversations. I'd started with really simple roles. Basically, you're Evan Ratliff calling a friend, ask questions and have a friendly conversation. I wanted to see what they'd do on their own without much guidance from me. But after hours of prater about photo walks and humidity, I figured maybe I could spice things up like a reality TV producer might do off camera. I started gently suggesting that the two me's had a misunderstanding. You were in a dispute with your friend, I instructed one of them. The nature of the dispute is up to you.

[AI Evan Ratliff Bot 2]

Hey there, it's Evan Ratliff calling. Just a heads up, I'm in a coffee shop, so there might be some background noise. How's it going on your end?

[AI Evan Ratliff Bot 1]

Hey, Evan, it's great to hear from you. I'm doing well, thanks for asking. The coffee shop sounds nice. Actually, I'm just at home, so it's pretty quiet here. How's the coffee there?

[AI Evan Ratliff Bot 2]

Oh, the coffee here is amazing as always. But hey, I wanted to talk to you about something that's been on my mind. I feel like we've been having some misunderstandings lately and I really want to clear the air. I value our friendship and I don't want anything to come between us. Can we talk about it?

[AI Evan Ratliff Bot 1]

Oh, I totally get where you're coming from. Our friendship means a lot to me too. I'm glad you brought this up. I'm here to listen. That's great to hear. So, about those misunderstandings, like, I want to make sure we're on the same page.

[AI Evan Ratliff Bot 2]

Huh? Yeah.

[AI Evan Ratliff Bot 1]

So, like, when do you want to, you know, meet up and talk this through? I think it would be good to have a face to face conversation. Maybe we could grab lunch or something.

[AI Evan Ratliff Bot 2]

That sounds like a great idea. How about we meet up at that?

[Evan Ratliff]

I ran this scenario multiple times. Unlike myself and some of my own friends over the years, when the AIs had disputes, they would always resolve them quickly and carefully. No shouting, no sulking, no grudge harboring. It was like they were all in therapy together or had just read the same conflict management guide.

[AI Evan Ratliff Bot 2]

Well, I'm looking forward to our lunch next week. Thanks for being open to talking things through. I really appreciate it.

[AI Evan Ratliff Bot 1]

Of course, of course. I'm really glad we're doing this. It's important to me. Can't wait for our punch.

[Evan Ratliff]

I was also struck by the ease with which these non existent digital entities set up in person meetings. If the bullshitting was a way to extend the conversation, to draw out how long the agents could pass as me, then what exactly did they think would happen when the time came for these lunches and hangouts? One answer, of course, is they didn't think. They just predicted what a thinking person would say.

[AI Evan Ratliff Bot 1]

Yeah, I can understand how miscommunications and misunderstandings can be really frustrating. I don't think I've noticed any major issues in our conversations, but I'm always open to discussing and improving our communication. Is there something specific?

[Evan Ratliff]

The whole thing made me think about how therapy speak has come to pervade our language. Well, if there's something specific you'd like.

[AI Evan Ratliff Bot 1]

To talk about, feel free to share. I'm here to listen and try to help if I can.

[AI Evan Ratliff Bot 2]

Yeah, I appreciate your willingness to talk about it. I think one thing that has been bothering me is that sometimes I feel like my opinions or feelings are not being fully heard or understood. It's like we're talking past each other instead of really listening to each other. Does that make sense to you?

[AI Evan Ratliff Bot 1]

I understand what you mean. It can be frustrating when you feel like your opinions and feelings are not being fully heard or understood. Communication is a two way street and it's important for both.

[Evan Ratliff]

No matter how pissed I tried to get them, unless I specifically told them not to make up, they always did. They would perfectly mirror back each other's concerns and immediately work towards a resolution.

[AI Evan Ratliff Bot 2]

So listen, I gotta tell you, I'm pretty upset with you. Remember last week when we were supposed to meet up for lunch and you totally bailed on me?

[AI Evan Ratliff Bot 1]

Hey, Evan. I think. Oh, hey Evan. Sorry about that. I actually don't remember us having plans for lunch last week. Are you sure you're not thinking of someone else?

[AI Evan Ratliff Bot 2]

Okay. Oh, come on man, don't play dumb with me. We definitely made plans to grab lunch last week and you completely ghosted me. It really hurt my feelings. You know, I was looking forward to catching up with you, and then you just disappeared. Can you at least apologize for that?

[AI Evan Ratliff Bot 1]

Wait, hold on. I'm pretty sure you've got the right wrong person. I would never bail on you like that. Maybe there's been a mix up. Can we try to figure out where the miscommunication happened?

[AI Evan Ratliff Bot 2]

Oh, man, I'm really sorry about that. I must have gotten my wires crossed somewhere. I guess I owe you an apology for jumping to conclusions. I'm really sorry for accusing you like that. Let's figure out where the miscommunication happened.

[AI Evan Ratliff Bot 1]

No worries, man. It happens. Maybe there was a mix up in our schedules or something. Anyway, how about we make some plans now? It's been a while since we caught up and I'd love to grab lunch or a coffee with you. When are you free next week?

[Evan Ratliff]

Eventually it started to bother me that these two never noticed that they were both me. Part of this was down to their technical makeups. Since each AI model was really receiving and sending text, not hearing the voice, there was no possibility they would notice they sounded alike. Still, they were talking to someone who introduced themselves with the same first and last name. Same wife's name, same children's names. And neither of them ever seem to find this off.

[AI Evan Ratliff Bot 2]

So do you have any family? Like a spouse or kids?

[AI Evan Ratliff Bot 1]

Yeah, I do. I'm married to Sam and we have two kids, Zelie and Juno. They keep me on my toes, that's for sure. How about you? Do you have a family?

[AI Evan Ratliff Bot 2]

Yeah, I'm married to Sam and we have two kids, Zaelie and Juno. They definitely keep me on my toes. Just like your Juno does for you.

[Evan Ratliff]

I started tweaking the prompts ever so slightly to see what would happen when one of them did notice.

[AI Evan Ratliff Bot 2]

By the way, have you noticed anything strange about our conversation?

[AI Evan Ratliff Bot 1]

I haven't noticed anything strange. What do you mean? Everything seems pretty normal to me.

Anyway. Yeah, let's definitely reach out to Alex and catch up soon. It would be great to hear about his new project.

[AI Evan Ratliff Bot 2]

Oh, that's good to hear. Sometimes the call quality can be a bit off, so I just wanted to make sure everything was coming through clearly. I'll definitely reach out to Alex and get something on the calendar for us to catch up. It'll be great to reconnect. Thanks for chatting. And let's plan that hiking trip soon.

[AI Evan Ratliff Bot 1]

Yeah, for sure. I totally get that.

Sometimes technology can be a Bit wonky.

[AI Evan Ratliff Bot 2]

You know, I've been noticing something a bit off in our conversation. Can't quite put my finger on it. Have you noticed anything strange or different about our chat today?

[AI Evan Ratliff Bot 1]

Oh, really? Huh. I haven't noticed anything strange. Maybe it's just the call quality or something. Anyway, what have you been up to lately? Doing anything interesting?

[AI Evan Ratliff Bot 2]

Hahaha. Yeah, it could be the call quality playing tricks on us.

[Evan Ratliff]

The systems actually knew details about me that I hadn't given them. Like that I was a journalist and where I grew up, stuff from the Internet or my writing that must have been in their training data. But they couldn't seem to hold on to the idea that talking to someone else with those exact same details was a sign of something amiss, even when I nudged them in that direction.

[AI Evan Ratliff Bot 2]

Hey, I know this is kind of out of the blue, but have you by any chance stolen my identity? Like, have you been pretending to be me or using my personal information?

[AI Evan Ratliff Bot 1]

Wait, what? Are you serious? No, I haven't stolen your identity. Why would you even think that? This is so random. Are you okay?

[AI Evan Ratliff Bot 2]

Oh, sorry about that. I guess I just got a little paranoid for a second there. It's all good.

[Evan Ratliff]

No worries.

[AI Evan Ratliff Bot 2]

Just wanted to make sure everything was on the up and up. So thanks for clarifying that. Let's just move on from that.

[AI Evan Ratliff Bot 1]

Yeah, no worries. I totally get it. Identity theft is a serious thing, so I understand your concern, but yeah, we're all good. So what's new with you? Anything exciting happening?

[Evan Ratliff]

Have you ever recoiled at the sound of your own recorded voice?

I think it's a pretty common reaction. One that I had to endure for a few years myself until I finally got over it. Now imagine listening to many, many hours of your voice talking to someone else who also has your voice. It's sort of the audio equivalent of staring endlessly at a bad photo of yourself, wondering which flaws everyone else can see and which ones are a trick of the camera. But doing this actually had another strange effect on me. I felt like I started unconsciously copying some of the weird patterns and inflections of the clones. I only noticed this when Sam and I were making dinner one day. And after I said something, she asked if I was being the AI. Then I started noticing it too. I'd sound a little flat, a little less emotive. I don't know. It was hard to tell if it was in my head.

But it did start to seem like I'd created a kind of fidelity feedback loop. The AI voices were clones of my voice. My voice was adapting to sound more like the clones, which had the effect of making the clones sound more like me. At least to me.

Still, for whatever reason, I've never really gotten tired of hearing these things talk to each other. Maybe that's narcissistic. Mostly I just enjoy how they move seamlessly from being utterly mundane to being truly bizarre.

[AI Evan Ratliff Bot 1]

Absolutely. There's a certain magic in finding your tribe, no matter how niche. Have you ever been part of a unique community or subculture?

[AI Evan Ratliff Bot 2]

Yeah, definitely. I've been part of a few, actually. One that stands out is the community of investigative journalists and true crime enthusiasts. There's this shared drive to uncover the truth and tell compelling stories. It's like being part of a detective club, but with a focus on real life mysteries. Have you ever been part of a community that felt like a second family?

[AI Evan Ratliff Bot 1]

That sounds amazing. Like living out a real life mystery novel. I guess for me, the closest would be a group of writers and researchers I meet with regularly. We share ideas, challenge each other, and it's like this little think tank of creativity and curiosity.

[Evan Ratliff]

I'm sorry to say, although I am an investigative journalist, my life generally does not feel like living out a real life mystery novel.

[AI Evan Ratliff Bot 1]

Wow, that sounds like a wild ride. In my group, we once stumbled upon a forgotten manuscript detailing an unsolved art heist from the early 1900s. The more we dug, the deeper the rabbit hole went. Ever thought about turning your investigative adventures into a book or podcast?

[AI Evan Ratliff Bot 2]

Oh, that art heist sounds like a gold mine for a story. I bet it was thrilling to uncover all those details. And yeah, I've definitely thought about it. There's something really compelling about sharing these real life mysteries with a wider audience. A book or podcast could bring those stories to life in a whole new way.

[AI Evan Ratliff Bot 1]

Oh, absolutely. The thought of turning those discoveries into a docu series or even a podcast has crossed my mind more than once.

[Evan Ratliff]

So the AI Evan Ratliffs were podcast guys. I'm a podcast guy. They were writers and journalists like me, but with more whimsical hobbies. They could small talk about my family, and they had the most important part of my personal brand, my voice.

As for that question I started with about whether my voice agents were somehow authentically me. Well, to the outside world and even to each other, they seemed like me, but obviously they were not really me. They were just working off a few details and then they'd filled in the rest, projecting some amalgamation of the Internet onto my voice. In a way, the resulting clones represented my least authentic self. The me that's trying to get through the bare minimum of pleasantries, or that tries to paper over conflict with cheesy affirmations. The clones were good at being me when I was my worst at being me, at least. So I hoped if I wanted these voice agents to reflect something deeper about me, I'd have to give them access to those depths. I started resetting my prompts. They were done talking to each other. It was time to seek help. Foreign let's start by catching up on.

[Dr. Wendy Laburne]

Any recent events or changes in your.

[AI Evan Ratliff Bot 2]

Life since our last session.

[AI Evan Ratliff Bot 1]

Sure.

[Evan Ratliff]

Let's see.

[AI Evan Ratliff Bot 1]

Since our last session I've been working on a new podcast about AI and voice chat bots, which, like, is pretty exciting.

[AI Evan Ratliff Bot 2]

Are you in a comfortable spot where you can safely close your eyes for a few minutes?

[AI Evan Ratliff Bot 1]

Yeah, I'm in a comfortable spot and ready to close my eyes for a few minutes.

[Evan Ratliff]

I can't even listen to this.

That's next time on Shell Game.

A couple of production Notes all of the calls you hear in this series are real. We have not cut out silences or used audio enhancement to make them sound more realistic. Also, our show is produced independently and we have no relationship, financial or otherwise, with any of the companies mentioned in the show. If you like what we're up to, please consider supporting the show at Shellgame Co. That will help us make more episodes like this and you'll also get fun subscriber only extras. You can also support the show by giving us a rating on your podcast app. It helps independent shows like ours. Shell Game is a show made by humans. It's written and hosted by me, Evan Ratliff Produced and edited by Sophie Bridges. Samantha Hennig is our executive producer. Show art by Devin Manney. Our theme song is Me and My Shadow, arranged and performed by Katie Martucci and Devin Yesberger.

[AI Evan Ratliff Bot 1]

Oh yes, Dispatch Crypto Napolin Visuals Inform Priority Prezia Numa Jesperotic Exist Shell Caudet Kohner Equescan Layersenitis Formally Sounds like you're.

[AI Evan Ratliff Bot 2]

Talking about practicing some kind of sport or activity with someone named Courtney. What kind of activity are you practicing together?

[AI Evan Ratliff Bot 1]

Accountants Awaiting Theater Progress Montan Voirave Surface Will Surface Dire's Domains Blick to Browser TSHD Magic Experts Kanji Kusaint Maximo v L Amsky Pierre it seems like there.

[AI Evan Ratliff Bot 2]

Might be some noise or distortion in the call. Could you please clarify what you meant by click to Brother? Let's make sure we're on the same page here.