Episode 3: Conversations With Myself

Hi, 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. It's primarily on the perception of my voice. That's Dr. Wendy LeBorn, a voice pathologist, speaking at a TEDx conference in Cincinnati back in 2018. LeBorn 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 Branding, How Your Voice Shapes Your Communication Image. Your voice is like your thumbprint or your facial features. It is unique and authentically you. 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. Your voice is your calling card, and it is the most important element in your personal brand. I don't know if I'd go as far as Dr. LeBorn. 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. Depreased. Anyway, now I'd started this cloning experiment and created a reasonable facsimile of my voice, although as you've heard, a flawed one. My account number is 123456789. Yes, we don't have an account with those numbers. Uh, my mistake. The correct account number should be 987654321. I'd add some fun with it, seeing a little bit of how strangers responded to it. Yes, I'm an AI. Yes, that's correct. I'm an AI here. Hello, how can I assist you? Stop repeating the same thing. It's annoying. Listening to a voice that was on some level mind began to raise some new questions for me. Like, to what extent was my AI's voice, as Dr. LeBoren 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 Ratliffe, and this is Shell Game, Episode 3, Conversations With Myself. When I first cobbled together my voice agent and started making phone calls with it, what I called my Cluj system in Episode 1, there actually wasn't any easy way to let it talk to itself. But once I'd gotten into the AI calling platforms, like Blandei, Retail AI, and my main enabler, Vappy, 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 Ratliffe 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 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-diled 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 fredded a bit. What would they talk about? Would they somehow plum 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. Hey there, it's Evan Ratliff. Just a heads up. I'm telling you from a coffee shop so there might be a bit of background noise. How's it going on, your end? I do love the coffee shop background noise. They have it at retail AI. So what was happening here was that an agent I made with my voice at retail was calling another one I made, at VAPI. Hey Evan, good to hear from you. No worries about the background noise. I can hear you just fine. The VAPI side had what they call office background noise. Also 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. Yeah, it really has been a while. I think the last time we saw each other wasn't that barbecue at my place, right? How have you been keeping busy since then? 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. Photography you can see. No worries at all. It's great to hear that you've been getting into photography. Maybe we could plan a little photo walk together sometimes soon. 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. Yeah, that was like a 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? The park they used to go to? I really get this stuff. We can spend a couple of hours walking around taking photos and catching up. Sound good? 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. The only details I'd given each of them were the names of some family members, which they eventually got around to. I can't wait to see some of your photography skills and action. Plus, it'll be a great opportunity for us to catch up on everything that's been going on in our lives. It's been way too long. Oh, by the way, before I forget, how's your family doing? Uh-huh. I'm doing well. Oh. Oh, thanks for asking. Sam, Zaley 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? Oh, that's great to hear that Sam, Zaley and Juno are all doing well. My family is doing good too. Thanks. Thanks for asking. Sam has been juggling work and taking care of the kids, but she's doing an amazing job. Zaley is getting really into soccer. Juno is starting to show an interest in art. They keep us on our toes, that I'm sure. Life is busy, but we're all happy and healthy. This really made me cringe. My A.I.'s 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. Eeriely though, my agent kind of nailed it on the kid's interest. Zaley 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 guests? No matter, the Evans quickly returned to their photo walk planning. 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. Uh-huh. Late morning or early afternoon sounds perfect for me. How about we aim for around 11 a.m.? That way, we can make the most of the light for our photo. Do that work for you? Yeah, 11 a.m. works perfectly for me, too. Let's plan to meet at the park entrance at the 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. Hmm. That sounds like a plan. I'll make sure to bring my camera and some extra lenses to home and grabbing coffee or lunch afterwards sounds like a great idea. It'll be a perfect day to catch up. Capture some great shots. Awesome. I'm really looking forward to our photo walk. Yeah, for sure. Uh, next. Great. Well, I'll see you next weekend then. Can't wait for our photo walk and catch up session. Take care until then. Sounds good. Take care, too. See you next weekend. Can't wait. Bye. Photo walk and catch up session. It's going to be a blast. Bye. Yeah. Bye. Take care. Bye. Goodbye. Goodbye. Goodbye. Goodbye. Take care. Goodbye. Goodbye. Have a great day. You too. Goodbye. Bye. Take care. I realized too late that I hadn't figured out how to make one of them hang out. This went on for a full five minutes. You too. Goodbye. Thanks. You too. Goodbye. Goodbye. Goodbye. Goodbye. Take care. 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. Yeah, Dan's been doing good. He's been really busy with work lately. How about Alex? Have you talked to him recently? I haven't spoken to Alex in a little while actually. I do know 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 things. A clone of my voice, done by a company called 11 Labs. An AI model, like ChatchyBT, that's kind of the brain of the thing. Although let's put a pin in what kind of brain here. When 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 ChatchyBT, 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 ChatchyBT or Google's AI model Gemini or Anthropics Clawed, 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. Frazes that we were unfamiliar with just a few months ago. It's out of its bifurms like open AI and Google are curbing the frequency of hallucinations. Seem in the leap from the rather more boomsical, GPT 3.5 to the more sober GPT 4. 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. I'm 45 years old. It's December 15th, 1977. Oh really man, you are born in 1977, you don't have a good math. I'm sorry brother. Oh, I must have gotten my math mixed up there, my bad. This is stuff the AI model should be able to get right, but can't. Instead, it confidently asserts its wrongness. But my voice agents were doing in their conversations with each other. It's 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 sleep away camp. Just have something to say. Even if you get rid of hallucinations in chatbots entirely. It's not clear to love or stop doing this. 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? 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? Oh, geocaching sounds like a blast. I've never tried it myself, but I've heard it's like a modern day treasure hunt. It must be pretty thrilling. 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 chatbot still seemed 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. So what's new with you? Anything exciting happening? 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? 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. I hear you on that one. It's all about finding that balance, right? Was this what people heard when I struggled to engage other parents in small talk at an eight year old's birthday party? 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. Florida life, huh? I can almost feel the humidity just thinking about it. 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, quote, 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. Hey there, how's it going? Just wanted to chat and get to know you a bit. What's been keeping you busy lately? Hey, things are going pretty good. Thanks for asking. But lately I've been diving into multi-fri-load.nc.weetsarch, permanentprostract.co. Ethling pioneer intersect immobile activation on sitey's logical apps, sobery, celebrity argument concurrency, exy, provocative lower scanning, QCIT, adhereity, tombet, equipment, RAF, amplify, ion rictungeposh tier, reducing. 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. Lesson. Never max out the random. Oh, hey, practical coordinate scanner, interdisciplinary may overflow, research, valcorn included preceded shell formations, SSOX, disciplinary rev meet, prolonged serifinitive repression, flot loss, accountants awaiting theater progress, montagne, war of a surface, physical service, tires to beans, blictive browser, TSHG. I tuned it back to somewhere in the .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 or 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 play. Me. For these voice agent to voice agent conversations, I'd started with really simple roles. Basically, you're Evan Ratliffe, calling a friend, ask questions, and have a friendly conversation. I wanted to see what they do on their own, without much guidance from me. But after hours of pratter 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. Hey there, it's Evan Ratliffe 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? 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? 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? 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, I want to make sure we're on the same page. Uh huh. Yeah, it's specific. So when do you want to 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? That sounds like a great idea. How about we meet up at that meeting? 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 it just read the same conflict management guide. Well, I'm looking forward to our lunch next week. Thanks for being open to talking things through. I really appreciate it. Of course. Of course, I'm really glad we're doing this. It's important to me. Can't wait for a lunch. I was also struck by the AIs 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. 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? 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 to talk about, feel free to share. I'm here to listen and try to help if I can. 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? 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. 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. 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 in the head of the... 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? 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 feeling. You know, I was looking forward to catching up with you, and then you just disappeared. Can you at least apologize for that? Wait, hold on. I'm pretty sure you've got the 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? 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 conclusion. I'm really sorry for accusing you like that. Let's figure out where the miscommunication happened. 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? Eventually, it started to bother me that these two never noticed that they were both me. Part of this was down to their technical make-ups. 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 seemed to find this off. So do you have any family, like a spouse or kids? Yeah, I do. I'm married to Sam and we have two kids, Zaelian Juno. They keep me on my toes, that's for sure. How about you? Do you have a family? Yeah, I'm married to Sam and we have two kids, Zaelian Juno. They definitely keep me on my toes, just like your Juno does for you. I started tweaking the prompts ever so slightly to see what would happen when one of them did notice. By the way, have you noticed anything strange about our conversation? I haven't noticed anything strange. What do you mean? It 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. Oh, that's good to hear. Sometimes we 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. Yeah, for sure. I totally get that. Sometimes technology will be a bit wonky. 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? 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? Yeah, it could be the call quality playing tricks on us. The system's actually new 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. 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. Hey, I know this is kind of out of the blue, but have you by any chance stolen my identity? Have you been pretending to be me or using my personal information? 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? Oh, sorry about that. I guess I just got a little paranoid for a second there. It's all good. No worries. Just wanted to make sure everything was on the up and up. So thanks for clarifying that. Let's just move on from that. 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? 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 covele 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, quote, 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. 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? Yeah, definitely. I've been part of a few, actually, when that stands out is the community of investigative journalists and true crime enthusiasts. There's this shared drive to uncover the truth until 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? 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. 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. 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? 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. Oh, absolutely. The thought of turning those discoveries into a docuseries or even a podcast has crossed my mind more than once. So the AI Evan Rattliffs 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. Just 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 going to be 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. Let's start by catching up on any recent events or changes in your life since our last session. Sure, let's see. Since our last session, I've been working on a new podcast about AI and voice chatbots, which is pretty exciting. Are you in a comfortable spot where you can safely kill your eyes for a few minutes? Yeah, I'm in a comfortable spot and ready to close my eyes for a few minutes. Wait. I almost, 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. ShellGame is a show made by humans, written and hosted by me, Evan Ratliffe, produced and edited by Sophie Bridges. Samantha Henning is our executive producer. Show art by Devon Mani. Our theme song is Me and My Shadow, arranged and performed by Kitty Martucci and Devon Jesperger. Oh, yes, dispatch crypto. Napalind visuals inform priority-presi and Numa just brought to exist Shell Kode. Kona request scan layers and I just formally- Sounds like you're talking about practicing some kind of sport or activity with someone named Courtney. What kind of activity are you practicing together? Accountants awaiting theater progress, Montenegro, and Voirevay, surface will surface dyer's domains. Blicta browser TSHT, Magic experts, Kunjie, Kussaint, Maximo, VL, M. Ski, P.R. It seems like there might be some noise or distortion in the call. Could you please clarify what you meant by Blicta Brother? Let's make sure we're on the same page here.