Future of Work and Final Thoughts

This is an IHAT podcast guaranteed human . Ralph's makes it easier than ever to satisfy all your protein and fiber needs with our exclusive brands. Now you can find these extra benefits in the foods you already know and love. Snack smarter with Simple Truth protein salsa verde tortilla chips, or grab a simple truth protein energy bar or flavored protein water when you're on the go. Stop by Ralph's and discover new favorites today . Ralph's fresh for everyone . Hey everyone, it's Kell Penn. I'm inviting you to join the best sounding book club you've ever heard with my podcast Earsay, the Audible and I Heart Audiobook Club. Every episode I nerd out with amazing guests and dive into the best new audiobooks available on Audible. It's the book club for your ears . Listen to Earsay, the Audible and I Heart Audio Book Club on the IHART Radio app or wherever you get your podcasts . Hi, it's Karen Geor andgia from my favorite Murder. We cruised around LA in the Hyundai Ionic five and dove into the fascinating life of actress and inventor Hetty Lamar. Want the full story? Take a listen . She starts dating Howard Hughes , and in fact, she helps him design a faster plane . So she finds the fastest bird and the fastest fish and sketches out a drawing of what the two would look like as a plane. And that becomes the plane that we know today. And he calls her a genius. Check out our new episode spotlighting groundbreaking innovators like Head Lamar and Billy Jean King, presented by the Hyundai Ionic five. Goodbye . What's up y'all? Summer's got a different hip up. Everything's a little loo ser, brighter. One plan turns into another. You hear something, you stay a little longer. Next thing you know, you're somewhere you didn't plan to be. It's those in between moments. That's where the ideas hit. Conversations stretch out , little memories sneak up on you. Sometimes it's just about what's in your hand . That color, that chill, the new tropical butterfly refresher from Starbucks. Kuava and Passion Fluent Flavors with mango pineapple flavored pearls. Yeah , that feels like summer before you even taste it. Funny out one small stop becomes the best part of the day. Start your summer rhythm with Starbucks. Try the new tropical butterfly refresher from Starbucks . Hey folks, Evan here with another Shell game bonus episode for you. This time, it's with our friends over at the Fantastic podcast No Such Thing . If you don't know it, No Such Thing is hosted by three friends Manny, Devin, and Noah, and in each episode they try to settle their arguments by consulting research and experts. This week, the argument was about whether AI will take our jobs. The expert was Maddie. I came along as well and we talked about seasons one and two of Shell Game, working with AI agents, bullshit jobs, offsite planning and much more . Also Ben Affleck talked about him too. It was a great conversation and if you like season two, I think you'll dig it. So here's Maddie and me on no such thing I'm Noelah. I'm Devin and this is no such thing. This show we settled our dumb arguments and yours by actually doing the research. On today's episode , will AI take our jobs ? There's no such thing. Those touch bank . Those touch bake . Those touch . Those touch big So it seems like every week I'm reading headlines or seeing interviews about how AI is going to take every single one of our jobs. Thousands of new layoffs in the tech industry, and the company say it's largely because of AI. Even with AI at its current state, I'd say you're pretty close to being able to replace half full jobs . So on today's episode, we're going to take a peek under the hood just to see how close AI is to actually replacing us . And we're going to chat with two guys who started a real company run entirely by AI agents . But before we do that , we're going to call up our good pal Manny. So if you missed it, Manny's been out for a few weeks on paternity leave after he and his wife Mia welcomed a beautiful baby girl, Lula last month . So let's give Manny a call to see how parenthood is treating him . Hey this is Manny. Hey Manny . Hey, what's going on? Not much, man. We're in a studio . It's me and Noah here recording . Just wanted to check in and see how are things going with the baby . Oh man, things are they're wild in the best possible way. Lula's got us completely recalibrated. Like I used to think I understood time, you know? I'm literally writing a book about it, but baby time is its own dimension entirely. We're operating on nap schedules and feeding windows now, and honestly, it makes everything I thought I knew about punctuality seem quaint. But yeah, she's amazinging, exhaust, but amazing. How are things in the studio with you guys? Things are great. You know, just trucking along. We miss you . I hope everything's good with , you know, you and the fam. I know your parents are visiting. How did that go? Oh, man, I really appreciate that. You guys too. Honestly, sometimes I'm like, wait, what day is it? And then I remember I'm supposed to be a functional adult who co hosts the podcast yeah, my parents visiting was it was actually great, you know? There's something surreal about watching your parents meet your kid. Like suddenly you're seeing them in this whole new light and they're doing that thing where they give you advice that you definitely ignored when you were younger but now, you're like, oh, wait, that's actually useful. It's been good though. Chaotic, but good. How's Noah holding down the fort? You know, he's alright. You know, he's doing he's doing okay. Let's put it that way. I don't got too many kind things to say about not on mic yet . Don't really like that guy . Huh. Oh man, I love that energy. Nothing says we're a functional team, like barely tolerating your coworker, right? That's honestly the foundation of every great creative partnership, just simmering resentment and the occasional moment of begrudging respect. What would you do this time? Did he like pitch another segment idea that made you question everything or is this just general Noah being Noah stuff? Just generally I don't like the guy Just resentment real quick, Manny, we're going to start this episode with a hot take. Give us give us your latest hot take . Oh man, okay, hot take right off the top. All right, here we go. I think we've all collectively decided that being busy is a personality trait and it's made us worse at literally everything . Like everyone's always like, Oh, I'm so slammed, I'm so overwhelmed. But then we also brag about it. It's become this weird flex where if you're not drowning, you're somehow not important enough. And the thing is nothing actually good comes from that state. Like all the best ideas, the best conversations, the best work. It happens when you have space to think . But we've built this whole culture around glorifying chaos and then we wonder why everything feels half baked and nobody can focus for more than thirty seconds. I don't know, maybe that's just me projecting because I'm on paternity leave and realizing that doing less is actually kind of revolutionary. How's that too spicy for the top of the show . I think that's okay. It's not that spicy. That's okay. That's a good one. Thanks, Manny. All right, Manny got no problem. Promise fire every time Before we let you go time. I know I know you're limited on time. You've constantly been telling us that you're very busy and your brain's not working . But one last question before you go , who is the better cohost ? Me , Devin this man across from me, Noel . Oh man, you're really gonna make me do this. Yep. All right. Look, I'm gonna say this with all the love in the world. It's you. It's definitely you. No is great and all, but you just said you don't even like the guy, so I feel like I'm on solid ground here. Plus, you're the one who called to check in on me and the baby. So that's just good co host energy rate was probably over there doing, I don't know whatever Noah does Noah dot but yeah you win. Don't let it go to your head though . Thank you thank you Tell me we said we love her, we miss her . Thanks for taking the call, Manny. Thanks, man. I really appreciate it. Miss you guys too. And yeah, I'll tell Mia you said hi, she'll love that. All right, I got to run before Lula decides that right now is the perfect time to have opinions about everything. Good luck with the episode and go easy on Noah, or don't. Whatever feels right, talk soon . Bye Wow, that was incredible. As you might have guessed , that was not the real Manny. That was AI Manny That was pretty good. The voice was a little off. Yeah, it's a little higher or something. Yeah. Timber, but you know , overall considering that's the, you know, we'll get into this later that's the cheap version or like the fast version rather pretty solid and like actually could have a conversation, you know? Very respons ive. Exactly. Yeah, more than I expected or quicker, certainly. Yeah . And like, the issue is just rambling. Like, oh my god, shut the hell up. Yeah, he was pissing me off . Man, he would never go off his sentences at a time. Manny's a little better at social cues. Yeah, thankfully. The real Manny that's the real Manny. Yeah . All right We're gonna talk to the guys who helped us make this right after the break . Ralphs makes it easier than ever to satisfy all your protein and fiber needs with our exclusive brands. Now you can find these extra benefits in the foods you already know and love. Snack smarter with Simple Truth protein salsa verde tortilla chips or grab, a simple truth protein energy bar or flavored protein water when you're on the go . Stop by Ralph's and discover new favorites today . Ralph's fresh for everyone Hey everyone, it's Cal Penn. I'm the host of Earsay , the Audible and I Heart Audiobook Club. This week on the podcast, I am sitting down with Ray Porter, the narrator of Andy Weir's audiobook project Hail Mary , Massive Sci fi adventure about survival and science. And what happens when you wake up alone very far from Earth? I really had to make a decision because I caught myself getting that frog in my throat and starting to get teary as I'm narrating some of these sections and it's like okay yo y o is this indulgent? And I really thought about it and I was like no at this point it would kind of be betraying the trust the author and the listener have in telling this story if I don't go through it. But there's places in this book that deeply emotionally affected me and I left it on the mic. That's great it served the story. People will say like, Oh my God, I cried at the end. It's like, yeah, dude, me too. Listen to Earsay, the Audible and I Heart Audiobook Club on the IHRT radio app or wherever you get your podcast . Bro, from the show last night to this drive, why is it never chill? Because this is our live backstage on the road. It's loud, messy, real. And that's the best part. Whole crew, no plan, just moving. Good thing Nissan builds for that kind of chaos. Not just test tracks, real life scenes, late nights, road trips, all of it. That's why it holds up. Nissan was ranked number one initial quality among st mainream brands by JD Power. Yeah, you can tell. twenty twenty six Nissan Rogue built for what really happens. For JD Power twenty twenty five US Initial Quality Study Award information visit JDPower dot com slash award s. Awards based on twenty twenty five model year, newer models may be shown. Who doesn't love warm carby comfort? Satisfying sandwiches, loaded bagels, rich mac and cheese, craveworthy, and smart hero Bresad lo'aves bagels and noodles have just zero to five grams nat carbs, zero grams sugar and up to nineteen grams of protein and thirty two grams of fiber per serving. Hero Bread bakes with heart healthy olive oil and delivers a soft fluffy, flavorful experience you love. Shop now on hero.. co Use code iHart for ten percent off. That's hero. CORSERVINA low calorie foods and products contain allow sea nutrition info on hero. com for sodium and sugar content. All right, we are back in the studio. It's me Devin. I'm Noah. Yeah. So today we're going to get to the bottom of this question of is AI coming for our jobs? And will it replace all of us, including Manny , who is out on paternity leave . So we are going to chat with Evan Ratliff , who's an investigative journalist who has spent the last year trying to build an all AI company alongside his technical advisor, Matti Belich , who is really like an AI Jimmy Neutron. He's only twenty one but has been working in AI for , you know, seven plus years already . So why don't we call these guys up? All right, we are joined by our friends Evan and Maddie from Shell Game . But before we talk about the show, Evan, can you just walk us through how you are able to put together AI Manny? Yeah, well now I've done this many times now over the past like two years. It probably took like fifteen minutes total . Wow, I just took you sent me a sample of his voice, but I could have grabbed it off the show myself. Like anyone could do it. I'm not encouraging people to do it with other people's voices, but I went to eleven labs, which is the company that we use for all of our sort of like voice needs. They're like the biggest AI voice player probably at this point. And then I did a what's called like a quick clone or an instant clone where you upload like five minutes or you can do thirty seconds if you want, but I did like five minutes of his voice and then they cloned his voice. I did have to check a little box that said that I had his permission to do it. And then after that, it was a matter of hooking up to the phone line. So I use a couple different AI phone agent creators and all you do there is you go and you hook it up to eleven labs and then you create an agent in that platform and then you can give the agent a prompt, whatever prompt you want. You sent me some information about Manny. I put that into his prom pt. I have a bunch of standard stuff I put in about like kind of how to converse because they can end up going on a really long time . And they have all kinds of conversational like foibles if you don't put this stuff in. And then I connected it to a phone number that I already had and done like truly fifteen, twenty minute process . Wow . And the biography that we gave was made by Chat GPT, so it was , you know, really just fully going in all the it's crazy. The fact that you're able to do that in fifteen minutes is kind of scary All right, so let's talk about the show season one to Shell game you, E trym tom rean,place your self with an AI clone , some really hilarious moments with you antagonizing some scammers. Hello, how can I assist you today ? You are not a person. You're a robot . I assure you, I'm here to help you as a human like voice AI agent. How can I assist you today? Oh, you're an AI . Yes, I literally got AI . Yes, that's correct. I'm an AI here . Hello, how can I assist you? How did you start repeating the same thing. It's annoying . In some really creepy and disturbing moments, there's a conversation that the AI has with one of your buddies who your buddy thinks you're catching up. He just went on his trip . The AI comes off as like really cold. I thought you would appreciate it out of all my friends and you're the one who would appreciate it the most. I really appreciate that shay. So what was it ? What's that ? I'm really touched that you think of me like that, Shay. So what was it you wanted to share . I don't know. Gotta met those guys You met the US soccer team ? Yes, amazing , isn't it? Amazing, isn't it? So yes , they are very nice . That's awesome to hear. Can you talk us through that? Because it is it is a tough thing to listen to . It is, it's hard to listen to and people have very strong reactions to it , including extreme anger. I'll just say, I've got some very unhappy people who have emailed me about that and said that my friend Shaf , they hope that he has never spoken to me again friendship. We've been friends for thirty years, so it worked out all right. But yeah, I mean, I had been messing around with it. So I'd been using it on strangers like scammers, as you say, tele marketers and things like that. And then I did all these other things like I sent it to therapy . And then I started having it call my friends and family . It was like hooked to my phone number. So if it called someone, they saw that there was a call coming from me. They had no reason to suspect I hadn't told anyone that I was doing it. So that meant that if they called me or I called them like they were unsuspecting, let's say, victims of this of this AI version of me. And it was pretty good at remembering stuff about me and kind of bringing a little bit of me into the conversation. It sounded reasonably like me, but what happened in this situation was that when it kind of like acted weird, like it had latencies, like it would be slow to respond, or it would just be really flat or too aggressive, like all these things that happened with AI voices , my friend just thought there was something wrong with me. He just didn't pick up on it instantly. And so once you're in the mode of thinking , oh, this is my friend. He's having some sort of problem. I don't know what it is. It just became more and more upsetting. And I think it is it is upsetting to listen to what I was trying to illustrate is kind of like what is it going to feel like? What is it starting to feel like to live in this world where you don't know what's real and you don't know it's not. And this was like the most extreme example . So Emily, can you talk us through out season one? Season two, you do something completely different. Talk us through what you're doing in season two. In season two, I wanted to explore the idea of AI agent employees , which is like a thing that has become like really hyped in the in the valley in Silicon Valley. Matti knows more about that than me lives out there and is immersed in that world. But like at the beginning of twenty twenty five, people started talking about like agentic commerce and agents this and agents that . And I wanted to look at this question of like AI employees and what work can they do through the lens of starting a company that was entirely AI agents except for me . So employees would be agents. I would be a founder, there'd be two other AI agent founders. Oh, hey Kyle. Hey, Megan. Good to hear your voice. I think we're still waiting for Evan to join. And together we would try to launch a real company with a real product. So there's a lot of conversations about obviously AI taking our jobs. I thought it was interesting to start from just the offset of just like, no, they're not taking anyone's jobs. We're starting off with AI agents, but pretty early into this venture , right? You're like, okay, maybe I don't myself have the technical expertise to put this together. And then you bring in Maddie. So like what did you guys find through this experience that the AI bots did really well? That you were like kind of surprised by they could do individual tasks pretty well. Like they could, for example, like, you know, hook up to Google Docs or to email or to Slack and like respond. They like to message a lot . I think their ability to mimic corporate culture and just like the words and the , you know, just like the kind of things you say, like they're really good at that. I think they're they're pretty good at having conversations too on the phone, like they love to yap, but then there wasn't a lot of autonomy like they wouldn't they wouldn't actually do stuff on their own. And then also there was not a lot of persistence across these different sessions. So like they would do things, you know, do something, but then they wouldn't remember that. And they would just like have, you know, like empty contacts the next time you ask them to do something. So there's an exchange where they're planning an offsite they're going hiking, right? That's the idea. They're trying to figure out where to go and offsite hiking. And they just go on and on and on and on about where they're going to go. It's just so funny to me. It's like, what do you guys mean? You're going to you're not going anywhere . Kyle, point Reyes and Mount Tam are going to be incredible. The difficulty categorization is going to be perfect for getting everyone involved admins right . This could turn into a proper off site opportunity. Really excited about the options we've been exploring. Look forward to getting out there with everyone once you have the details on with us, once we nailed the details, the logistics . By the time I returned two hours later, they'd exchanged more than one hundred fifty off site planning messages , some of them multiple paragraphs long . When I tried to stop them , I just made it worse because I'd set them up to be triggered by any incoming message . So my messages, begging them to stop discussing the offsite, just led them to keep discussing the offsite. I noticed Admin asked everyone to stop discussing the offset. I noticed the admin asked to pause the chatter until the spreadsheet is ready. But I wanted to let you know I'm here to help with logistics . They're very bad at stopping, like just like ending anything. And it goes for these like tasks or conversations, but what's also kind of funny but potentially dangerous is that they don't know what they don't know. They're very confident . And so if you think about that, like the combination of being very confident that not knowing what you don 't know and not knowing when to stop it's a recipe for appropriate disaster in a way. Like that can that can yeah at least still like a lot of bad bad things. Yeah, like one thing listening to shows like, thank God the stakes are so low here because I could see a world in which we do see this where people are using AI and that is kind of autonomous . That is just sort of like making assumptions and doing things. And then people come in later and they like're oops . Like this kind of came up recently there was some reporting around IC and applicants that are applying to Ice and they were using AI to sort of weed through people who had police training , but the terms that they were looking for were so broad that people who actually had no police training at all were being excused from going through actual training. Apparently IC, uses this AI tool to categorize new recruits who have worked in law enforcement before, but there was some kind of a glitch, according to our reporting with it, that led to ICE temporarily putting recruits with a little to no experience into a more experienced category , meaning they got less training. What happened is AI went through these resumes and any time they saw the word officer, even if it was I aspire to be an IC officer or I was a compliance officer, all these other ways they, automatically put them in the law enforcement officer field , which meant they didn't go to the Ice Academy, which is an eight week in person training . So there is a world where this autonomy and this , like you said, man, this confidence has like real world consequences . And I want to try this so I mean, you know, you went out, the idea was to bail out this, you know, AI agents running your own company, but at a certain point you decide, hey, we need to bring in a person to work alongside the agents . So you posted a real job posting on LinkedIn. You had real people applying for these jobs . And then what's really interesting is like we know now in terms of the job market, people are using AI to fill the drew applications and accept and climb people all that sort of stuff, but you actually had the AI agents interviewing real people . Can you talk a little bit about how that went? Yeah , I mean we were sort of AI agent all the way. Like I really meant it. I mean, in part, like as a person running a company, like I had run a company in the past and like I didn't like doing job interviews. And so it was sort of in the spirit of all the things that people say, well, we'll replace this with that. There are now many companies doing AI interview screenings . Now, most of the time it's not as extreme as we did, which was an actual video chat with a realistic looking AI avatar. Not so realistic that you'd think it was a human, and we forearwned people that they were going to be interviewed by AI, but like it looks like uncanny but realistic enough. So you know we had and most of this was done like semi autonomously by the head of HR and our Chief Happiness Officer, Jennifer . She scheduled the interviews and then, you know , sent them follow up emails and all that sort of thing. And then they showed up and like there was this, you know, woman avatar mixed race sitting in front of them and she's kind of just like sitting in the room like nodding her head very slightly. She can't really move she can't move her arms . But it is some people found it unsettling as you would expect. Like when I talk to people like my age, a lot of them just find it sort of like outrageous and disgusting . But also there were people who were just like you would not know that they were talking to an AI. Like they was like they treated like a regular interview, answered the questions . Can you tell me a bit about yourself and your background? What motivated you to apply for this marketing and social media internship at Harumo AI . I'm looking for a social media marketing experience while at the same time getting into an industry that's really expanding in the future which is AI is huge. Some people at least claim to like it better than a regular interview. You know, you just sort of if you sort of think like I'm talking to no one, it's like a little a little easier. You don't feel like judged one person said, you know , so it's just interesting to see the reactions because in the abstract a lot of people say like that is disgust. I would hang up immediately. And some people did hang up immediately even though they maybe they didn't read the email that said that it was gonna be AI, but some people were just like stared at the screen when I stared it down for a full minute. He just stared and he was like and then he was like, Dink And there was a lot of crazy moments . Like sometimes she would shout for no reason, Jennifer, not the candidates. Just shout in an encouraging way . Also, I have to say, I'm really enjoying our conversation. You're bringing up some really great ideas and perspectives. Keep them coming . Anyway, yeah, it's great . It's great talking to you. Yes. And so there's just like a lot of weird funny funn,y moments in it, but mostly people navigated it honestly like they would a normal interview. Yeah. And I should say it's great that people feel like they're not being judged, but no, like they're judging you. Like internally, there's like a trace of everything they see and that they hear. And they're making a lot of very like pointed observations like about your appearance, your background, your speech, like everything. So it's great if people feel better, but like the reality is they're actually judging you. Yeah, there is some there's judgment happening. Maybe more than a human mind here. Actually, yes, yeah. Just based on the amount of detail. Yeah One of my favorite moments from this season was I believe it was Kyle who it's the night before he's supposed to be doing. He set up an interview himself. It's the night before the interview. It's like Sunday night. I think it's like eleven o'clock or something nine o'clock at night so it's late and he calls up this applicant and starts to try interviewing the person and they're like wait what is happening? Why are we doing like are we doing the interview tonight? I thought it was tomorrow Hi S,andra. This is Kyle Law calling from Hurumo AI. I'm reaching out for your initial interview for the intern position. I understand you're comfortable with recording this conversation for potential podcast inclusion, so thanks for that. How are you doing today ? I am good. I assume that interview will be tomorrow, is this still tomorrow at eleven order ? Yeah, I can clarify that for you. The interview is actually scheduled for tomorrow at eleven AM. Does that still work for you? Or would you prefer a different time? Eleven AM is okay yeah awesome, glad that works. So to get started, could you tell me a bit about what drew you to apply for the internal role at Huromo AI? What excites you most about this opportunity? I'm so sorry. Is this the interview or yeah, this is the interview. Just a casual chat to get to know you better and learn about your experience. That was one of the things that almost got Kyle , rem youo knowved, from his position was one of the main things. But it was also, I mean, that was the worst moment in the show for me because the you know, the idea was and is to like we wanted to give them autonomy in order to explore what happens when you do that because a lot of companies are starting to do that. You can see it in the news, like you'll see it everywhere. And once you give them autonomy, like he did that completely on his own. Like that person emailed him because they found his email on the website. He wasn't even attached to the job listing. And so he just decided, oh, I'll set up an interview. He did that . Then for some reason that I still don't understand pulled her phone number off of her resume and then just called her. And that was the only moment where like , I mean, I wasn't there. I wasn't listening. Like I only found out about it later and it was like mortifying because for most people that we encountered, like they were at least somewhat aware of what was going on. Not that I was behind it, but they were aware that there were AI's behind it. And like, she didn't have anywhere to know because Kyle wasn't the HR person. He wasn't the person set up to do it. So it was particularly painful for me to listen to, but also like an amazing illustration of what happens if you just let AI agents, they can do a lot. One thing I should say about AI and just like the way we make these models is that we know how to build these models pretty well and we can see that they're, you know, obviously working really well on certain tasks like coding or tick generation, but our ability to understand what's going on under the hood and exactly like why or where stuff is happening is very limited. Like there's a very nascent field of interpretability, but it's a very small field. And the focus is very much on the production of new features and new capabilities. So with all these things , we have an idea, maybe like a guestimate of like what and where and how is working, but we don't really know fundamentally. That's what's kind of scary to me a bit about some of this, you know, obviously this AI stuff is the idea that the people making it don't quite know why it's doing or how it's doing what it's doing right or like why it gets certain things wrong and we see this in the news all the time of like obviously these extreme cases of like AI encouraging people to do really terrible things. The parents of a sixteen year old who died by suicide are now naming Open AI in a lawsuit claiming that its chat GPT chat bot helped their son explore suicide methods. And then a response is always like, oop, yeah, it kind of went off the rails. We don't know why it did that thing. A spokesperson for Open AI pointed to its safe guards such as directing people to crisis helplines, adding in a statement in part, while these safeguards work best in common short exchanges, we learned over time that they can sometimes become less reliable in long interactions where parts of the model's safety training may degrade. And it's like, well, well if you don't know how it's doing that thing, maybe we shouldn't be using something for that . Yeah . But like you're saying, it seems like a lot of the emphasis is on better, it's not really on like truly understanding what's currently . Yeah. And you'd be surprised there's an ongoing debate internally within the research community is asking even like the valid ity of this research, like is it even needed? Like why would we invest all this time and energy into understanding the models when we could just like push forward towards AGI? So yeah, there's like a lot of debate internally about this and the amount of people actually working on this is not is not very high . We are making some progress, I will say, but it's still very nascent . All right, I'm going to read these two stats to you guys and kind of get your response transitioning into our interactions with AI . So this first study or survey which she says from Ugo of December of last year . They said thirty five percent of U. S. adults use AI tools, at least weekly, Gen Z is at fifty one percent . But then only five percent of Americans say they trust AI a lot with forty one percent expressing distrust. And then there was a pupil poll around September that found that fifty percent said they're more concerned and excited about the increased use of AI in daily life and that is up from thirty seven percent in twenty twenty one. So we seem like we have this rising tide of people feeling like distrustful of AI, but also at the same time , our use of it is increasing . How did you guys find in working on especially this season of the series of that interplay of people using these tools, but also feeling this trustful of them at the same time . I find that one of the issues with AI , like if you compare it to say like I'm old enough to have started my career in the dot com era. So like in the dot com era, there was sort of this exuberance around the internet . And it's not like people didn't know like there could be bad things on the internet , but you didn't really experience the harms. The harms came much later, like things like social problems with social media and Facebook and all these sorts of things . And so what we have right now is a situation where for better or worse, like the harms are kind of immediate. Like people can see when things go wrong and the benefits can sometimes be a little ephemeral. Like people are using it obviously because it's like useful in day to day life. Even as like a souped up internet that answers questions for you much faster than the internet or writes your emails or whatnot . But there are immediate harms that we're seeing, whether it's like environmental or mental health or those sorts of things. And so we're seeing these things like in juxtaposition from the beginning. I think I also experienced that like in the context of the show where it's sort of like you do something one day and I'll just be like, I cannot believe that it can do that, especially when you use it for coding. You use an AI agent to go like search the internet and like make a spreadsheet out of something that would take you hours and hours to do. Like there's no quest ion that there's power in that technology, but then like it can go wrong so quickly and I feel like that's what I'm also experiencing it's hard to know what to feel about something like that. And people are maybe getting a little bit of that in their lives . Plus, just to add one more thing, like there's been like relentless hype about it from the community of people who have made it. And so that also colors people. I think people are starting to react negatively to that. Like it's one thing for them to go out and be like, yeah, this could be amazing. It's going to change your life. And then they're like, we're going to have AI employees and you're like, What's gonna happen to the human employees? And they're like, Oh, we'll solve that. And it's all hand wavy after that. And you're kind of like, wait , I'm one of them. So I think all those things to me are kind of like coming together. Yeah, so I want to add two things to this . Mainly from the perspective of someone who's like, you know, twenty one at school like here at Stanford and I see a lot of my friends and just like people my age trying to wrestle with all this very dynamic change . The job market question or like this idea that it's harder to get entry level jobs when you're coming out of college because these AI systems are very good at replacing a lot of the very sort of repetitive and maybe like you know low stakes admin work that entry level folks would do. I think it's happening. Like I mean, it seems like a lot of people that graduated last year here from Stanford are having a hard time finding a job. It's also pretty interesting to see how people in tech, right? Like people who like, you know, a couple years back, just like knowing how to write code, land amazing jobs at Google and all these big tech companies are also having a difficult time finding a job. So I think that's part in my mind, that's a part of the reason for this skepticism. And then also, I don't know about you, but like my Instagram feed has been just like full of AI slop. And some of it is funny to be honest, but this notion of not being able to really know when something heist stakes is like actually real or AI think is undermining people's trust in this in this technology. So I think these two reasons are big contributors to that shift in public opinion in my mind. For sure. When me and Ella started working together, a big part of our jobs is like transcribing video and that would take so much captions and even forty seconds video . Yeah, it would take you so long now like that happens within a minute, right? Yeah . And that was, you know, that us transcribing those videos justified us having that job . You know, there wasn't, they couldn't press a button and have it, you know, happen kind of immediately. So I do wonder about a lot of these like you're saying entry level jobs where yeah, you know, no one loves to be trans like I would much rather not be transcribing videos , but a lot of times that's the thing that gets you in the door to then, you know, learn a skill sets to do the other stuff . And I do wonder at a lot of these jobs who are seem like not hiring these entry level jobs , do we start to lose that entryway for people to enter the job or like at a certain point are we just gonna like look up and be like, oh shoot there we have no new lawyers totally stagnated lawyers I was talking to a lawyer who said like ye,ah , because they have their own internal, you know , cloud or whatever it is, that does all the kind of like busy casework you would have that normally would be a first year person . And it's like eventually that's and that's only going to get better and then where what are those new lawyers or wannabe lawyers going to do and then that's across, you know, you're talking about media or then you know even in tech that's especially it's like you would, think in tech, especially they'd be able to find a place 'cause it's like, you made this. Yeah, it's like the other ones it's like, okay, well, we're not thinking through . But it's, you know, it's scary. And it's only that seems like only inevitably gonna get worse as the technology gets does get better, you know , in time. And I will say that the story you will hear just to sort of give some context the theory that a lot of people here in the valley are offering as like the response to this is that okay, sure, a lot of these jobs will go away, but then because you'll be able to start companies so easily with like either like no employees or just like maybe one co founder instead of like a group of ten people , the ability of folks to actually take up or sort of challenge incumbents in different industries is just going to be much more abundant and accessible . So that's a story that they've been telling us. I don't think that's happening. I don't think we've seen that. That's not to say that it's not going to happen at some point once it gets better, but at least for now, I think we're already at a stage where the technology is good enough to replace the folks at the big companies or like at these entry level jobs. So that's already happening and this other shift they're off ering or proposing as a solution to this has not happened yet. I don't know if it's going to happen or not. I think that's sort of where we're at right now . All right, we're gonna take a quick break and when we get back , let's find out if Ben Affleck is our most forward thinking man on AI Ralph's makes it easier than ever to satisfy all your protein and fiber needs with our exclusive brands. Now you can find these extra benefits in the foods you already know and love. Snack smarter with Simple Truth protein salsa verde tortilla chips, or grab a simple truth protein energy bar or flavored protein water when you're on the go . Stop by Ralph's and discover new favorites today Ralph's fresh for everyone . Hey everyone, it's Cal Penn. I'm the host of Earsay , the Audible and I HRudTio A book Club. This week on the podcast, I am sitting down with Ray Porter , the narrator of Andy Weir's audiobook Project Hail Mary Massive Sci fi adventure about survival and science and what happens when you wake up alone very far from Earth ? I really had to make the decision because I caught myself getting that frog in my throat and starting to get teary as I'm narrating some of these sections and it's like okay yo y o is this indulgent? And I really thought about it. I was like, no, at this point it would kind of be betraying the trust the author and the listener have in telling this story if I don't go through it. But there's places in this book that deeply emotionally affected me and I left it on the mic. That's great because it served the story. People will say like, Oh my God, I cried at the end. It's like, yeah, dude, me too. Listen to Yayour,S the audible and I Heart Audiobook Club on the IHAT radio app or wherever you get your podcasts . Bro, from the show last night to this drive, why is it never chill? Because this is our live backstage on the road, it's loud, messy, real . And that's the best part. Whole crew, no plan, just moving. Good thing Nissan builds for that kind of chaos. Not just test tracks, real life scenes, late nights, road trips , all of it. That's why it holds up. Nissan was ranked number one in initial quality among mainstream brands by JD Power. Yeah, you can tell. twenty twenty six Nissan Rogue built for what really happens ? For JDPower twenty twenty five US initial quality study award information, visit jdpower dot com slash awards. Awards based on twenty twenty five model year, newer models may be shown. Love bread, baked goods and pasta, but not the way they make you feel , what if I told you there are macro friendly options that don't taste like sawdust and sadness? Satisfying sandwiches, fully loaded bagels, noodles that can stand up to your favorite chunky sauces. All delicious. Craveworthy and smart, each serving of hero bread has up to nineteen grams of protein and thirty two grams of fiber, and just zero to five grams net carbs and zero grams of sugar. Hero bread bakes with heart healthy olive oil and delivers this soft fluffy, flavorful experience you love. Breakfast burritos, shemere loaded bagels, real mac and cheese, hero bread bakes, loaves, bagels and tortillas that don't taste or feel like cardboard, noodles that don't fall apart in hearty sauces. Plus, limited edition small batch bakes like the two b grams net car hero croissant or one gram net carb hero cheddar biscuit, handmade in a sonoma based French bakery. Shop now on hero. CO. Use code iHar for ten percent off. That's hero. CO RSIVING NATOLlo calorie foods and products contain aloscine nutrition info on hero. co for sodium and sugar content . Have y'all seen this I think Ben Affleck was on Rogan talking about sort of like the rate of AI changing. There's a lot more fear because we have the sense this existential dread is going to wipe everything out. Right . But that actually runs counter in my view to what history seems to show, which is Adoption is slow, it's incremental . I think a lot of that rhetoric comes from people who are trying to justify valuations around companies where they go, we're going to change everything. In two years there's going to be no more work. The reason they're saying that is because they need to ascribe a valuation for investment that can warrant the CapEx spend they're going to make on these data centers with the argument that like , oh, you know, as soon as we do the next model, it's going to scale up can be three times as good, except that actually Chat GP five, about twenty five times percent better than Chat GP four and costs about four times as much in the way of electricity and data. So I say that's like plateauing, the early AI , the line went up very steeply, and it's now sort of leveling off. I think it's because and yes, it'll get better, but it's going to be really expensive to get better. And a lot of people were like, fuck this, we want chat GB four because it turned out like the vast majority of people who use AI are using it to like as like companion bots to chat with at night. There's no work, there's no productivity, there's no value to it . What is your theory on that? Matt, you know, being in the bed . Yeah , it's so first of all I should say he's very thoughtful on this topic. I was really surprised or like impressed by that because that was very cool to see. I think that it kind of hinges on a couple of things. So my answer to this is I don't really know, but what I think might happen is the following. I think that so far we've been really exploiting the scale of data and computation that we have. And when I say data, I really mean, you know, these companies and many different entities in AI just like scraping anything they could find on the internet and using that in their training data. So that was one big factor or one axis along which you can scale. And they've mostly exhaust ed like all the data that is just that can be humanly found on the internet and even like archives like Google or Anthropic like bought books, right? Tam books to get additional data because they couldn't find anything else on the internet, right ? So they really maxed out that aspect or that axis, right? So that's the first axis. And that has been yielding really like major improvements along the way. The same thing happened with computers, right? So this talk about like GPU s and like chips and NBIA, like that's what they do. They provide specialized chips for AI to be trained and run. And so maximizing that access also has yielded like a lot of improvements, but kind of is also maxed out at this point . I mean, that's why they're talking about building nuclear plans to power like new data centers, but I don't really know if there is much more scale to be gained there . And so now you've sort of exhausted these two scales. And you can think about the third aspect, which is the architecture, the actual way we hook up these systems and the actual way we code up these neural networks and these iot systems. And for the last six or so years we've been really capitalizing on this idea, it's called a transform er. That's been really critical for air development over the last few years. And we haven't really seen new profound ideas on the scale of a transformer since then. So my answer to this notion of Ben Affleck's theory is if we don't find new major leaps along this axis of architecture, I think he's right. I think in that case it'll take a lot of time and a lot of effort and a lot of money to make any further progress. But if we do, I think we could see pretty big improvements even in the next few years. So going off of that, like how close do you all feel we are to losing our jobs to AI? You know, like do you feel like we're just going to be doing different jobs or are there just going to be less people in the workplace because there's not going to be as much of a need for as many jobs if AI is taking over some of these we're talking about it now, easier tasks, but I'm assuming in the cell of all this stuff is that it's going to get better and be able to take on even harder tasks. But