EconTalk #1000 (with Russ Roberts)

Jun 2 2025

In honor of EconTalk's 1,000th episode, host Russ Roberts reflects on his long, strange journey from pioneer of the podcast format to weekly interviewer of leading economists, authors, and thinkers. Hear him answer your--and Chat GPT's--questions about why he got started, how he preps, and how he picks guests. He also explains why debate gave way to conversation--even about arguments with which he disagrees--and why EconTalk isn't only (or even mostly) about economics anymore. And yes, he shares some of his all-time favorite episodes and why he's so grateful to be the host.

LISTEN NOW:

Comment

●

READ TRANSCRIPT

●

DELVE DEEPER

DOWNLOAD

Time	Podcast Episode Highlights
0:37	Intro. [Recording date: May 15, 2025.] Russ Roberts: Today is May 15th, 2025. There is no guest today. This is a monologue. As far as I know, this is the 1000th episode of EconTalk. And, to mark that occasion, I thought I'd share some thoughts. It's a little self-indulgent. I'm going to talk about some of the logistics and nuts and bolts of the podcast, which people have asked me about over the years, and I'm going to reflect on what this has been like to do this for almost 20 years, 1,000 times.
1:11	Russ Roberts: So, to do that--I started to do this. I made an outline of what I was going to talk about and then realized I wasn't excited about doing it, and I went home and told my wife that it had just kind of fell flat, just couldn't get any enthusiasm for the idea. And she said, 'We should have had ChatGPT [Generative Pre-trained Transformer] ask you the questions.' And I thought, 'Well, that's a good idea.' So, I did that. And so, this--I will occasionally repeat some of its questions or just answer them because that'll make sense. But, that was a fascinating experience in and of itself, and I may reflect on that along the way as we get started. So, the first question--I love the way that it asked this question. This is the -03, by the way, of ChatGPT, which is really an extraordinary achievement. I've done, I think 20 episodes on AI [artificial intelligence], interviewing people about it, its threats, its potential, how it works; and I do think -03 is a step--a quantum leap--in improvement. And, we'll talk about that maybe at another time.
2:20	Russ Roberts: But here's the wording of the first question: ChatGPT: What was the spark that convinced you to hit Record? And, what were your earliest ambitions for the show? And, it had said before: When you launched EconTalk back in 2006, podcasting was still a fringe medium; and long-term, long-form economics conversations sounded frankly like a gamble. So, what was the spark? Russ Roberts: Well, I was late to blogging. I started Cafe Hayek with Don Boudreaux, and it has had a long run under Don's leadership. In the early days, I blogged alongside him; and I felt we had come late to blogging in whenever we started in 2004, whenever it was. And so, I didn't want to be late to podcasting once I discovered it. And, the way I discovered it was, as far as I know, James Reese, an economist, interviewed me on his podcast, Radio Economics. I don't think it exists anymore. Jim, if you're out there, say hello. Or if anybody knows about this, can remember this better than I can. But, he called me up and interviewed me about--which is how we did interviews in those days, on the phone--he called me up and asked me to talk about Walmart. And at the end, or maybe it was beforehand, I said, 'How many people listen to this?' I mean, I'd never heard of a podcast. He said, 'Well, it's 2-to-3,000.' And, when I heard that, I thought, 'Wow. If I could show up on Monday mornings and there were 3,000 people sitting in an auditorium with two chairs at the front of the room and I could go sit in one of them and a guest could be in the other one, I think I'd come to that room. And it would be fun to have 3,000 listeners.' Now, at the time, I thought, 'Well--' And, the other reason I was interested was that I wanted to do a--I had considered for a while doing a radio show, a talk radio show, an interview program. And, I had done a lot of commentary at that point, I think for NPR [National Public Radio]. And, I thought maybe someday I could get an NPR talk show--maybe--and maybe I was interested. I didn't know if I could really want to do it. It seemed like a lot of work. But, this seemed like a way to try it, and do, like ,a free trial to do podcasting and see if anybody listened. And, how hard was it? So, in the early days, I think I started off just doing them occasionally. You can look at the archive. But shortly after that, I realized after starting, I realized that people expected to hear one on some kind of regular basis. Because otherwise they'd show up and it would be the same episode as it was up there before, and we wouldn't be making any progress. So I was pretty quickly, pretty early on, I decided I would do one every week. And I kept to that schedule. I would take off the last week or two of the year for the holiday season, give myself a break, and then I realized: Well, people like it every week. So I think I'll just record one in advance. I can take off the holidays anyway. And so, it turns out, according to artificial intelligence--I forget which one I looked at, I think it was ChatGPT--I have put out an episode of EconTalk for 854 consecutive Mondays. This will be 855 if all goes well. Or maybe it's a little more than that actually because it didn't know about the couple that are coming up. But, December 2008 was the last time I missed a Monday. So, the first Monday of 2009, for the last 16 years, I have done one of these. It's hard. I have a job now that's pretty demanding. I had a job before, but EconTalk was a non-trivial part of it. So, the chance to do this every week has been a lot--the privilege of doing it every week has gotten a lot harder--now that I'm president of Shalom College in Jerusalem. But I'm kind of addicted to it and I like to think some of you are as well. So, we haven't missed a Monday in a long time. I worried during the war that we might miss--the war here since October 7th [Oct. 7, 2023]--I might miss one. We've managed to not do that. We've managed to keep them going. I will have a health issue inevitably, probably, someday while this program is still in my hands, and that's exciting. It's still in my hands, but someday it will have a challenge; and we'll maybe use an old episode to keep the streak going. But, for now, we've kept it going for 850-plus Mondays. Which is kind of cool.
7:15	Russ Roberts: The next question was: ChatGPT: How did I think of this 3,000-person interview audience? Was it going to be a lecture, or a radio call and a fireside chat, or something else? Russ Roberts: And, it's funny, when I started the program, for some reason I kind of thought it should be about an hour. I don't know why I thought that, but I soon found out that sometimes it's hard to keep it to an hour. But, I tried to, in the early days. I remember my dad saying, 'Oh, an hour? No one's going to listen for an hour.' I mean, it's 2006. He said, 'Radio pieces are, like NPR [National Public Radio] is eight minutes. That's long. No one will listen for an hour.' I didn't care. The other thing that was fun in the early days is that people said, 'Well, you'll run out of gas because how many economists can you interview?' Of course, I found out quickly that there were people who weren't economists who were fun to talk to, and I had this brilliant idea that you could interview somebody more than once. Sometimes they had more than one hour's worth of interesting information. So, obviously the program has changed a lot since the early days when it was pretty much all economists all the time. But, I'm now am happy to go over for an hour. And of course, since I started the podcast, there are podcasts that go for three and four hours. I've been a guest on some of those. They say, 'How long are we going to go for?' 'Oh, three or four hours.' I think I can't stand to listen to myself for barely more than an hour. I can't do that. So, I've done a few longish ones. But on EconTalk, I think the longest episode we ever did was Davies on Extreme Economies, I think it's called. We'll put a link up to it. It's Richard Davies, and that was two hours and four minutes. The Haviv Rettig Gur episode is about that long. It's two hours and four minutes--maybe a few seconds shorter than the Davies one--but they're both in the two-hour-and-four-minute length. That's a little long. But the goal now is I try to go a little over an hour and if it's still interesting, I go an hour and 15, or an hour and 20. In the early days, the audience I had in mind were people interested in economics, and I was always thinking, 'How do I reach people who are interested in economics? Should I advertise in The Economist or the Wall Street Journal?' Of course, we never advertised anywhere in that normal way. But that's who I saw as my core audience. And, in the back of my mind, I thought I was going to encourage people to understand free-market principles better. So, early episodes--especially with people that I didn't agree with--were more or less a debate. And, if you go back to the early episodes, there's two things that bother me about them. One is that debate mindset. And the other is I talk too much. So, if you go back to the beginning, as many people have--which blows me away--there are many people who tell me they start at the beginning or they've gone back to the beginning and they've listened to every single episode. Some of them more than once. But if you do that, don't be discouraged: They do get better. But, I got interested--well, two things. One is I realized pretty quickly that my audience wasn't people interested in economics. It was people interested in learning something, which is why eventually we added the tagline, Conversations for the Curious. It was for curious people. People were looking for educational content that was somewhat a little bit entertaining. And that was my audience. That is my audience now. And, it's a crazy thing. You're doing the dishes right now or you're walking your dog or you're working out at the gym and you want to grow or learn or have an interesting something to listen to. And, those are the people I think are my main audience, which is--hello, out there. It's nice to have you. So, that's the story there.
11:09	Russ Roberts: The next question actually at this point--it's kind of interesting. Just an AI aside: as I mentioned, I think the beginning of EconTalk was when I was interviewed by Jim Reese, James Reese on the show Radio Economics. In the new version of -03, if you watch while it's thinking, you can see its thoughts, whatever that means: you can see what it's looking for and what it's trying to discover. It kept coming back to that question of what was the first podcast I was on that got me interested in EconTalk? It didn't let it put it down. It couldn't put it down. Two or three or four different times that was what it started looking at when I asked it to continue and ask me another question. It was very obsessed with that. And also, it refused to do what I asked it to do, which was to have a conversation back and forth. So, at this point, after I answered the question I just did, it then gave me a bunch of questions: ChatGPT: How much with the mix of entertainment versus education, engineering or re-engineering the prep for when I wasn't doing as much debate? How do I get chemistry to work across the screen now that we're doing it on Zoom? Broadening the virtual hall: How did I get more downloads and people? Russ Roberts: And, we now probably have something over, by the way, it was something like 100,000, maybe 150,000 listeners. It's hard to define. Any one month has different numbers, and my actual total numbers of downloads are down for, I think two reasons. One, there are people who got angry that I did a bunch of episodes on Israel; and maybe we'll talk about that. And also, Apple stopped automatically downloading episodes to people who, once they subscribe, they don't get every episode that comes out anymore. Now you have--if you don't listen to any of the episodes that have been downloaded, if you don't listen for a while, it stops automatically downloading. So, that hurt my numbers. Of course, that shows the numbers were somewhat distorted. Anyway, our listenership is something over 100,000, maybe 150,000. Anyway, so to continue, the question is why did I stop doing the debate? And, a couple of reasons. I realized that if I yelled at people and debated them and challenged them constantly--people who disagreed with me--really[?] wouldn't be as interested in coming on the program. And that would mean I'd end up preaching to the choir. And I wasn't interested in that. And I also came to believe--maybe just convincing myself because I'm biased--that debate isn't as good as a shared exploration. That's more like a conversation for discovering truth. If you rant and counter-rant, you're going to get eyeballs and downloads and hits, but I didn't think that would be good for my soul. I thought that would be bad for me. And, I also realized a gentler approach was just more pleasant. I trusted my listeners. I didn't think you had to hear every counter-argument. People would say, 'How could you let so-and-so get away with saying that? Why didn't you answer them? Why did--' I thought, 'Well, that's your job. Your job out there is to when you hear something you think is a bad argument, to take note.' And I also would say to people who complained about that: You know, if I answered everything I disagreed with and tried to refute it, we wouldn't get too many observations in the of course of the talk--of the interview. It would just kind of stagnate. So, the bottom line is I tried to build what I would call respectful skepticism with people I didn't agree with. But, I saw my mission when I'm interviewing an author about a book they've written, to let them make the case for the book. To try to bring out the narrative arc of the book, or at least the parts that I thought were interesting or that I thought you, the listeners, would find interesting. Now, I still challenge lots of things. I still raise questions about something an author would claim. But in general, I do not keep going back and forth and argue with them. So, it's not an argument. I challenge respectfully. That's sort of my way I think about it. There are exceptions, even in the later years. Some people say things that are so shocking to me, I feel like I can't stay quiet. But, in general, I try to be let them have their say. I make it clear when appropriate that I do not agree and why. And then, you, the listener, can make the decision of which one makes sense to you. My prep hasn't changed much in a long time. I script about 15 questions--maybe 12, maybe 18. I sometimes will have quotes from the book that I want to use as question generators or that I might read out loud to let you, the listener, try to understand what the book is about. But, I script about 15 questions that I know will get us enough material for the hour, or hour-plus. Of course, I don't just go down the list. We digress. We go off into side-tangents. And, a lot of what is challenging about being the host--which, it wasn't clear to me until I actually had to do it--is you're doing a bunch of things at once. It's very hard to listen--because you're looking at the clock, you're trying to figure out how much time you have left, how much questions you have left, should you ask a follow-up question? Should you switch gears? Should you challenge? And so, it's funny: many of you probably have a better idea of what I said or what the guest said than I do, because my attention is always being pulled in those different directions. And, every once in a while--without naming names--I'll get a guest who is not very chatty or not very conversational or very taciturn in general or shy. And I realize early on that I'm in trouble. Fifteen or 20 questions are not going to be enough to fill the time. And you'll hear me even in later years talk more than I might normally do in those situations. So, if you notice that, that's what's going on there.
17:30	Russ Roberts: The next set of questions--again, ChatGPT wanted to ask me a bunch at once: ChatGPT: How do I know when to bite my tongue? What about those questions? What about tangents? What about leaving economics and doing other things? Russ Roberts: A whole bunch of others; there's a bunch more. But it came up with about 14 questions at that point, so I'm going to try to answer some of them. So: When it comes to biting my tongue--that is, not responding to something--I don't remember particular moments. Sometimes I hesitate internally: I'm debating whether I should answer or not. What else? Oh: Do I share the questions in advance? Never; almost never. I have guests who ask me to, but I always worry that if I do that it'll sound scripted and less spontaneous. So, I will occasionally give them--when they're uneasy or nervous, I'll give them an overview of the topics we're going to talk about; but I don't give them the exact questions. A handful of times I've said the first question to the guest because I want to get off on a good start. I don't want them to be all rambling and lost when they start. And, I should also say that if you go back to the first episodes of the program, I am often fumbling around trying to get the conversation started. And, I realized pretty early on that that's when listeners leave the room: you switch channels, turn it off, go to find something else. So, I always script the opening question and read it verbatim. But after that, often I'll improvise and go with the flow. What else? Was there a conscious moment when I broadened the focus from economics? I don't think so, but it was gradual. It was pretty clear to me when--a couple of things were clear to me at various points. After the Financial Crisis of 2008, it was pretty clear to me that I had to understand it. And I knew I didn't. I knew almost nothing about finance. So, I did 20, 30 episodes to try to get tooled up on that. And, you came along for the ride. You heard those as well. And I figured you wanted to understand it as well as I did. And, as a result of that, I wrote a book Gambling with Other People's Money, trying to understand the incentives that may have contributed to the Financial Crisis. So, that was really a wonderful intellectual journey that I couldn't have done without the different guests that I did, that I interviewed in those days. And then, starting around the rise of Trump in the mid-2010s--2015, 2016, it was also clear to me at that point that standard economics was not what people cared about at the moment, and I started trying to understand what was going on in America that led to Trump. And by that I meant--and I've said this many times--I don't think of Trump as much as, until recently, I would say he was much more of an effect rather than a cause. Right now he's doing some causes, he's causing some things. It's a very different time. We may do a future episode on that, a follow-up to the one I did with Mike Munger on DOGE. But, the general broadening was the realization that economics, part of it was economics is too narrow to understand what's going on. This isn't just about 'the economy, stupid'; it's about other things. And, the other part was that I found economics less interesting. I found economics less able to contribute to my understanding of the world. There were many, many other things I was interested in. And, every once in a while I reflect on the reality that while that is true--that I am a little tired of economics--it's also the case that a little economics goes a very long way in preventing bad reasoning. So, even though I sometimes have become more skeptical of economics as a way of thinking, or I've softened my views on what is some of my dogmatism--I'll give you an example of that in a few minutes--even though I've softened my views on that, it really is useful to understand some of the basics.
22:00	Russ Roberts: But having said that, I have a joke that--I have listeners, I'm sure some of you are still out there who would love to have an episode on Bitcoin every week; or on monetary economics generally or some topic that you're passionate about. Which I respect. The problem is, is that I'm sure there are things I don't understand about Bitcoin, quite a few things, but I understand what I want to understand. I've kind of learned what I think I need to learn about Bitcoin. Just like I'd learned what I needed to learn about the Financial Crisis. I'm sure there are things I don't understand about it. I'm sure there are other theories. But, many of those theories are just not interesting to me. And, maybe I'm wrong. Maybe I'm missing a chance to learn about some incredible theory of the Financial Crisis or some aspect of Bitcoin that's revolutionary that I'm neglecting. But, what I've done in those topics is I've done a bunch of interviews. Same with AI right now. I've done a bunch of interviews on AI. There are more things to learn, there are different perspectives, but I've learned a lot, and I hope you have, too; and it's time to move on to other topics. I would say the same thing about Israel. I moved to Israel in 2021. I'm Jewish. You'd think I'd know a lot about the founding of the state and the Arab-Israeli crisis and what became the war in Gaza. But the fact is, I didn't know a lot about it when I moved here. I knew something about it. So, a lot of those episodes--and I don't know, we did 14 or so on Jewish history, Israeli history. And I tried to bring in voices from across the spectrum. I struggled to find Palestinian voices. I have some in the archive, but the truth is some Palestinians said they would be on the program and then we couldn't ever find a date. I tried a few times. It was clear for whatever reason, they either didn't want to be on the program or had bigger fish to fry. And most of them just never responded to my emails. For whatever reason. There's no point in speculating what the reason is. I want you to know out there that I did try. But, even without those voices, I tried to get some variety in the perspectives on the Arab-Israeli relationship and on the history of the founding of the state and the post-state problems that Israel has had with its neighbors and October 7th and its aftermath and so on. But a lot of people didn't like that. I've lost listeners who were angry I was too pro-Israel, which I'm sorry about that. I am pro-Israel, but I am eager to learn other things. I'm eager to understand the Palestinians' narrative; and I certainly understand that it's complicated, which of course is sort of the motto of the show. It's complicated.
24:56	Russ Roberts: ChatGPT asked: ChatGPT: Are there moments that left me emotionally wrung out? Russ Roberts: Sure. There were a couple episodes where people yelled at me, insulted me. I mostly kept my cool, I think. I try not to lose my cool. I would often get letters in those days, people saying, 'How'd you stay calm?' And, they'll see me in person; and if I give a talk, if I'm giving a talk somewhere publicly and people come see me, they'll always often remark how different my persona is on stage giving my own talk versus as host of EconTalk. And, they'll say, 'Wow, you're so passionate or intense, but on EconTalk you're so calm.' And, I always say, 'Well, yeah, when I'm doing EconTalk, I'm wearing my EconTalk hat.' And, my EconTalk hat, which is what I figuratively wear when I'm the host is--and you can get an EconTalk hat, by the way. EconTalk swag is available. An actual EconTalk hat But I don't wear that hat when I'm podcasting. That EconTalk hat means: when I'm the host, I've got to stay calm. And, it took a while. You'll hear it: in the early days with people I don't agree with, I'd get worked up. And it got to the point where I got less worked up, and I got calmer even when I was insulted, which--fantastic skill to have, I'm very happy to have it. It's not the case that I can always remember I'm wearing my EconTalk hat, because sometimes I'm not the host: I'm out in the world. Anyway, the last few years, you know, they're less. I want to say one other thing. At some point I realized that--the show, although listeners claim sometimes to want to hear me, they often would complain in the early days they wanted to hear the guest--more of the guests. And I'd say, 'Fine. Great.' And, I came to embrace that. I try to give the guest more time than I might want to naturally grab. And, again, I saw my goal in those days--and still today--that my job is to help you understand whether this book is worth reading. Is it valuable? My ideal is to try to have an interview that's better than the book. I can't always do that. Some books are fabulous and I can't live up to that. And, some guests speak--don't speak as well as they write. So, the interview is not as exciting as the book. But sometimes it's better--in my mind at least. Which is very satisfying. But, that's my goal, is to help you either learn the ideas that are in the book or the essay and maybe decide whether you want to buy it or not. But, you might decide, 'I got enough out of this. I don't need to read it.' Or that it's not worth reading in your view. That's fine. I always love it when people say, 'I didn't think I was going to like that episode, but it turned out it was really interesting.' So, I do hope you can trust me. I try to read books that I and interview guests I find interesting, and I hope if you're a listener that you will feel the same way. We'll see. Anyway, a lot of people say, which is--I can't tell you how gratifying it is--that my lack of combativeness in the face of disagreement is--they like that. You learn from that. And, I find that I'm so appreciative that that's the case for you. I love it. That was not the goal of the program, but it is, I'd say, the most important thing that I've accomplished with the show, which is to give people a mode of disagreement that's respectful. And, I've tried to get better at that over time. I don't know if I am.
28:38	Russ Roberts: There's virtually no editing of the program. We edit out coughs, sneezes. I sometimes lose my train of thought. I'm doing one of these interviews at the end of a very long day and I have trouble keeping things on my mind, in my mind, in my head. And, I'll say, 'I lost my train of thought.' I'll try to regather myself. And, we edit that part out. But otherwise, it's pretty much just the conversation. One of the things that happened once a guest had insulted her profession, her colleagues in general--not a particular person. But she said something negative about her discipline, and she called me or emailed me afterwards and said, 'Can we cut that part out?' And I said, 'Maybe, well sure if you want, but let's see how bad it was.' So, I went back and listened to it. And I didn't think it was bad. So I said, 'I'll tell you what, I'll let you listen to it. I'll send you the raw file and if you don't like it, you can take it out.' Once she heard it, she thought, 'Yeah, it's fine. You're right. No big deal.' It's just an interesting phenomenon that when you look back on an interview or conversation, a lot of times you forget what actually happened and you get anxiety about it.
29:49	Russ Roberts: AI wanted to know: ChatGPT: if I use any AI tools for prep other than this episode. Russ Roberts: And the answer is: I don't. But, maybe that'll change going forward. I do like to read the book. I would not like to interview a guest where I used AI to read the book in advance and generate the questions. It could happen under stress or time pressure. But in general, I try to read the whole book. Which I think is unusual. And of course, that affects what kind of guests I can have. I don't want to read a book a week. But there are years you can go look where I'll do 20, 30 books. I think most years I do 20, 30 books a year. I try to pick books that I'm interested in, I'm going to read anyway ideally, or I want to read. But, because of the time pressure reading the book, and that expectation I've set for myself, I try to mix in things with the books. And of course, some of those interviews are my favorites--they're probably yours--where I interview a practitioner about what their life is really like. We've interviewed people about how potato chips are made, how a Broadway show gets done, what it's like to run a hair salon, what it's like to be a car sales person, what it's like to run a seafood restaurant chain. So, I love those. I hope you like them, too. I wouldn't mind doing more of them. They're fantastic. And, obviously they're less prep for me. I can talk to those people all day long. I don't have to read anything in advance. But, in general, I try to read the book, if it's a book. And I try to read every word. But sometimes I lose interest in the book or I don't have time. And so, what I do is I read--the way I describe it is I read every page. I'll scan a page, make sure I see the key agreements--excuse me, the key arguments--that the author is making. Because I don't want to misunderstand the point they're making or misinterpret something they're saying and then ask them a question that's messed up because it's not what they're saying at all. So, I do try to read the whole book; but it's naturally the case sometimes that I realize, 'Gee, this book looks a lot more interesting when I started it.' And then, I tend to skim a little bit in the middle there or toward the end. I don't choose guests that I don't respect. I only choose guests that I respect. So, when sometimes you'll write me and say, 'Why haven't you interviewed so-and-so?' Or, 'You should interview so-and-so.' And, by the way, if you ever want to find out if I've interviewed someone--a lot of times people will say, 'You should interview so-and-so.' And, I'll say, 'Your wish is my command.' And, I'll send them the interview. Necause I've already done it. And you just missed it. Or, you didn't know how to look it up. We have an archive at econtalk.org. We have an archive at russroberts.info, which is my personal website. But, the easiest way to find out if we've ever interviewed anyone, so if you want to know, did I ever interview Milton Friedman? You just put EconTalk Milton Friedman and it pops up. It's always the first one. Or Ronald Coase. Milton Friedman. To my great delight, I was able to interview Ronald Coase, and he was the oldest guest I've ever interviewed. I think he was 102 or 104, I can't remember. But that's the easiest way to find out. But, anyway, someone will suggest a guest I haven't interviewed. And they'll say, 'You should interview so-and-so.' And, I'll think, 'Well, it would be lively, but I don't respect so-and-so.' So, if I interview that person, it's going to be embarrassing. I'm not going to do a good job. It's not going to go well. So, the bottom line--and sometimes I'm wrong, of course: I shouldn't respect someone. But most of the time, almost always, the people I've invited are not--they're people I respect. It's one of the reasons though I don't generally--I don't think I've ever broken this rule: I don't interview politicians because I'm interested in the truth. They're obviously selling. Of course, academics aren't always interested in the truth either, so it's hit or miss with them, too. I was asked: Could there be an episode 2,000? It's unlikely. I'm 70 years old. I don't think I'll be doing this when I'm 87 or 90, but I'd like to do it for a while. I can't tell you how intellectually alive EconTalk keeps me. I have learned so many things and gotten so excited about so many things. Just a silly example: As you know, my granddaughter loves owls, and I thought, 'You know what? I should learn something about owls to keep her engaged with that.' I realized I don't know anything about them. So, what did I do? I found a book on owls and I read it, and then I interviewed the author Jennifer Ackerman. And that's a blast. That's incredibly fun. Or: I don't know much about the pharmaceutical industry and I interview a zillion people. And I get smarter. And I hope that works for you too, because that's definitely what I'm trying to do here. Okay?
35:08	Russ Roberts: So next: As I said, once I feel like I've learned enough about something, I'll put it down. Right now, that's the case for AI--so I'm not going to do another episode for a bit, probably. But on the other hand, it's changing so quickly; that'll change, too, and maybe I do a bunch soon. Maybe it'll be different worries that I think people have that come to light. It's changing. So I'm going to spend more time with it and learn about it. And maybe something else--other issues will come up. Some topics are endlessly interesting to me, as you probably know. Epistemology--that is, how do we know what we know--is endlessly interesting to me. Healthcare, for example, what works and doesn't work. The complexity involved in the human body always fascinates me, and you can see some evolution in my thought as time passes on the issue of healthcare. I'm pretty free-market on healthcare. That is, I think the current system in the United States, for example, is not very effective. It's very expensive. I think it's pretty high quality for the people who have good access to it, but not everybody has good access to it. And that means, because it's highly subsidized--which is not a free-market thing--those who don't have access pay through insurance or government programs pay an enormous premium. The only point I'll make there, as I've said many times on the program, out-of-pocket costs of that program have--excuse me, out-of-pocket spending by healthcare consumers has fallen dramatically over time. And, that means that when you're getting healthcare in America, you're not spending your own money. That pushes up your desire for healthcare: You're spending somebody else's money. And that has an important effect. So, that'd be one example. But, the other example I want to give, which I think is more about the challenges of avoiding bias: I used to be a defender of the pharmaceutical industry. I still am when appropriate, but when we think about, say, price controls on pharmaceuticals or changing property rights around pharmaceuticals, I'd always say, 'Well, if you do that, it's going to come at a big cost. You're going to have less innovation.' And that's true, of course. But, what I didn't understand and I came to understand, for example, after listening to Robin Feldman's episode on pharmaceutical pricing, is the creativity of the pharmaceutical industry in playing with intellectual property laws to keep competition from generics at a minimum. So, the monopoly power of a patented pharmaceutical gets extended beyond the letter of the law. Sometimes it's shorter than the letter of the law because of time it takes for approval and so on, so I do understand that. But my point is, is that economists often have a knee-jerk reaction: Well, government intervention there is going to--well, the healthcare system is not free market, not close to free market. The intellectual property rights around pharmaceuticals are incredibly complicated, and a lot of times economists have stylized stories to tell about those things that I think are overly simplified. And so, that was a chance of growth. That was growth for me to appreciate that. What else did I want to say here? I think I made it clear: I'm not that interested in monetary economics anymore. I thought I understood it when I was younger, when I was training at the University of Chicago. It was very powerful; and now I'm more skeptical of its reliability as a way of fully understanding everything. I think macroeconomics is really complicated. I've become much more of a Hayekian than a Friedmanian monetarist. When I say Hayekian, I mean in the Hayekian of the Nobel Prize address, "The Pretence of Knowledge." The "Pretence of Knowledge," fabulous essay, fabulous speech he gave when Hayek won the Nobel Prize. It basically expressed a skepticism about our ability to have a full understanding or a useful understanding of the complex system called the macroeconomy. As you may know, I am increasingly interested in talking to creative people. I love my interviews with the photographer, Jessica Todd Harper; Sabin Howard, the sculptor; the novelists and poets I've interviewed: Dwayne Betts, Dana Gioia, Amor Towles, and Mark Helprin. Those are exhilarating for me. They're fun for me.
39:56	Russ Roberts: I was asked: Have I ever listened to an episode, relistened, and been surprised by what I said? As I mentioned before, a lot of times I'm not listening, so I do miss stuff because I'm thinking about other things to get the episode going. I wish I was better at putting guests at ease. It's quite a challenge over Zoom. A lot of people would assume that if I do something face-to-face, it's going to be more intimate--and more, it'll be a better conversation. That's not true. Some people are very uncomfortable being in the room with a stranger for the first time and trying to be interviewed. So, Zoom actually is good for some people, that distance that it provides. In my recent episode with Dwarkesh Patel, we talked about that. I think it's a real art to put people at ease. My favorite episodes, many of them are where I feel I've made a friend. A lot of that's been in recent years. In the early days, I loved EconTalk because I always learned something. I still do sometimes, obviously. But once I changed the tone and made it more of a conversation and less of a debate, I got better at connecting to the guests on a human level; and it's special. I won't name names, but there are many, many guests I've had in the last, say, 10 years where I realized it'd be great to see them for a drink or socially if they ever came to Jerusalem or if I was ever in their city. Those are very precious to me. There were a handful of episodes where once the recording stopped, we shared things that were personal that we didn't want to record, that were really powerful. Those are really magical for me. Other guests, they're just friends in my mind. Maybe I'm a friend in their mind. We had a special connection. Maybe another time we'll reconnect in person. And, I should just mention in passing that our relationship--mine with you, the listener--is of course very asymmetric. You've listened to me for thousands of hours. I may have received an email from you. So, you know about my granddaughter. You know about my quirks, my parents, my weird habits about eating. I've shared all kinds of things over the years about that. But I know nothing about you, so I'm kind of your friend, but you're less my friend--which is just the nature of modern digital life. What else did I want to say here? I'll just say something about conversation rather than debate, also. I like to think our brains are wired to hear conversation and learn from it. It's certainly true for most human history: That's all there was. There weren't any books, there was no reading, there was nothing else except people talking to each other. And there's no video. It wouldn't be surprising if our brains had an architecture that was designed to take in information and discover information through exploratory conversation or listening. So, I love that. And so, even though one of the deepest things I've ever learned is from Adam Mastroianni that the brain is not connected to the ears--and therefore what we hear in a lecture doesn't always go in, and sometimes we need experience to learn lessons--I like to think that conversation is different. And, you listening to conversation, is different than just being told something. So for example, one of the nicest things you say to me sometimes as listeners is, 'You asked the question I was going to ask.' So, that's cool, because what that means is that your brain is running alongside mine and we're learning together from the guest and processing it in a similar way. At least I like to think so. Another big thing I learned from being the host, of course, which we've talked about before on the program, is when I realized that both sides of most ideological debates have lots of facts on their side and lots of studies. And, that was the beginning of my, I think what the fancy name is, epistemological humility. That is: I'm not always confident that what I think is true, is true. And, along the way, I became highly skeptical of the power of econometrics, data analysis of the kind that economists and other social scientists do. You'll find that theme running back through the program starting, I don't know, 2010 maybe, I'm not sure. But, I realized that the people on my side, their facts and truths were maybe not true. They maybe weren't any more reliable. Their facts could be true; but the other side of facts, also. And so, you're stuck with logic and other ways. I've written a lot on this. Maybe we'll put up something about it. I mean, it's a bit discouraging to think that you can't use data and statistics to prove things. I always add: That doesn't mean they're irrelevant. It doesn't mean data doesn't matter, facts don't matter. It's just that the ability to tease out, say, causation in a complex world is, I think, very challenging. And, I think the replication crisis that we've had a couple episodes on is a good example of that.
45:10	Russ Roberts: What are some of my favorite episodes that I remember vividly? Well, Christopher Hitchens would be one of them. Christopher Hitchens was visiting the Hoover Institution. I was there for the summer; and I realized he was in town and was at Hoover. And I got ahold of him--like, it was probably on a Wednesday--and I asked him if he'd like to do an EconTalk episode. I needed an episode for Monday. So, he said, 'Yes.' I said, 'Let's talk about Orwell.' And then I ran to a bookstore on University Ave.--I forget the name of what it was right now. It might've been a Borders that used to exist. And they had one book by Hitchens: They had his book on Orwell. And, the book is called, I think, Why Orwell Matters. So, I asked Hitchens if that's what we could talk about, and he said, 'Sure.' So he said, 'Come to my house.' So, he was staying at someone's house; and it was large and sprawling. And he told me to bring lunch. I got there around noon, and we sat out at the pool that was at the house, and we ate sandwiches. And, I'm pretty sure we had a scotch, and I'm ashamed I don't remember what brand it was, but I'm sure there's some Hitchens fans out there who will know. But we had a scotch; we're out by the pool; and now I've got to interview him. And you'll go back and listen to it: our audio quality wasn't as good in those days. This was obviously live and face-to-face. And, we were recording this and there were workmen working on the house, and they would constantly come into the living room where we were recording and interrupt us. I was there till, I don't know, three or four o'clock. I was there for hours. But, it's one of my favorite interviews because the one question I was wise enough to ask him was if he saw himself as an Orwellian figure--a man who stood up for his principles and paid a price in lost friendship. Because Orwell, famously, after the Spanish Civil War, soured on communism. And a lot of his communist friends hated him for that, and probably I think, stopped talking to him. And maybe he had personal danger. And, Hitchens had been a supporter of the war in Iraq, and he lost a lot of friends and supporters. So, I asked him if he saw that as a parallel. And it's one of my favorite moments of the program. He said, 'Absolutely not. We're nothing alike.' What Orwell had to endure for what he said and stood up for is nothing compared to what, he, Hitchens had to endure. So, that was very moving to me. And you can listen to that in the interview. I have very powerful memories of interviewing Milton Friedman in 2006. Now, I never had Milton for a class for credit. I had him for a non-credit class. My first year at Chicago was his last year before he went out to Stanford and the Hoover Institution. But, I sat in on that class. Many of us first year students did. We wanted to learn from him. And that class was only one thing: It was Milton standing in the front of the room and answering questions, anything we asked him: we could ask him anything we'd want. We'd often ask him questions off the Core Exam--the exam that we'd be taking at the end of the year--to see if he could answer them. And, he couldn't always, which was really great. It made us feel good. Anyway, Milton was always nice to me after that because--it's a long story, not worth going into. But, the bottom line is I knew him beyond that. I had interacted with him about my first book, and he gave me a blurb for it. And, once I started the podcast, I thought, 'Boy, it'd be great to have Milton Friedman on EconTalk.' So, I showed up at his apartment in downtown San Francisco, a gorgeous high floor overlooking the city with at least two, if not three views, views in two or three different directions. It was absolutely magnificent. And, we sat in his study, and I put a microphone on him and clipped on his lapel; and I had one on my lapel. And we talked for--I don't remember how long. We divided it into two parts. One is on money--meaning the monetary history of the United States and his views on monetary policy and monetary economics. And the second was on his book, Capitalism and Freedom. And, they're pretty good interviews. I talk way too much--I'm ashamed. I wish I'd talked less. But he was, I think, 94 at the time. I might be wrong about that, but he was old. And, I remember standing in the doorway as I parted from him and just said thank you to him. And, I realized I probably wouldn't see him again. And I did not. That was August of 2006, and he passed away shortly after that. But, it was a thrill to be able to talk to him, a thrill to interview him. My favorite moment in that interview, by the way, is when I asked him--I mentioned that a lot of the ideas in Capitalism and Freedom were still relevant, even though he'd written it in, I think 1962, when it had come out in 1962. And he said something like, 'Well, our ideas are timeless. They'll be true 10,000 years from now'--or 1,000 years from now--I don't remember what he said. But the part I remember is that he said, 'our' and I remember thinking, 'Yeah, yeah, we're with the same ideas.' Which we kind of do. But, part of the money conversation that was insane is--he was talking about the relationship between the money supply and nominal GDP [Gross Domestic Product], I think. You can go look it up in the episode. And, when I got home, I thought, 'How tight is that relationship?' And, I did some quick calculations, and I thought, 'Well, they're not really very closely related.' Maybe it was money and inflation. Maybe it was money and inflation. And, I wrote Milton. I challenged him afterwards and I said, 'You know, I'm not sure this is--I know you made this point on the air, but they're not that well correlated.' And, he writes back and he says, 'No, no, no, you're looking at the wrong measure of money.' I think I had used M2 or M1. He said, it should be M3 or M4--I can't remember. And, he sent me a spreadsheet and showed me that actually it was pretty correlated. And, I just got such a kick out of that, that this 90-plus-year-old man sent me a spreadsheet.
52:00	Russ Roberts: What else? Let me say a little bit about uncertainty and certainty. I did an episode with Robert Burton on that, where he tells this incredible story of this guy who is so convinced of his own narrative and so certain about it that he believed that someone had come into his office and switched desks. And when the other person said, 'Well, yeah, but the desk--or the table--has the exact same marks as the one that you had before.' He said, 'That's what's so creepy about it. They reproduced the desk exactly and swapped out this new one.' And, it was an example of how hard it is to give up on your narratives and the stories you feel. I have my own personal example that I want to share. I don't know if I've ever told this story, which is hard to believe since I think I've told every story I know on this program. But maybe not this one. Maybe I have. Anyway, my son--one of my sons--had a job; and it was his first day of work, in the summer. And I told him, 'You've got to get to work early. You've never been to this office before. You've never seen this person in face-to-face. You need to make sure you get there not just on time but early.' And, I think he was supposed to get there at nine o'clock, and it's 10-to-nine and he hasn't left yet. And, I said, 'You're going going to be late.' He said, 'It's only an eight minute ride.' And I'm thinking, 'Yeah, that only leaves you two minutes to find your way.' I'm really frustrated. And, I was going right near there myself, by car; and my wife drove me and dropped me off. And, as I'm getting out of the car at two minutes to nine, one minute to nine, I see my son on his bike going in the exact opposite direction from the office I know he's supposed to be at. And, he's clearly lost. And he's now going to definitely be late. And I see that, and I get out of the car, and I call his name at the top of my lungs to grab his attention and bring him back. And, he totally ignores me. Doesn't even turn to look at me. And, I'm going--I'm incredibly frustrated. He didn't take my advice to leave himself enough time. He's riding in the wrong direction. Just like I told him: I said, 'You could get lost.' And, I've called his name, and he hasn't even responded. And then, to make it worse, as I see him flash by--and this is all happening within a second and a half--I'm really annoyed because he's wearing someone else's backpack. And that's because it's not him. My mind has filled in the blanks and I've told myself a story. So, those kind of things, as I think interest me a lot--our ability to deceive ourselves. And then, related to these issues, are the challenges we have in decision-making. And, the episode I did with Agnes Callard, and then the one I did with L.A. Paul, both with the Burton book, and those of others, ended up leading to my last, most recent book, Wild Problems. And I'm so grateful for the way EconTalk lets me explore intellectual things, intellectual problems, questions, puzzles. And it's--what a wonderful thing that is. What else? Another thing I love learning is about intuition. I love the episode with Patrick House. Sometimes a single episode will change my way of thinking about something or the way I understand something. Patrick House says, talking about it--this comes out of his book, his book on consciousness--a great book. He says, 'Intuition is not in your gut. It's in your brain.' And his claim is--I don't know if you remember the story, but it's a great story about the young officer or young person in the army who is driving a fancy, high-ranking person in Iran--excuse me, in Iraq. I think it was Iraq. And, he's driving along between two towns and the road is a little bit dangerous. They both know that. And, all of a sudden the driver slams on the brakes, turns around, and goes back to the base they started at. They're almost--they're halfway. It's crazy, they're partway. And the big shot says, 'What are you doing?' He says, 'Well, I just don't have a good feeling.' And, the other guy's thinking, 'Well, what kind of thing is it to not have a good feeling? That's enough for you to turn?' That's your intuition, you have a bad feeling? Sounds like just paranoia. And, they get back to the base. And a couple hours later, the guy again asks the driver, 'Do you think you have a better idea of why you turned around?' And, he says, 'Yeah, I don't, but I have an idea of partly maybe kind of why, which is when I think back on it, there were no kids playing on the road that day. And, maybe my brain processed that fact and said, if the kids aren't playing on the road, maybe the moms know something about there's some danger here so they told their kids to stay inside. But I didn't think about that consciously.' His brain just said, 'Something's wrong.' That fascinated me. I am intrigued by this idea of intuition. I'm intrigued by this idea of how our experiences--House's idea is at the back of our brain is processing things without our conscious knowledge and it's an amazing thing. I think it's true. [More to come, 58:03]

Time

Podcast Episode Highlights

0:37

Intro. [Recording date: May 15, 2025.]

Russ Roberts: Today is May 15th, 2025. There is no guest today. This is a monologue. As far as I know, this is the 1000th episode of EconTalk. And, to mark that occasion, I thought I'd share some thoughts.

It's a little self-indulgent. I'm going to talk about some of the logistics and nuts and bolts of the podcast, which people have asked me about over the years, and I'm going to reflect on what this has been like to do this for almost 20 years, 1,000 times.

1:11

Russ Roberts: So, to do that--I started to do this. I made an outline of what I was going to talk about and then realized I wasn't excited about doing it, and I went home and told my wife that it had just kind of fell flat, just couldn't get any enthusiasm for the idea.

And she said, 'We should have had ChatGPT [Generative Pre-trained Transformer] ask you the questions.' And I thought, 'Well, that's a good idea.' So, I did that.

And so, this--I will occasionally repeat some of its questions or just answer them because that'll make sense. But, that was a fascinating experience in and of itself, and I may reflect on that along the way as we get started.

So, the first question--I love the way that it asked this question. This is the -03, by the way, of ChatGPT, which is really an extraordinary achievement. I've done, I think 20 episodes on AI [artificial intelligence], interviewing people about it, its threats, its potential, how it works; and I do think -03 is a step--a quantum leap--in improvement. And, we'll talk about that maybe at another time.

2:20

Russ Roberts: But here's the wording of the first question:

ChatGPT: What was the spark that convinced you to hit Record? And, what were your earliest ambitions for the show? And, it had said before: When you launched EconTalk back in 2006, podcasting was still a fringe medium; and long-term, long-form economics conversations sounded frankly like a gamble. So, what was the spark?

Russ Roberts: Well, I was late to blogging. I started Cafe Hayek with Don Boudreaux, and it has had a long run under Don's leadership. In the early days, I blogged alongside him; and I felt we had come late to blogging in whenever we started in 2004, whenever it was.

And so, I didn't want to be late to podcasting once I discovered it.

And, the way I discovered it was, as far as I know, James Reese, an economist, interviewed me on his podcast, Radio Economics. I don't think it exists anymore. Jim, if you're out there, say hello. Or if anybody knows about this, can remember this better than I can.

But, he called me up and interviewed me about--which is how we did interviews in those days, on the phone--he called me up and asked me to talk about Walmart. And at the end, or maybe it was beforehand, I said, 'How many people listen to this?' I mean, I'd never heard of a podcast. He said, 'Well, it's 2-to-3,000.'

And, when I heard that, I thought, 'Wow. If I could show up on Monday mornings and there were 3,000 people sitting in an auditorium with two chairs at the front of the room and I could go sit in one of them and a guest could be in the other one, I think I'd come to that room. And it would be fun to have 3,000 listeners.'

Now, at the time, I thought, 'Well--' And, the other reason I was interested was that I wanted to do a--I had considered for a while doing a radio show, a talk radio show, an interview program. And, I had done a lot of commentary at that point, I think for NPR [National Public Radio].

And, I thought maybe someday I could get an NPR talk show--maybe--and maybe I was interested. I didn't know if I could really want to do it. It seemed like a lot of work.

But, this seemed like a way to try it, and do, like ,a free trial to do podcasting and see if anybody listened. And, how hard was it?

So, in the early days, I think I started off just doing them occasionally. You can look at the archive. But shortly after that, I realized after starting, I realized that people expected to hear one on some kind of regular basis. Because otherwise they'd show up and it would be the same episode as it was up there before, and we wouldn't be making any progress.

So I was pretty quickly, pretty early on, I decided I would do one every week. And I kept to that schedule. I would take off the last week or two of the year for the holiday season, give myself a break, and then I realized: Well, people like it every week. So I think I'll just record one in advance. I can take off the holidays anyway.

And so, it turns out, according to artificial intelligence--I forget which one I looked at, I think it was ChatGPT--I have put out an episode of EconTalk for 854 consecutive Mondays. This will be 855 if all goes well. Or maybe it's a little more than that actually because it didn't know about the couple that are coming up.

But, December 2008 was the last time I missed a Monday. So, the first Monday of 2009, for the last 16 years, I have done one of these.

It's hard. I have a job now that's pretty demanding. I had a job before, but EconTalk was a non-trivial part of it. So, the chance to do this every week has been a lot--the privilege of doing it every week has gotten a lot harder--now that I'm president of Shalom College in Jerusalem. But I'm kind of addicted to it and I like to think some of you are as well.

So, we haven't missed a Monday in a long time. I worried during the war that we might miss--the war here since October 7th [Oct. 7, 2023]--I might miss one. We've managed to not do that. We've managed to keep them going. I will have a health issue inevitably, probably, someday while this program is still in my hands, and that's exciting. It's still in my hands, but someday it will have a challenge; and we'll maybe use an old episode to keep the streak going. But, for now, we've kept it going for 850-plus Mondays. Which is kind of cool.

7:15

Russ Roberts: The next question was:

ChatGPT: How did I think of this 3,000-person interview audience? Was it going to be a lecture, or a radio call and a fireside chat, or something else?

Russ Roberts: And, it's funny, when I started the program, for some reason I kind of thought it should be about an hour. I don't know why I thought that, but I soon found out that sometimes it's hard to keep it to an hour. But, I tried to, in the early days. I remember my dad saying, 'Oh, an hour? No one's going to listen for an hour.' I mean, it's 2006. He said, 'Radio pieces are, like NPR [National Public Radio] is eight minutes. That's long. No one will listen for an hour.' I didn't care.

The other thing that was fun in the early days is that people said, 'Well, you'll run out of gas because how many economists can you interview?' Of course, I found out quickly that there were people who weren't economists who were fun to talk to, and I had this brilliant idea that you could interview somebody more than once. Sometimes they had more than one hour's worth of interesting information.

So, obviously the program has changed a lot since the early days when it was pretty much all economists all the time. But, I'm now am happy to go over for an hour. And of course, since I started the podcast, there are podcasts that go for three and four hours. I've been a guest on some of those. They say, 'How long are we going to go for?' 'Oh, three or four hours.' I think I can't stand to listen to myself for barely more than an hour. I can't do that.

So, I've done a few longish ones. But on EconTalk, I think the longest episode we ever did was Davies on Extreme Economies, I think it's called. We'll put a link up to it. It's Richard Davies, and that was two hours and four minutes.

The Haviv Rettig Gur episode is about that long. It's two hours and four minutes--maybe a few seconds shorter than the Davies one--but they're both in the two-hour-and-four-minute length. That's a little long. But the goal now is I try to go a little over an hour and if it's still interesting, I go an hour and 15, or an hour and 20.

In the early days, the audience I had in mind were people interested in economics, and I was always thinking, 'How do I reach people who are interested in economics? Should I advertise in The Economist or the Wall Street Journal?' Of course, we never advertised anywhere in that normal way. But that's who I saw as my core audience.

And, in the back of my mind, I thought I was going to encourage people to understand free-market principles better. So, early episodes--especially with people that I didn't agree with--were more or less a debate.

And, if you go back to the early episodes, there's two things that bother me about them. One is that debate mindset. And the other is I talk too much.

So, if you go back to the beginning, as many people have--which blows me away--there are many people who tell me they start at the beginning or they've gone back to the beginning and they've listened to every single episode. Some of them more than once. But if you do that, don't be discouraged: They do get better.

But, I got interested--well, two things. One is I realized pretty quickly that my audience wasn't people interested in economics. It was people interested in learning something, which is why eventually we added the tagline, Conversations for the Curious. It was for curious people. People were looking for educational content that was somewhat a little bit entertaining. And that was my audience. That is my audience now.

And, it's a crazy thing. You're doing the dishes right now or you're walking your dog or you're working out at the gym and you want to grow or learn or have an interesting something to listen to. And, those are the people I think are my main audience, which is--hello, out there. It's nice to have you. So, that's the story there.

11:09

Russ Roberts: The next question actually at this point--it's kind of interesting. Just an AI aside: as I mentioned, I think the beginning of EconTalk was when I was interviewed by Jim Reese, James Reese on the show Radio Economics. In the new version of -03, if you watch while it's thinking, you can see its thoughts, whatever that means: you can see what it's looking for and what it's trying to discover. It kept coming back to that question of what was the first podcast I was on that got me interested in EconTalk? It didn't let it put it down. It couldn't put it down. Two or three or four different times that was what it started looking at when I asked it to continue and ask me another question. It was very obsessed with that.

And also, it refused to do what I asked it to do, which was to have a conversation back and forth. So, at this point, after I answered the question I just did, it then gave me a bunch of questions:

ChatGPT: How much with the mix of entertainment versus education, engineering or re-engineering the prep for when I wasn't doing as much debate? How do I get chemistry to work across the screen now that we're doing it on Zoom? Broadening the virtual hall: How did I get more downloads and people?

Russ Roberts: And, we now probably have something over, by the way, it was something like 100,000, maybe 150,000 listeners.

It's hard to define. Any one month has different numbers, and my actual total numbers of downloads are down for, I think two reasons. One, there are people who got angry that I did a bunch of episodes on Israel; and maybe we'll talk about that.

And also, Apple stopped automatically downloading episodes to people who, once they subscribe, they don't get every episode that comes out anymore. Now you have--if you don't listen to any of the episodes that have been downloaded, if you don't listen for a while, it stops automatically downloading. So, that hurt my numbers. Of course, that shows the numbers were somewhat distorted. Anyway, our listenership is something over 100,000, maybe 150,000.

Anyway, so to continue, the question is why did I stop doing the debate? And, a couple of reasons. I realized that if I yelled at people and debated them and challenged them constantly--people who disagreed with me--really[?] wouldn't be as interested in coming on the program. And that would mean I'd end up preaching to the choir. And I wasn't interested in that.

And I also came to believe--maybe just convincing myself because I'm biased--that debate isn't as good as a shared exploration. That's more like a conversation for discovering truth. If you rant and counter-rant, you're going to get eyeballs and downloads and hits, but I didn't think that would be good for my soul. I thought that would be bad for me. And, I also realized a gentler approach was just more pleasant.

I trusted my listeners. I didn't think you had to hear every counter-argument. People would say, 'How could you let so-and-so get away with saying that? Why didn't you answer them? Why did--' I thought, 'Well, that's your job. Your job out there is to when you hear something you think is a bad argument, to take note.'

And I also would say to people who complained about that: You know, if I answered everything I disagreed with and tried to refute it, we wouldn't get too many observations in the of course of the talk--of the interview. It would just kind of stagnate.

So, the bottom line is I tried to build what I would call respectful skepticism with people I didn't agree with. But, I saw my mission when I'm interviewing an author about a book they've written, to let them make the case for the book. To try to bring out the narrative arc of the book, or at least the parts that I thought were interesting or that I thought you, the listeners, would find interesting.

Now, I still challenge lots of things. I still raise questions about something an author would claim. But in general, I do not keep going back and forth and argue with them. So, it's not an argument. I challenge respectfully. That's sort of my way I think about it.

There are exceptions, even in the later years. Some people say things that are so shocking to me, I feel like I can't stay quiet. But, in general, I try to be let them have their say. I make it clear when appropriate that I do not agree and why. And then, you, the listener, can make the decision of which one makes sense to you.

My prep hasn't changed much in a long time. I script about 15 questions--maybe 12, maybe 18. I sometimes will have quotes from the book that I want to use as question generators or that I might read out loud to let you, the listener, try to understand what the book is about. But, I script about 15 questions that I know will get us enough material for the hour, or hour-plus.

Of course, I don't just go down the list. We digress. We go off into side-tangents. And, a lot of what is challenging about being the host--which, it wasn't clear to me until I actually had to do it--is you're doing a bunch of things at once. It's very hard to listen--because you're looking at the clock, you're trying to figure out how much time you have left, how much questions you have left, should you ask a follow-up question? Should you switch gears? Should you challenge?

And so, it's funny: many of you probably have a better idea of what I said or what the guest said than I do, because my attention is always being pulled in those different directions.

And, every once in a while--without naming names--I'll get a guest who is not very chatty or not very conversational or very taciturn in general or shy. And I realize early on that I'm in trouble. Fifteen or 20 questions are not going to be enough to fill the time. And you'll hear me even in later years talk more than I might normally do in those situations. So, if you notice that, that's what's going on there.

17:30

Russ Roberts: The next set of questions--again, ChatGPT wanted to ask me a bunch at once:

ChatGPT: How do I know when to bite my tongue? What about those questions? What about tangents? What about leaving economics and doing other things?

Russ Roberts: A whole bunch of others; there's a bunch more. But it came up with about 14 questions at that point, so I'm going to try to answer some of them.

So: When it comes to biting my tongue--that is, not responding to something--I don't remember particular moments. Sometimes I hesitate internally: I'm debating whether I should answer or not.

What else? Oh: Do I share the questions in advance? Never; almost never. I have guests who ask me to, but I always worry that if I do that it'll sound scripted and less spontaneous.

So, I will occasionally give them--when they're uneasy or nervous, I'll give them an overview of the topics we're going to talk about; but I don't give them the exact questions.

A handful of times I've said the first question to the guest because I want to get off on a good start. I don't want them to be all rambling and lost when they start.

And, I should also say that if you go back to the first episodes of the program, I am often fumbling around trying to get the conversation started. And, I realized pretty early on that that's when listeners leave the room: you switch channels, turn it off, go to find something else. So, I always script the opening question and read it verbatim.

But after that, often I'll improvise and go with the flow.

What else? Was there a conscious moment when I broadened the focus from economics?

I don't think so, but it was gradual.

It was pretty clear to me when--a couple of things were clear to me at various points. After the Financial Crisis of 2008, it was pretty clear to me that I had to understand it. And I knew I didn't. I knew almost nothing about finance. So, I did 20, 30 episodes to try to get tooled up on that. And, you came along for the ride. You heard those as well. And I figured you wanted to understand it as well as I did. And, as a result of that, I wrote a book Gambling with Other People's Money, trying to understand the incentives that may have contributed to the Financial Crisis. So, that was really a wonderful intellectual journey that I couldn't have done without the different guests that I did, that I interviewed in those days.

And then, starting around the rise of Trump in the mid-2010s--2015, 2016, it was also clear to me at that point that standard economics was not what people cared about at the moment, and I started trying to understand what was going on in America that led to Trump.

And by that I meant--and I've said this many times--I don't think of Trump as much as, until recently, I would say he was much more of an effect rather than a cause. Right now he's doing some causes, he's causing some things. It's a very different time. We may do a future episode on that, a follow-up to the one I did with Mike Munger on DOGE. But, the general broadening was the realization that economics, part of it was economics is too narrow to understand what's going on. This isn't just about 'the economy, stupid'; it's about other things.

And, the other part was that I found economics less interesting. I found economics less able to contribute to my understanding of the world. There were many, many other things I was interested in. And, every once in a while I reflect on the reality that while that is true--that I am a little tired of economics--it's also the case that a little economics goes a very long way in preventing bad reasoning.

So, even though I sometimes have become more skeptical of economics as a way of thinking, or I've softened my views on what is some of my dogmatism--I'll give you an example of that in a few minutes--even though I've softened my views on that, it really is useful to understand some of the basics.

22:00

Russ Roberts: But having said that, I have a joke that--I have listeners, I'm sure some of you are still out there who would love to have an episode on Bitcoin every week; or on monetary economics generally or some topic that you're passionate about. Which I respect. The problem is, is that I'm sure there are things I don't understand about Bitcoin, quite a few things, but I understand what I want to understand. I've kind of learned what I think I need to learn about Bitcoin.

Just like I'd learned what I needed to learn about the Financial Crisis. I'm sure there are things I don't understand about it. I'm sure there are other theories. But, many of those theories are just not interesting to me. And, maybe I'm wrong. Maybe I'm missing a chance to learn about some incredible theory of the Financial Crisis or some aspect of Bitcoin that's revolutionary that I'm neglecting. But, what I've done in those topics is I've done a bunch of interviews. Same with AI right now. I've done a bunch of interviews on AI. There are more things to learn, there are different perspectives, but I've learned a lot, and I hope you have, too; and it's time to move on to other topics.

I would say the same thing about Israel. I moved to Israel in 2021. I'm Jewish. You'd think I'd know a lot about the founding of the state and the Arab-Israeli crisis and what became the war in Gaza. But the fact is, I didn't know a lot about it when I moved here. I knew something about it. So, a lot of those episodes--and I don't know, we did 14 or so on Jewish history, Israeli history. And I tried to bring in voices from across the spectrum. I struggled to find Palestinian voices. I have some in the archive, but the truth is some Palestinians said they would be on the program and then we couldn't ever find a date. I tried a few times. It was clear for whatever reason, they either didn't want to be on the program or had bigger fish to fry. And most of them just never responded to my emails. For whatever reason. There's no point in speculating what the reason is.

I want you to know out there that I did try. But, even without those voices, I tried to get some variety in the perspectives on the Arab-Israeli relationship and on the history of the founding of the state and the post-state problems that Israel has had with its neighbors and October 7th and its aftermath and so on.

But a lot of people didn't like that. I've lost listeners who were angry I was too pro-Israel, which I'm sorry about that. I am pro-Israel, but I am eager to learn other things. I'm eager to understand the Palestinians' narrative; and I certainly understand that it's complicated, which of course is sort of the motto of the show. It's complicated.

24:56

Russ Roberts: ChatGPT asked:

ChatGPT: Are there moments that left me emotionally wrung out?

Russ Roberts: Sure. There were a couple episodes where people yelled at me, insulted me. I mostly kept my cool, I think. I try not to lose my cool. I would often get letters in those days, people saying, 'How'd you stay calm?'

And, they'll see me in person; and if I give a talk, if I'm giving a talk somewhere publicly and people come see me, they'll always often remark how different my persona is on stage giving my own talk versus as host of EconTalk. And, they'll say, 'Wow, you're so passionate or intense, but on EconTalk you're so calm.' And, I always say, 'Well, yeah, when I'm doing EconTalk, I'm wearing my EconTalk hat.'

And, my EconTalk hat, which is what I figuratively wear when I'm the host is--and you can get an EconTalk hat, by the way. EconTalk swag is available.

But I don't wear that hat when I'm podcasting. That EconTalk hat means: when I'm the host, I've got to stay calm. And, it took a while. You'll hear it: in the early days with people I don't agree with, I'd get worked up.

And it got to the point where I got less worked up, and I got calmer even when I was insulted, which--fantastic skill to have, I'm very happy to have it. It's not the case that I can always remember I'm wearing my EconTalk hat, because sometimes I'm not the host: I'm out in the world.

Anyway, the last few years, you know, they're less.

I want to say one other thing. At some point I realized that--the show, although listeners claim sometimes to want to hear me, they often would complain in the early days they wanted to hear the guest--more of the guests. And I'd say, 'Fine. Great.' And, I came to embrace that.

I try to give the guest more time than I might want to naturally grab.

And, again, I saw my goal in those days--and still today--that my job is to help you understand whether this book is worth reading. Is it valuable?

My ideal is to try to have an interview that's better than the book. I can't always do that. Some books are fabulous and I can't live up to that. And, some guests speak--don't speak as well as they write. So, the interview is not as exciting as the book. But sometimes it's better--in my mind at least. Which is very satisfying.

But, that's my goal, is to help you either learn the ideas that are in the book or the essay and maybe decide whether you want to buy it or not.

But, you might decide, 'I got enough out of this. I don't need to read it.' Or that it's not worth reading in your view. That's fine.

I always love it when people say, 'I didn't think I was going to like that episode, but it turned out it was really interesting.'

So, I do hope you can trust me. I try to read books that I and interview guests I find interesting, and I hope if you're a listener that you will feel the same way. We'll see.

Anyway, a lot of people say, which is--I can't tell you how gratifying it is--that my lack of combativeness in the face of disagreement is--they like that. You learn from that. And, I find that I'm so appreciative that that's the case for you. I love it. That was not the goal of the program, but it is, I'd say, the most important thing that I've accomplished with the show, which is to give people a mode of disagreement that's respectful.

And, I've tried to get better at that over time. I don't know if I am.

28:38

Russ Roberts: There's virtually no editing of the program. We edit out coughs, sneezes. I sometimes lose my train of thought. I'm doing one of these interviews at the end of a very long day and I have trouble keeping things on my mind, in my mind, in my head. And, I'll say, 'I lost my train of thought.' I'll try to regather myself. And, we edit that part out.

But otherwise, it's pretty much just the conversation.

One of the things that happened once a guest had insulted her profession, her colleagues in general--not a particular person. But she said something negative about her discipline, and she called me or emailed me afterwards and said, 'Can we cut that part out?' And I said, 'Maybe, well sure if you want, but let's see how bad it was.' So, I went back and listened to it. And I didn't think it was bad. So I said, 'I'll tell you what, I'll let you listen to it. I'll send you the raw file and if you don't like it, you can take it out.'

Once she heard it, she thought, 'Yeah, it's fine. You're right. No big deal.'

It's just an interesting phenomenon that when you look back on an interview or conversation, a lot of times you forget what actually happened and you get anxiety about it.

29:49

Russ Roberts: AI wanted to know:

ChatGPT: if I use any AI tools for prep other than this episode.

Russ Roberts: And the answer is: I don't. But, maybe that'll change going forward.

I do like to read the book. I would not like to interview a guest where I used AI to read the book in advance and generate the questions. It could happen under stress or time pressure. But in general, I try to read the whole book. Which I think is unusual.

And of course, that affects what kind of guests I can have. I don't want to read a book a week. But there are years you can go look where I'll do 20, 30 books. I think most years I do 20, 30 books a year. I try to pick books that I'm interested in, I'm going to read anyway ideally, or I want to read.

But, because of the time pressure reading the book, and that expectation I've set for myself, I try to mix in things with the books. And of course, some of those interviews are my favorites--they're probably yours--where I interview a practitioner about what their life is really like.

We've interviewed people about how potato chips are made, how a Broadway show gets done, what it's like to run a hair salon, what it's like to be a car sales person, what it's like to run a seafood restaurant chain. So, I love those. I hope you like them, too. I wouldn't mind doing more of them. They're fantastic. And, obviously they're less prep for me. I can talk to those people all day long. I don't have to read anything in advance.

But, in general, I try to read the book, if it's a book. And I try to read every word. But sometimes I lose interest in the book or I don't have time. And so, what I do is I read--the way I describe it is I read every page.

I'll scan a page, make sure I see the key agreements--excuse me, the key arguments--that the author is making. Because I don't want to misunderstand the point they're making or misinterpret something they're saying and then ask them a question that's messed up because it's not what they're saying at all.

So, I do try to read the whole book; but it's naturally the case sometimes that I realize, 'Gee, this book looks a lot more interesting when I started it.' And then, I tend to skim a little bit in the middle there or toward the end.

I don't choose guests that I don't respect. I only choose guests that I respect. So, when sometimes you'll write me and say, 'Why haven't you interviewed so-and-so?' Or, 'You should interview so-and-so.' And, by the way, if you ever want to find out if I've interviewed someone--a lot of times people will say, 'You should interview so-and-so.' And, I'll say, 'Your wish is my command.' And, I'll send them the interview. Necause I've already done it. And you just missed it. Or, you didn't know how to look it up. We have an archive at econtalk.org. We have an archive at russroberts.info, which is my personal website.

But, the easiest way to find out if we've ever interviewed anyone, so if you want to know, did I ever interview Milton Friedman? You just put EconTalk Milton Friedman and it pops up. It's always the first one. Or Ronald Coase. Milton Friedman. To my great delight, I was able to interview Ronald Coase, and he was the oldest guest I've ever interviewed. I think he was 102 or 104, I can't remember.

But that's the easiest way to find out.

But, anyway, someone will suggest a guest I haven't interviewed. And they'll say, 'You should interview so-and-so.' And, I'll think, 'Well, it would be lively, but I don't respect so-and-so.' So, if I interview that person, it's going to be embarrassing. I'm not going to do a good job. It's not going to go well.

So, the bottom line--and sometimes I'm wrong, of course: I shouldn't respect someone. But most of the time, almost always, the people I've invited are not--they're people I respect.

It's one of the reasons though I don't generally--I don't think I've ever broken this rule: I don't interview politicians because I'm interested in the truth. They're obviously selling. Of course, academics aren't always interested in the truth either, so it's hit or miss with them, too.

I was asked: Could there be an episode 2,000? It's unlikely. I'm 70 years old. I don't think I'll be doing this when I'm 87 or 90, but I'd like to do it for a while. I can't tell you how intellectually alive EconTalk keeps me. I have learned so many things and gotten so excited about so many things.

Just a silly example: As you know, my granddaughter loves owls, and I thought, 'You know what? I should learn something about owls to keep her engaged with that.' I realized I don't know anything about them. So, what did I do? I found a book on owls and I read it, and then I interviewed the author Jennifer Ackerman. And that's a blast. That's incredibly fun.

Or: I don't know much about the pharmaceutical industry and I interview a zillion people. And I get smarter. And I hope that works for you too, because that's definitely what I'm trying to do here. Okay?

35:08

Russ Roberts: So next: As I said, once I feel like I've learned enough about something, I'll put it down. Right now, that's the case for AI--so I'm not going to do another episode for a bit, probably. But on the other hand, it's changing so quickly; that'll change, too, and maybe I do a bunch soon. Maybe it'll be different worries that I think people have that come to light. It's changing. So I'm going to spend more time with it and learn about it. And maybe something else--other issues will come up.

Some topics are endlessly interesting to me, as you probably know. Epistemology--that is, how do we know what we know--is endlessly interesting to me. Healthcare, for example, what works and doesn't work. The complexity involved in the human body always fascinates me, and you can see some evolution in my thought as time passes on the issue of healthcare. I'm pretty free-market on healthcare. That is, I think the current system in the United States, for example, is not very effective. It's very expensive. I think it's pretty high quality for the people who have good access to it, but not everybody has good access to it. And that means, because it's highly subsidized--which is not a free-market thing--those who don't have access pay through insurance or government programs pay an enormous premium. The only point I'll make there, as I've said many times on the program, out-of-pocket costs of that program have--excuse me, out-of-pocket spending by healthcare consumers has fallen dramatically over time. And, that means that when you're getting healthcare in America, you're not spending your own money. That pushes up your desire for healthcare: You're spending somebody else's money. And that has an important effect. So, that'd be one example.

But, the other example I want to give, which I think is more about the challenges of avoiding bias: I used to be a defender of the pharmaceutical industry. I still am when appropriate, but when we think about, say, price controls on pharmaceuticals or changing property rights around pharmaceuticals, I'd always say, 'Well, if you do that, it's going to come at a big cost. You're going to have less innovation.' And that's true, of course. But, what I didn't understand and I came to understand, for example, after listening to Robin Feldman's episode on pharmaceutical pricing, is the creativity of the pharmaceutical industry in playing with intellectual property laws to keep competition from generics at a minimum.

So, the monopoly power of a patented pharmaceutical gets extended beyond the letter of the law. Sometimes it's shorter than the letter of the law because of time it takes for approval and so on, so I do understand that. But my point is, is that economists often have a knee-jerk reaction: Well, government intervention there is going to--well, the healthcare system is not free market, not close to free market. The intellectual property rights around pharmaceuticals are incredibly complicated, and a lot of times economists have stylized stories to tell about those things that I think are overly simplified. And so, that was a chance of growth. That was growth for me to appreciate that.

What else did I want to say here? I think I made it clear: I'm not that interested in monetary economics anymore. I thought I understood it when I was younger, when I was training at the University of Chicago. It was very powerful; and now I'm more skeptical of its reliability as a way of fully understanding everything.

I think macroeconomics is really complicated. I've become much more of a Hayekian than a Friedmanian monetarist. When I say Hayekian, I mean in the Hayekian of the Nobel Prize address, "The Pretence of Knowledge." The "Pretence of Knowledge," fabulous essay, fabulous speech he gave when Hayek won the Nobel Prize. It basically expressed a skepticism about our ability to have a full understanding or a useful understanding of the complex system called the macroeconomy.

As you may know, I am increasingly interested in talking to creative people. I love my interviews with the photographer, Jessica Todd Harper; Sabin Howard, the sculptor; the novelists and poets I've interviewed: Dwayne Betts, Dana Gioia, Amor Towles, and Mark Helprin. Those are exhilarating for me. They're fun for me.

39:56

Russ Roberts: I was asked: Have I ever listened to an episode, relistened, and been surprised by what I said?

As I mentioned before, a lot of times I'm not listening, so I do miss stuff because I'm thinking about other things to get the episode going.

I wish I was better at putting guests at ease. It's quite a challenge over Zoom. A lot of people would assume that if I do something face-to-face, it's going to be more intimate--and more, it'll be a better conversation. That's not true. Some people are very uncomfortable being in the room with a stranger for the first time and trying to be interviewed. So, Zoom actually is good for some people, that distance that it provides.

In my recent episode with Dwarkesh Patel, we talked about that. I think it's a real art to put people at ease. My favorite episodes, many of them are where I feel I've made a friend. A lot of that's been in recent years. In the early days, I loved EconTalk because I always learned something. I still do sometimes, obviously. But once I changed the tone and made it more of a conversation and less of a debate, I got better at connecting to the guests on a human level; and it's special. I won't name names, but there are many, many guests I've had in the last, say, 10 years where I realized it'd be great to see them for a drink or socially if they ever came to Jerusalem or if I was ever in their city. Those are very precious to me. There were a handful of episodes where once the recording stopped, we shared things that were personal that we didn't want to record, that were really powerful. Those are really magical for me. Other guests, they're just friends in my mind. Maybe I'm a friend in their mind. We had a special connection. Maybe another time we'll reconnect in person.

And, I should just mention in passing that our relationship--mine with you, the listener--is of course very asymmetric. You've listened to me for thousands of hours. I may have received an email from you. So, you know about my granddaughter. You know about my quirks, my parents, my weird habits about eating. I've shared all kinds of things over the years about that. But I know nothing about you, so I'm kind of your friend, but you're less my friend--which is just the nature of modern digital life.

What else did I want to say here? I'll just say something about conversation rather than debate, also. I like to think our brains are wired to hear conversation and learn from it. It's certainly true for most human history: That's all there was. There weren't any books, there was no reading, there was nothing else except people talking to each other. And there's no video. It wouldn't be surprising if our brains had an architecture that was designed to take in information and discover information through exploratory conversation or listening. So, I love that.

And so, even though one of the deepest things I've ever learned is from Adam Mastroianni that the brain is not connected to the ears--and therefore what we hear in a lecture doesn't always go in, and sometimes we need experience to learn lessons--I like to think that conversation is different. And, you listening to conversation, is different than just being told something.

So for example, one of the nicest things you say to me sometimes as listeners is, 'You asked the question I was going to ask.' So, that's cool, because what that means is that your brain is running alongside mine and we're learning together from the guest and processing it in a similar way. At least I like to think so.

Another big thing I learned from being the host, of course, which we've talked about before on the program, is when I realized that both sides of most ideological debates have lots of facts on their side and lots of studies. And, that was the beginning of my, I think what the fancy name is, epistemological humility. That is: I'm not always confident that what I think is true, is true.

And, along the way, I became highly skeptical of the power of econometrics, data analysis of the kind that economists and other social scientists do. You'll find that theme running back through the program starting, I don't know, 2010 maybe, I'm not sure. But, I realized that the people on my side, their facts and truths were maybe not true. They maybe weren't any more reliable. Their facts could be true; but the other side of facts, also. And so, you're stuck with logic and other ways.

I've written a lot on this. Maybe we'll put up something about it. I mean, it's a bit discouraging to think that you can't use data and statistics to prove things. I always add: That doesn't mean they're irrelevant. It doesn't mean data doesn't matter, facts don't matter. It's just that the ability to tease out, say, causation in a complex world is, I think, very challenging. And, I think the replication crisis that we've had a couple episodes on is a good example of that.

45:10

Russ Roberts: What are some of my favorite episodes that I remember vividly?

Well, Christopher Hitchens would be one of them. Christopher Hitchens was visiting the Hoover Institution. I was there for the summer; and I realized he was in town and was at Hoover. And I got ahold of him--like, it was probably on a Wednesday--and I asked him if he'd like to do an EconTalk episode. I needed an episode for Monday. So, he said, 'Yes.' I said, 'Let's talk about Orwell.' And then I ran to a bookstore on University Ave.--I forget the name of what it was right now. It might've been a Borders that used to exist. And they had one book by Hitchens: They had his book on Orwell. And, the book is called, I think, Why Orwell Matters. So, I asked Hitchens if that's what we could talk about, and he said, 'Sure.'

So he said, 'Come to my house.' So, he was staying at someone's house; and it was large and sprawling. And he told me to bring lunch. I got there around noon, and we sat out at the pool that was at the house, and we ate sandwiches. And, I'm pretty sure we had a scotch, and I'm ashamed I don't remember what brand it was, but I'm sure there's some Hitchens fans out there who will know.

But we had a scotch; we're out by the pool; and now I've got to interview him. And you'll go back and listen to it: our audio quality wasn't as good in those days. This was obviously live and face-to-face. And, we were recording this and there were workmen working on the house, and they would constantly come into the living room where we were recording and interrupt us. I was there till, I don't know, three or four o'clock. I was there for hours.

But, it's one of my favorite interviews because the one question I was wise enough to ask him was if he saw himself as an Orwellian figure--a man who stood up for his principles and paid a price in lost friendship. Because Orwell, famously, after the Spanish Civil War, soured on communism. And a lot of his communist friends hated him for that, and probably I think, stopped talking to him. And maybe he had personal danger. And, Hitchens had been a supporter of the war in Iraq, and he lost a lot of friends and supporters. So, I asked him if he saw that as a parallel. And it's one of my favorite moments of the program.

He said, 'Absolutely not. We're nothing alike.' What Orwell had to endure for what he said and stood up for is nothing compared to what, he, Hitchens had to endure.

So, that was very moving to me. And you can listen to that in the interview.

I have very powerful memories of interviewing Milton Friedman in 2006. Now, I never had Milton for a class for credit. I had him for a non-credit class. My first year at Chicago was his last year before he went out to Stanford and the Hoover Institution. But, I sat in on that class. Many of us first year students did. We wanted to learn from him. And that class was only one thing: It was Milton standing in the front of the room and answering questions, anything we asked him: we could ask him anything we'd want. We'd often ask him questions off the Core Exam--the exam that we'd be taking at the end of the year--to see if he could answer them. And, he couldn't always, which was really great. It made us feel good.

Anyway, Milton was always nice to me after that because--it's a long story, not worth going into. But, the bottom line is I knew him beyond that. I had interacted with him about my first book, and he gave me a blurb for it. And, once I started the podcast, I thought, 'Boy, it'd be great to have Milton Friedman on EconTalk.'

So, I showed up at his apartment in downtown San Francisco, a gorgeous high floor overlooking the city with at least two, if not three views, views in two or three different directions. It was absolutely magnificent. And, we sat in his study, and I put a microphone on him and clipped on his lapel; and I had one on my lapel. And we talked for--I don't remember how long.

We divided it into two parts. One is on money--meaning the monetary history of the United States and his views on monetary policy and monetary economics. And the second was on his book, Capitalism and Freedom. And, they're pretty good interviews. I talk way too much--I'm ashamed. I wish I'd talked less. But he was, I think, 94 at the time. I might be wrong about that, but he was old. And, I remember standing in the doorway as I parted from him and just said thank you to him. And, I realized I probably wouldn't see him again. And I did not. That was August of 2006, and he passed away shortly after that. But, it was a thrill to be able to talk to him, a thrill to interview him.

My favorite moment in that interview, by the way, is when I asked him--I mentioned that a lot of the ideas in Capitalism and Freedom were still relevant, even though he'd written it in, I think 1962, when it had come out in 1962. And he said something like, 'Well, our ideas are timeless. They'll be true 10,000 years from now'--or 1,000 years from now--I don't remember what he said. But the part I remember is that he said, 'our' and I remember thinking, 'Yeah, yeah, we're with the same ideas.' Which we kind of do.

But, part of the money conversation that was insane is--he was talking about the relationship between the money supply and nominal GDP [Gross Domestic Product], I think. You can go look it up in the episode. And, when I got home, I thought, 'How tight is that relationship?' And, I did some quick calculations, and I thought, 'Well, they're not really very closely related.' Maybe it was money and inflation. Maybe it was money and inflation. And, I wrote Milton. I challenged him afterwards and I said, 'You know, I'm not sure this is--I know you made this point on the air, but they're not that well correlated.' And, he writes back and he says, 'No, no, no, you're looking at the wrong measure of money.' I think I had used M2 or M1. He said, it should be M3 or M4--I can't remember. And, he sent me a spreadsheet and showed me that actually it was pretty correlated.

And, I just got such a kick out of that, that this 90-plus-year-old man sent me a spreadsheet.

52:00

Russ Roberts: What else? Let me say a little bit about uncertainty and certainty.

I did an episode with Robert Burton on that, where he tells this incredible story of this guy who is so convinced of his own narrative and so certain about it that he believed that someone had come into his office and switched desks. And when the other person said, 'Well, yeah, but the desk--or the table--has the exact same marks as the one that you had before.' He said, 'That's what's so creepy about it. They reproduced the desk exactly and swapped out this new one.'

And, it was an example of how hard it is to give up on your narratives and the stories you feel.

I have my own personal example that I want to share. I don't know if I've ever told this story, which is hard to believe since I think I've told every story I know on this program. But maybe not this one. Maybe I have. Anyway, my son--one of my sons--had a job; and it was his first day of work, in the summer. And I told him, 'You've got to get to work early. You've never been to this office before. You've never seen this person in face-to-face. You need to make sure you get there not just on time but early.' And, I think he was supposed to get there at nine o'clock, and it's 10-to-nine and he hasn't left yet. And, I said, 'You're going going to be late.' He said, 'It's only an eight minute ride.'

And I'm thinking, 'Yeah, that only leaves you two minutes to find your way.'

I'm really frustrated. And, I was going right near there myself, by car; and my wife drove me and dropped me off. And, as I'm getting out of the car at two minutes to nine, one minute to nine, I see my son on his bike going in the exact opposite direction from the office I know he's supposed to be at. And, he's clearly lost. And he's now going to definitely be late.

And I see that, and I get out of the car, and I call his name at the top of my lungs to grab his attention and bring him back. And, he totally ignores me. Doesn't even turn to look at me.

And, I'm going--I'm incredibly frustrated. He didn't take my advice to leave himself enough time. He's riding in the wrong direction. Just like I told him: I said, 'You could get lost.' And, I've called his name, and he hasn't even responded.

And then, to make it worse, as I see him flash by--and this is all happening within a second and a half--I'm really annoyed because he's wearing someone else's backpack.

And that's because it's not him.

My mind has filled in the blanks and I've told myself a story.

So, those kind of things, as I think interest me a lot--our ability to deceive ourselves.

And then, related to these issues, are the challenges we have in decision-making. And, the episode I did with Agnes Callard, and then the one I did with L.A. Paul, both with the Burton book, and those of others, ended up leading to my last, most recent book, Wild Problems. And I'm so grateful for the way EconTalk lets me explore intellectual things, intellectual problems, questions, puzzles. And it's--what a wonderful thing that is.

What else? Another thing I love learning is about intuition. I love the episode with Patrick House. Sometimes a single episode will change my way of thinking about something or the way I understand something. Patrick House says, talking about it--this comes out of his book, his book on consciousness--a great book. He says, 'Intuition is not in your gut. It's in your brain.'

And his claim is--I don't know if you remember the story, but it's a great story about the young officer or young person in the army who is driving a fancy, high-ranking person in Iran--excuse me, in Iraq. I think it was Iraq. And, he's driving along between two towns and the road is a little bit dangerous. They both know that. And, all of a sudden the driver slams on the brakes, turns around, and goes back to the base they started at. They're almost--they're halfway. It's crazy, they're partway. And the big shot says, 'What are you doing?' He says, 'Well, I just don't have a good feeling.'

And, the other guy's thinking, 'Well, what kind of thing is it to not have a good feeling? That's enough for you to turn?' That's your intuition, you have a bad feeling? Sounds like just paranoia.

And, they get back to the base. And a couple hours later, the guy again asks the driver, 'Do you think you have a better idea of why you turned around?' And, he says, 'Yeah, I don't, but I have an idea of partly maybe kind of why, which is when I think back on it, there were no kids playing on the road that day. And, maybe my brain processed that fact and said, if the kids aren't playing on the road, maybe the moms know something about there's some danger here so they told their kids to stay inside. But I didn't think about that consciously.' His brain just said, 'Something's wrong.'

That fascinated me. I am intrigued by this idea of intuition. I'm intrigued by this idea of how our experiences--House's idea is at the back of our brain is processing things without our conscious knowledge and it's an amazing thing. I think it's true. [More to come, 58:03]

EconTalk #1000 (with Russ Roberts)

Michael Munger on EconTalk's 500th Episode

Don Cox on the Economics of Parenting

READER COMMENTS

Krishnan Chittur

Jun 2 2025 at 8:38am

Mark

Jun 2 2025 at 9:02am

Mark Sundstrom

Jun 2 2025 at 10:52am

Hunter McDaniel

Jun 2 2025 at 11:35am

Peter Ruble

Jun 2 2025 at 12:26pm

Leah Klint

Jun 2 2025 at 1:06pm

Todd Kreider

Jun 2 2025 at 1:07pm

Joseph

Jun 2 2025 at 3:05pm

Ben Lau

Jun 2 2025 at 6:14pm

Sluggh McGee

Jun 3 2025 at 12:13am

Shalom Freedman

Jun 3 2025 at 11:37am

Tom Gregorich

Jun 3 2025 at 1:49pm

Mark

Jun 3 2025 at 3:50pm

LEAVE A COMMENT

EconTalk #1000 (with Russ Roberts)

Michael Munger on EconTalk's 500th Episode

Don Cox on the Economics of Parenting

READER COMMENTS

Krishnan Chittur

Jun 2 2025 at 8:38am

Mark

Jun 2 2025 at 9:02am

Mark Sundstrom

Jun 2 2025 at 10:52am

Hunter McDaniel

Jun 2 2025 at 11:35am

Peter Ruble

Jun 2 2025 at 12:26pm

Leah Klint

Jun 2 2025 at 1:06pm

Todd Kreider

Jun 2 2025 at 1:07pm

Joseph

Jun 2 2025 at 3:05pm

Ben Lau

Jun 2 2025 at 6:14pm

Sluggh McGee

Jun 3 2025 at 12:13am

Shalom Freedman

Jun 3 2025 at 11:37am

Tom Gregorich

Jun 3 2025 at 1:49pm

Mark

Jun 3 2025 at 3:50pm

LEAVE A COMMENT

Enter your email address to subscribe to our monthly newsletter: