Prozac and ChatGPT: How Technology is Changing the Way We See Ourselves - Ep. 15 with Peter D. Kramer

[00:00] So first of all, antidepressants work. They're not glorified placebos. Yes, I think we are in a sort of low ebb for the cultural view of antidepressants. - There are probably some people who are like, has Dan gone crazy? Like, what does this have to do with ChatGPT? It's about how technology change how we see ourselves and the world. - I feel like ChatGPT is afraid that he or she is gonna get sued. [00:26] It is remarkable to have something [00:30] in this way. This is really impressive compared to anything from a few years ago. [00:46] Peter, welcome to the show. [00:48] Thank you. Bye. [00:49] I am so excited to have you because you are one of my favorite authors. You wrote a book that like literally changed my life. [00:57] I have it right here. If you can see, there's like, [01:00] So many little dog years on the in this book, like I read it like four times. It's incredible. I love that. [01:07] So for people who don't know you, you are a psychiatrist. You're also a writer. You're the author of the book that I just held up, Listening to Prozac, which you wrote 30 years ago, but you're also the author of many other books like Overcoming Depression. You wrote a book about Freud, which I also read, which I really enjoyed. And you're also a novelist. Remind me again of the title of your most recent novel. [01:29] Death of the Great Man. Death of the Great Man, which is sort of, it feels like you're talking a little bit about a psychiatrist's interaction with someone who's kind of like Donald Trump, but you haven't really said that. Yes, a psychiatrist is coerced into treating a...

[01:46] authoritarian buffoonish uh autocratic national leader in his disastrous second term well let's hope it doesn't come true and uh it's sort of like sopranos-esque but uh the president instead of a mob boss maybe um so i love that i love how sort of multidisciplinary you are um [02:08] You know, like one of the things that about psychiatry, in my experiences with psychiatry, which we can get into in a second, is psychiatrists often are like, they're sort of like brain, like mad brain scientists or whatever. And they just sort of like give you magic chemicals that, that in my experience that they're like, oh, they don't know how it works. We don't know how it works, but like, it might make you feel better, but it makes you feel worse than in the [02:36] interested in humans and like the human experience and stuff like that. And I think it's like such a shame in the in the field because like there's that divide and you seem to just be in this like really nice like both very humanistic, very interested in human experience and into the into the brain chemicals thing that that I really love. [02:58] Yeah, so I came to psychiatry via, I suppose, my experience as a patient. I was in a very [03:06] successful, I think, anyway, very compelling psychoanalysis in London in the early 1970s and decided then to become a doctor in order to become a psychiatrist and had some other

[03:24] therapy is good and bad, but became really a student of psychotherapy. In that time in London, I read a lot of Freud and some of the other kind of founding psychoanalysts. And then in medical school, became interested in a range of psychotherapies. The early 70s was a time of the flowering of psychotherapies. There were some related to family and some to social justice and [03:54] third book wrote about should you leave. But [03:57] So so when Prozac appeared, I was really someone focused with my patients on psychotherapy and. [04:06] seeing their responses. Now, there's a 30th, I should run and hold it up, I suppose, but there's a 30th anniversary edition of Listening to Prozac that's out just the end of last year. And in it, I got to write a new preface and afterwards about what held up and didn't hold up. But I also write about how I came to write the book. And I used to keep these yellow sheets of paper for easy identification and patients' charts where I wrote down the medicines and doses [04:36] And I wasn't prescribing for most patients, but also their responses. If there were side effects and things and those, you know, the notes on those yellow sheets started looking with Prozac like my. [04:47] regular psychotherapy sheets, people were talking about sort of neurotic symptoms that had been muted and I started

[04:54] Yeah. [04:54] having a thought that the medication was acting like a co-therapist, that it was doing some of the psychotherapy. So that's really, [05:02] in a way, the origin of the book. [05:03] Yeah, that makes sense. And I should, I should, I think I like dove right in right off the deep end into like psychotherapy, psychiatry stuff. And I should actually probably introduce for the people who are listening and watching why you're on the show at all. Because I think there are probably some people who are like, has Dan gone crazy? Like, what does this have to do with chat UBT? And the answer is, I'm not as crazy as I used to be. Thank you to some of the medications that you, you talk about in your book. [05:33] this book and I'll tell people like a little bit about about the book and a little bit about like sort of the theme. But the theme of the book is it's about how technology in this case, Prozac, or the larger class of drugs we call antidepressants changes how change how we see ourselves and the world. And I think you sort of set out to write what you call this like resonant portrait where you're looking at how technology changes people, changes culture, changes, changes the way that [06:03] And there's a sort of important tradition of people doing that. So another person that you've brought up before is someone like Tracy Kidder, who did the same thing with the PC Revolution. [06:13] So it's not just about like, obviously, antidepressants change how we see ourselves in a certain like more obvious way where maybe it blunts at negative emotions or negative affect. But I think one of your points is that technology in general can do that. And I see that with ChatGPT. I've been sort of.

[06:33] writing about that and thinking about about that inspired in large part by your work that I think [06:39] also has impacts on on how we how we see ourselves um [06:43] And so what I want to do in this show is talk about your book because I think it's just really important. [06:49] um talk about antidepressants because i think that people don't talk about them enough in the right way [06:55] in public. [06:58] I think your book does it really well, and I'm happy to share sort of my experience with them. And then I want to take sort of like some of the lessons or some of the things that you pull out of the things that you notice about how Prozac and other antidepressants change, how we see ourselves change the human experience, and apply them to ChatGPT. Because I think that there are some like really interesting parallels. And then we're just going to explore ChatGPT together, and we have a fun idea for how to do that. [07:28] Thank you. [07:28] of the show and why you're on the show. And, and I'll pause there. It sounds like you might have something to say. No, I really appreciate that summary because this book was exactly about a certain moment in contemporary time, modern time 30 years ago, and how I thought our sense of self was going to change. And I was really interested in writing fiction. I chose my editor because she [07:55] had edited fiction I had based on the outline of the book. I had a choice of a few publishing houses and I looked then at nonfiction for models, how I would write nonfiction that had some of the flavor of fiction. And that Tracy Kidder book about the birth of a new machine seemed to me have that quality of focusing on a little

[08:18] change in technology and how it gives you a sense of what's going on in the wider culture. And oddly, Verlin Klinkenberg's book about [08:26] using historical means of making hay and changes in how hay is made. And John McPhee's about making orange juice. I mean, it wasn't all high technology, just, you know, I think that there are lots of technologies that really changed the environment. And I thought, you know, I had hold of one. And my patients said that. So before I wrote a book, I was writing a monthly column for a psychiatrist [08:56] I was saying to my colleagues, you're seeing what I'm seeing as these new antidepressants came into use. And one of the things. [09:05] was that my patients said things like I'm myself at last. And I thought, really, you you would never become yourself if this medicine hadn't been invented or they. [09:17] thought that some aspects of themselves that they thought arose from their history their psychological history how obsessed they were with this and that uh that those aspects just became muted as you say on the medicine they were less obsessed with whatever it was and it seemed that that had been kind of a biological glitch rather than uh you know a developmental [09:41] theme. And I thought, oh, we should think about how that might be happening. Yeah. Yeah. I think that's the interesting, that's one of the most striking things about your book is like when people think about antidepressants, one is maybe they don't really even know what they do, but they're like, I guess generally they like help with depression or generally they help with like all the whole range of psychological issues that people tend to have, like depression, anxiety, OCD. Yeah.

[10:06] which I have. [10:08] All of that stuff they tend to help with. And I think one of the points that I took away from your book is like, yeah, like to some degree, like they do operate directly on something like depression. Maybe they do curb negative affect or if you're feeling really depressed or feeling really anxious, like those things will be blunted a little bit. But they also, and this is something that like almost nobody knows, despite how popular your book was, they work directly on personality. [10:35] Um, and so what, what they may do is they may, um, like tweak some of these, some of these things about people's personality. Like you'll be a little bit bolder. [10:44] you'll be a little bit less sensitive to rejection. You may obsess a little bit less. And one of the interesting things about your book is that it doesn't deal with people who are super, super, super sick, who become like start to be able to function normally. You often focus on people who [11:04] definitely have problems, but they're fairly mild. And when they take... [11:09] Prozac or Lexapro or Zoloft or any one of these antidepressants. [11:14] They become what you called better than well. They actually like become the issue resolves, but they also become like better versions of themselves. And you have this like really striking anecdote at the beginning of the beginning of the book, which you already referred to, which is like you might put a patient on Prozac for a while to resolve a depressive episode. [11:36] And they'll become bolder, they'll become less sensitive to rejection, all that kind of stuff.

[11:42] Markit changes in their lives and when you taper them off, they come back to you and they're like, well, I'm not myself anymore. And even though they're not depressed. And so the question, the question that you pose is like, well, what is a self to begin with? Like you weren't yourself for the first 30 years of your life before I put you on this drug. But it, but. [12:00] the drug just brought out this other [12:03] Other people, [12:04] thing from you that was maybe always latent or always there, but it needed to turn those dials to let it come out. Right. I think it brings up the question of the natural. So if you [12:16] were subject to migraines and really they were [12:20] untreatable. You just were living the whole of your life with pain in your head and it was affecting you and your job and your relationship to other people. Pain was constantly intruding and then [12:35] you took a medicine that finally prevented migraine, one was invented, we would say, yes, you were yourself at last. We would agree that the migraine was some kind of an external thing imposed on you. Depression is culturally much more complicated. So there's a long history, I write about this in a book called Against Depression, a long history of romanticizing melancholy that goes back certainly to the Renaissance, probably before, but is very [13:05] and colics are thought to have some special insight into the human condition. So taking that away, you know, isn't as automatically restorative as taking away a migraine, but maybe it should be, right? I mean, maybe depression has some of that same illness quality to it. And even in these very minor situations,

[13:25] forms, sort of sub forms. Maybe that really isn't who you are. So I but I play with that both ways. I mean, the book begins with what patients said to me, and that was what they said. The better than well comes from a patient saying, you know, I didn't just get over that episode of depression or obsessionality. I'm really. [13:47] able to function in the dating marketplace better. I'm less easy to push around and I'm more certain about what I'm looking for. Totally. Yeah. And I will say for myself, I have experienced that. And yeah, it's been a crazy change for me. I think one of the things I should point out, which you sort of alluded to, is that one of the things I love about the book is it sort of came [14:17] high watermark of antidepressant optimism where everyone was like, well, maybe it'll cure everything. And then I feel like right now we're in this like low of like, it's been probably overprescribed to people who like, aren't, aren't, haven't, you know, been properly educated or aren't in psychotherapy or whatever. And, and so I think there's a lot of people out there who are like, oh, maybe it doesn't work. Maybe it's a placebo. And like, it's definitely, it's not a placebo. [14:47] of the things I love about the book is that, um, [14:50] is you're kind of ambivalent about it in the sort of classical sense of ambivalence where you're like...

[14:57] you're presenting the case, but you're like, [14:59] And there's some good things about this. It really does amazing things for people, but it's also not all good. And we shouldn't be like too glib about like jumping into changing all aspects of our personality in particular, because like you said, you know, melancholy, it's that sort of a cultural thing, like whether or not melancholy is acceptable. And I'll say for myself, like having OCD, I was... [15:22] I was watching and my history is like, I'm from, I'm Jewish and my, my family's from like Eastern Europe and there were, there were definitely like very Orthodox Jews. And like, I was watching a YouTube video the other day of like how an Orthodox Jew conducts their day. And like, it's pretty obsessive, you know, like you're saying blessings about everything. You're like, you're, you're touching, you're touching the mezuzah, you're, you're, you're rubbing the seat seat or whatever. [15:52] sense of morality. And that's one of my sort of obsessive things. It's like this sense of morals. And like, if your ancestors studied Talmud all day, you might be obsessive too, but I'm not in that culture anymore. And so those features were like not particularly adaptive to me. And so I think one of the points of your book is that we can turn that down so that it's, I'm more fit to the culture, but then you're, you always have to ask me, is that right? Like, should I, [16:21] need to do that and that's that's an open question yes i you know yes to about seven things so first of all antidepressants work they're not glorified placebos i wrote another book called ordinarily well about how antidepressants work and what the evidence is and yes i think we are in a sort of low ebb for the cultural view of antidepressants and in that new introduction to listening to

[16:51] Borges story, Pierre Menard, author of the Quixote. So [16:57] uh, [16:59] Borges imagines an author made up author, Pierre Menard, who writes one and a half chapters of the novel Don Quixote in the 1910s. All right. So we're in World War One. [17:14] and you know, war is horrible. And in the Quixote in the chapters, Cervantes is glorifying war and [17:26] uh borges says how much more brilliant menard's version is than quixote's version because the same words are written in a very different cultural surround and is it ironic and uh you know how is he making us think about war i mean it's a very clever uh metaphor trope and i thought what because i was asked by penguin to do a 30th anniversary edition actually afterward what would [17:56] uh in 2023 when we're so negative about antidepressants and I don't know that that would be you know brilliant or not brilliant but it you it would definitely be going against the grain um whereas I think in uh the 19 late 1980s early 1990s I was writing this book there was a lot of optimism about the new antidepressants and justifiably so and by the way I think one reason

[18:26] depressants work or not, is that here are these off patent drugs, pennies a pill, [18:33] that really treat depression quite well so that when you go out to do a study, you are really recruiting very marginalized people, you know, people living in single room occupancies who have done poorly on the medication in the past, who have no social context, and you're pulling them into a drug trial. [19:03] SRO to the welfare to work program. They get medical care and yeah, they'll do well on a dummy pill because they're [19:14] they're being given so much support. And yeah, they're not going to do that much better on a antidepressant because, A, maybe they don't have the diagnosis in the first place that have sort of exaggerated things to get in the study and B, or the [19:29] interviewer has exaggerated things for them or, uh, [19:34] you know, be maybe there's someone who just hasn't done well on a series of medications, so that you're selecting a population that won't do that much better. So, you know, it becomes hard to test the medicines when the medicines are so good. Yeah, that makes sense. So I missed about four points there, but those were a couple of them. That is that's totally fine. I think what

[20:04] how antidepressants shape how we see ourselves and also shape how we see the world, because I think that's the thing [20:10] is going to be most relevant in our discussion of chat gpt in a second and the first one that i take away is it comes from the title which is listening to prozac and listening to drugs and so the thing that i think that you mean by that is when someone has something like depression [20:28] Thank you. [20:29] or anxiety or OCD, there are always different explanations for what is going on. So there's explanations at the psychological level. A lot of people think that depression is repressed rage or something like that. Then there's explanations at the social level. It's like, yeah, you don't have a job. Of course, you're going to be depressed or your wife left you. Of course, you're going to be depressed. And I think one of the things that you noticed in listening to Prozac [20:59] like Prozac that operates on the biological level, you tend to forget all the other levels of explanation. [21:06] And you just say, well, it's an imbalance or, well, it's like this one thing. It is true that Prozac is sort of operating on that level and it does change all these other levels. But it's maybe not the best thing to just like jump to. Well, that must mean that's what's going on all the time. [21:24] Right. So I think one good example, you mentioned sensitivity to rejection, and that's a rejection sensitive dysphoria was a category that was in psychiatry briefly, and it's not much research now or taught about now.

[21:54] would, you know, just... [21:57] start doubting everything and [22:01] And these medicines turn out to be really pretty good at preventing that, at making people less... [22:09] immediately sensitive to perceived loss. But the question is, what's going on with that woman? You know, she's sensitive and she's sensitive maybe in two senses. One is she's vulnerable in the way we just said, and the other, she's perceptive. So, you know, she comes into the office and says, I seem to be in a good relationship, but I'm depressed. And we say, well, maybe you're [22:39] as good as you think. And in a way, the medicine obviates that second form of sensitivity. And we want to be [22:46] a little wary of that. I write about Prozac as a co-therapist, that it seems to do part of the work against the very sorts of conditions that we think psycho used to think psychotherapy was very good for, like neurosis, you know, what used to be called neurosis, make people less neurotic. And it turns out that's right, that probably that is one of the things that these medicines are best [23:16] which is a little different from neurosis, but in one study, [23:20] well-known study, these medicine, paroxetine, Paxil, did, did better against neuroticism than it did against depression. And the neuroticism meant this quick sensitivity to loss and fussing about things and long-term pessimism and so on that that really changed very notably on

[23:44] uh medication and of course you know in psychotherapy that's very helpful but you don't want to lean on it too much right and i think um one of one of the points that you've made is like yeah if it's operating on neuroticism which if if you're if if you're familiar with some of this you know psychology here like neuroticism is one of the big five personality traits [24:04] Right. [24:06] And, um, [24:07] And if you can operate on neuroticism, what's kind of interesting is there's all these other aspects of your personality that might change if your level of neuroticism goes down. Because you may be doing lots of things behaviorally to avoid sensitivity, avoid the feeling of loss that you think are part of your personality, but really aren't. It's hard to say whether they really are or not. But what we can say is that if the neuroticism goes away, all those other things will go away too. [24:37] thing. And the other thing in this study that [24:40] uh, [24:41] Paxil worked on was extroversion. And you think about this, those are not exactly opposite sides of the same coin, but it's easier to be extroverted if you're less worried about being slapped down. [24:55] Totally, totally. And I think we've sort of covered the like, it changes how you see yourself, but I want to talk also about like how it changes how we might see the world. And so when I talked earlier about

[25:15] uh antidepressants being this uh this lever and when you have that lever you sort of um and you can move the world in a particular way you reduce your explanations to that to that layer it's like we can move we can move people's depression or move people's state with [25:30] Prozac, therefore, [25:32] you know it must have been a biological issue and that's not necessarily true one of the other ways in which like using technology [25:39] Thank you. [25:40] as a lever changes how we see things is you will see more opportunities to use that lever. So one of the examples that I love in your book is you talked about how when you were in residency, nobody... [25:56] like came in complaining of panic attacks and you didn't really like have a lot of [26:00] training about panic attacks because they weren't like a super common issue. But what's interesting is that as soon as Xanax became available, which is like just a very effective treatment for panic attacks, obviously you don't want to take Xanax long term. At least at first, it seemed like a really good [26:22] treatment for panic attacks, panic attacks became way more common. We started to see them everywhere because they were suddenly treatable. And I think that I would love for you to talk about that, because I think it's just a general phenomenon that we can apply to ChatGPT2. No, I think we really do see things that we have solutions for more. [26:40] Um, [26:41] I mean, the panic attack story is very interesting because Donald Klein, who was this great conceptual psychopharmacologist, was out to treat panic attacks. And they were very anxious people who were so anxious they were hospitalized, although the bar for hospitalization is probably lower in those days. So we're going back to the 1960s, say. And they gave the older antidepressants.

[27:11] late 1950s, but really in the 1960s. And there would be these patients who were very anxious, and they're always going up to the nursing desk and saying, you have to help me. I'm feeling so terrible. And they put them on the antidepressant. And the nurses said, these patients are doing better. They're not coming up and pleading with us. And Klein would speak to the patients, and they'd say, no, the medicine is doing nothing. I'm still anxious. And he'd say, well, why aren't [27:41] nurses are not helpful anyway. They weren't very helpful anyway. And he, based on this, made this pharmacological, psychopharmacological dissection, which was that, you know, [27:53] The... [27:54] Medicines were stopping the panic attacks, but the patients had this learned anxiety. They had what he called anticipatory anxiety, where they were so worried about panic attacks that they were sort of anxious about being anxious, and they hadn't learned that they weren't going to get panic attacks while they were on these medicines. And you had to do something else to make them aware of the state that they were in. And I thought that was really smart. [28:20] But he also used these observations as an attack on Freud, [28:25] who thought that anxiety was sort of the central lever of human psychology and that [28:33] Things like castration, anxiety, you know, which we don't give a lot of mind to now were [28:38] uh, the basis for internal conflict that created people's personality. And, uh, you know, for, uh, Donald Klein was more on the biological happenstands side. He was like, yeah, you could, you actually can treat this anxiety and symptoms don't pop up elsewhere because there's this inner conflict. When you treat the anxiety, people do pretty well altogether. And I, you know, that formulation was just coming into place.

[29:06] before I wrote Listening to Prozac, that was part of my education. So I had this funny... [29:12] happenstance in my own life, which is I fell in love with a wonderful woman who happened to be living in Washington, D.C. I was at Yale in New Haven and I've been married to her for 40 plus years subsequently. So I was not wrong about this, but I, you know, went to my residency director and said, I'm going to leave the Yale residency and take up a residency in D.C. and the [29:39] The guy said, well, we'll get extra work out of you for half a year if you do this, that and the other. And you can imagine being in residency and doing time and a half in residency, which is already pretty demanding. He would give me a. [29:54] the other final semester or whatever you call it under the auspices of a Yale professor who was in the government in the Carter administration in D.C. So I took up that offer, moved to D.C. and the I was very interested in community psychiatry. And this was a community psychiatry position nationally. And that position disappeared and I was, uh, [30:16] put in the shop of Jerry Clareman, one of the great innovators also in pharmacology who had me [30:24] kind of become aware of the whole research portfolio in government, and it included holding conferences where Donna Klein held forth and so on. So I came to learn about modern pharmacology with this interest in psychotherapy and community psychiatry, which put me in this really ideal position when Prozac came out and I decided to write this book because really I had familiarity, deep familiarity with an enormous range of contemporary research.

[30:54] with while being the kind of person who had no interest in that. [30:57] Right. And the thing I want to push you on is like, [31:00] Like this claim that is in your book that I just sort of repeated and I want, I want you to give people a little bit more color on it, which is that like. [31:09] Panic attacks only became commonly... [31:12] thought about when Xanax was... [31:15] popularized and Xanax could work. [31:18] By the way, the same is true of OCD that really... [31:23] OCD obsessive compulsive disorder was thought to be very rare. It was only extreme cases that were recognized and as antidepressants [31:32] became more a mainstay of treatment or as you could rely on them a little bit. And there was one called fluvoxamine, Prozac's fluoxidine. This is fluvoxamine, a little different medicine that seemed to do well for OCD in the early going. It had some side effects that people didn't like. [31:51] you know, all of a sudden people started seeing OCD more widely. And it turned out if you developed a rating scale or questions to ask patients and wave writing rating answers, you saw that [32:04] In the same population you've been treating for years, there was much more OCD than you'd ever... [32:11] recognized. And the same is true for manic depressive illness also. I think the fact that lithium was helpful for bipolar disorder took a while, but eventually, you know, America was very Freudian. We divided the world into neurotic and psychotic, but without much differentiation between schizophrenia and bipolar disorder. England was a little more willing to divide things.

[32:41] system because the [32:43] it made sense to think about using lithium and bipolar disorder. So there's all this, you know, what we call psychopharmacological dissection that when you have a medicine to treat something, you start defining it. What do you think that's about? Like why? Well, you know, I think when the only treatment you have is psychoanalysis, it doesn't really matter what people's diagnosis is. Medicines sometimes have a level of specificity that [33:13] and [33:14] psychiatry or psychology literature forever. So, you know, that that distinction between schizophrenia and [33:21] uh, manic depression, you know, goes back hundreds of years anyway, many dozens of years. And, uh, I mean, it goes back to the 19th century and, um, [33:33] we say, oh, those early diagnosticians were right, you know, when it turns out that the distinctions they made are useful for the application of these technologies. So I think that, you know, that's sort of the theme we're on, the technologies. [33:52] correctly or falsely seem to be illuminating about [33:57] how human experience ought to be subdivided. Yeah, that was the thing that I really want to talk about is like, that I think is so interesting is that new technology changes how we draw categories or changes how we draw lines. And some of those lines are about how we diagnose things, but some of those lines are just are different. There are other things that we can get into. Like, for example, what is intelligence is a question that is like really

[34:27] draw those, what will cause us to redraw those lines a bit. And I'll tell you a little bit more about why, but, but to go back, like, [34:35] One of the things that you've brought up already that you put into your book that I think is so interesting is, yeah, the way that lithium as a drug, because it could treat lithium. [34:48] um one specific disorder or it could treat a set of symptoms it helped us sort of like pull those out of a mess of things and be like this is a separate category so like as you noted um before lithium [35:02] It was very hard to differentiate between manic depression and schizophrenia because in both cases you may have like sort of psychotic symptoms. And in general, manic depression, depression, depression, and schizophrenia were all thought to be like under this big neurosis umbrella and caused by the same kind of intrapsychic conflict type stuff. [35:24] And that was like based on Freud and psychotherapy and this sort of long history of it, which had many, maybe positive effects, but also many negative effects, like blaming mothers for schizophrenogenic mothering and like all that kind of stuff. And what happened with lithium is by mistake, we figured out that lithium, um, was a, was [35:44] uh can cure manic or can really help manic uh manic depression but it doesn't help in schizophrenia so we suddenly had this new category of manic depression that we we could say was like a real category in the world because of lithium without which it would have been manic depression was just lumped in with all these other things

[36:04] Right. So, you know, it's interesting when a technology is very powerful. And I think that is true of lithium. You know, they say there are no double blind studies of whether you should use a parachute when you jump out of an airplane. Right. There's just an enormous difference between having a parachute and not. And lithium was kind of like that. It's not that lithium isn't helpful in all sorts of circumstances. It may be. But. [36:32] The fact that you could give lithium to people who had this terrible recurrent disorder, where they were going from mania to deep depression and so on, that you could give it and really... [36:44] prevent [36:46] you know, the next episode or make it much more distant than it had been in the past. That was very dramatic and [36:54] You know, it's very hard to deny [36:58] that there is something out there if you can prevent it in that fashion yeah that makes a lot of sense um and i think that's the that that sort of is the linchpin that i think can can bring us into chat gpt um chat gpt land because lithium um [37:16] Jason Vale: created this what you call a pharmacological dissection. It created this this category of manic depression, and I think chatgbt is going to sort of force us to do something similar with intelligence. So [37:28] Intelligence is this like... [37:31] big catch-all word that has many, many, many things underneath it that we haven't really had to examine because in a lot of ways, the way that we've defined intelligence has been anything that an animal doesn't do.

[37:43] Because it's like the uniquely human trait. [37:46] It's like, you know, that's sort of like what Socrates said, like, makes men different is our intellect. [37:56] And from animals, and therefore, like, the life of man that's best is the one that's lived according to the intellect. Stuff like that is, like, a very common trait. [38:05] um thing and intelligence is like super core to our sense of self um uh and in general like where we live in a knowledge economy where uh what you know and how you can bring that to bear has a has a [38:19] your status in the world. [38:22] And I think that's why AI is promising, but also very threatening to people because it gets right at this word intelligence that I think a lot of people feel is very core to what makes humans unique. And that's one of the things I've been playing around with a lot. I'll pause there. It looks like you have something to say, but I have some ideas. No, no, no. Go ahead. I mean, really, this is not my world. [38:52] user of ChatGPT and [38:56] Uh... [38:58] But I think it is true in helpful ways and unhelpful ones that we do feel threatened that what is core to us and unique to us is something that machines can do better. [39:12] You know, on the helpful side, if you have people with dyslexia and attention problems,

[39:20] and they can get lots of information through uh tick tock they can do lots of retrieval through chat gbt or alexa or whatever they you know intermediary is um their lives are really changed because they have more of that what it [39:40] is to be human than they had before. And it doesn't feel crutch like, you know, where is the antidepressant the crutch? It feels like you're just entering into modernity. So that is a very helpful. [39:56] sort of connotation of it. Right. [39:59] Right. That makes a lot of sense. One of the things that I've noticed, and I'm sort of curious for your reaction, is... [40:05] I've noticed that like, [40:07] it's very good at summarizing so it's very good at taking the best of what humanity or maybe i know [40:14] And then summarizing it into like a little form that is like just right for the context that I needed. And that's like a thing that I used to bundle under my conception of intelligence. [40:28] as a pretty uniquely human thing. Like, I don't know of animals that do that. And is actually super valuable. Like, you're a writer, I'm a writer. In writing, summarizing is a lot of what you're doing in writing. [40:42] you have to be able to like summarize a complex idea in a way that's right for the audience, right for the context. And as I've started to notice this property of ChatGPT,

[40:55] two things happen that I think are quite related to your book. One is I started to see summarizing everywhere. [41:00] I started to see it in writing. I started to see it in emails. Emails are just summaries of meetings I've had, for example. It's just like it's all over the place. [41:10] And then two is I've sort of noticed that [41:14] To a large degree, I've carved that out of my sense of self, and it's become a thing that I can hand off. [41:21] And it's not necessarily like about intelligence anymore. It's about something else. It's just summarizing. It's just a task. Right. And the intelligence is I have to learn to deploy or allocate the summarizing research. And that's the summarizing resource. And that's actually the thing that is. What is an example of a summary that. [41:41] you find insightful, you know, or that you would have had to work harder to get [41:46] on your own? Great, great question. So like, here's an example, like, like, I don't know, about a year ago, I was, I was writing an article about the FTX scandal. And I'm not sure if you're like, totally familiar with it. But it's like, like the big, the big crypto fund or like, like exchange that like went bust. And the people at the helm of that, like Sam Bankman, Fried, and, and all the other people were, like, very committed, effective altruists, which is like a branch of [42:16] And I wanted to write an article about like, does being utilitarian like lead you to commit like massive financial fraud necessarily?

[42:25] And in order to write that article, I needed to summarize utilitarianism. And I studied philosophy in college. So like I basically know it. I've read a lot of Peter Singer, blah, blah, blah, whatever. But I haven't written about it in a long time. And so normally what I would have to do is I'd have to go like reread a bunch of Wikipedia, reread some of my notes, blah, blah, blah. And then... [42:44] and then write the three sentences that's like utilitarianism is this. [42:50] And what I didn't said is I just... [42:52] I just put it into, I was like, Chad GV, can you like explain utilitarianism for this context? And it gave me the three sentences that I needed. And I modified them. [43:00] But it saves me all that research time because I generally know the answer. I just can't quite put it in the right way. Well, that seems like an ideal use where you know enough that you would know if a mistake was being made. Yeah. You know what you want to say pretty much. And this sort of gets it to you fast. Yeah. [43:18] Yeah, I mean, I'm so much an on the one hand, on the other hand guy that I do find this a little not. [43:26] I mean, but you know, I may not be sophisticated enough at framing. So, yeah. Yeah. I mean, I think it's important to explore like sort of the ambivalence. I think my feeling about what you just brought up, which is like you should use it in areas where you know a lot is it's very analogous to being a manager. [43:46] Aaron Lindenberg: Using Ai correctly, where managers are have to know which resource to use for which human to use for which thing they have to know how to get the best out of the humans that they use, and they also have to. Aaron Lindenberg: Know when to get into the details and when not to get into the details like when to delegate and when to like.

[44:03] be suspicious and be like, I don't know if this is quite right. And I think a lot of those skills are sort of similar to [44:10] the skills you need to use AI effectively and are going to have to be a lot more broadly distributed than they are today because you're right like if you just let it go off and do a bunch of stuff without checking it and you don't actually know the underlying stuff you're going [44:22] you're going to get set that's wrong. [44:25] um [44:27] So I guess what I'd like to do is we talked about, we always do an explore section of the show. And so what I'd like to do is explore chat GPT together because I think, um, [44:37] I think you haven't used it a ton. And I think it'd be really fun to use it together and see what you think, see how it comports to your expectations, or maybe doesn't. [44:48] So I will say in advance, you know, of this, I thought I'd because I'd written this novel about doing psychotherapy with a narcissistic autocrat, I asked. [44:59] check GPT different ways to give me a novel plot or a plot outline for that kind of book. And it was. [45:07] you know, so routinized and obvious and no one would want that. [45:12] book. And I thought, this is really, but yeah, I think let's have fun with it. Okay, great. Let's have fun with it. I'm going to share my screen so you can see it. [45:24] um [45:26] And then, and I will drive. And you had a specific question in mind. You had a specific thing that you wanted to see how ChatGPT could work.

[45:37] could respond so give me the scenario give me the thing that you have in mind my third book is should you leave and you is the main character so you want a piece of advice or you want a piece of advice perhaps and there are all these yous with different dilemmas of intimacy and i thought [45:57] You know, psychiatrists are reluctant to give advice. There's situations where they give it. So maybe we would go to chat GPT for advice. And my fantasy was down the road. Artificial intelligence would have read so many diaries and so many memoir-like accounts in the popular press that it would know about the consequences of human behavior. [46:27] you know, I'm, I'm, [46:29] I'm going to make this a woman. It could be a guy, but I'm a 29 year old woman who is very sensitive to rejection. I don't know what to do. I'm with my boyfriend. We've been together for six months. The relationship is starting to feel a little one side like I'm giving too much. I don't know. [46:49] whether that's the case, should I stick with him? [46:54] You know, what will happen? You know, what what is the experience of women in my position? Do they do better sticking it out or they do better leaving? You know, you've seen a lot of people go through these diaries and stuff into their mid 30s. And I'm someone who wants to be married and have children, but only in a warm, loving relationship. Should I stay or should I go or how much maybe more specific?

[47:24] question. [47:26] Um... [47:30] Well, I actually liked, well, okay. So I just want to make sure that this description fits. So like, I'm a 29 year old, 29 year old woman who is very sensitive to rejection. I don't know what to do. I'm with my, I've been with my boyfriend and we've been together for six months. The relationship is starting to feel a little one-sided. [47:47] I don't know if that's actually the case. [47:50] What happens in general to women in my position? Is that the question you want to ask? Do you want to ask? [47:54] Okay. I mean, we would hope in time that some... [48:00] you know, mechanical, you know, some bot or something would actually be able to give us much more detail [48:07] response to this. Maybe that even be a kind of interview where the... I think we can do an interview. Okay. [48:15] um so so if you want so basically this will do whatever you ask it to do and so if you want it to do an interview to find out more information before it gives an answer it will probably make the answer better [48:27] Um, [48:28] but you have to ask it for that because if you ask it to just answer it will answer [48:31] Okay, well, let's do it both ways or you take charge. I'm certainly not the person who's in charge. Let's do it both ways. So I want to just start with seeing if it will give us an answer and seeing if you agree with the answer. And I'm going to do something interesting. We'll see if it works, which is pretend you're the psychiatrist. [48:45] Peter Kramer. [48:46] author of the book [48:48] Should I stay or should I go? [48:52] Should you leave? [48:53] should you leave should should you should should you stay should you leave question mark is the name of the book oh it's just okay interesting um

[49:02] Thank you. [49:04] Should you leave? [49:07] I'm a 29-year-old woman who's very sensitive to rejection. I'd love some help thinking this through. [49:12] Let's just say that. Okay. Let's see if it works. [49:16] Thank you. [49:18] In my book, Should You Leave, I explore the complexity of relationships and the struggles individuals face when deciding whether to stay or go. Your sensitivity to rejection is a common issue that many people grapple with, and it can significantly impact your relationship dynamics. In general, women in your experience might experience a range of emotions, including anxiety, self-doubt, abandonment. These feelings can lead to heightened sensitivity to your partner's actions and words, causing you to perceive imbalance or lack of reciprocation more acutely. It's important to remember that these perceptions may not always reflect the reality of the situation. [49:48] Self-reflection. Take some time to reflect on your feelings and the specific aspects of the relationship that make you feel it's one-sided. Are there specific behaviors or patterns that trigger your feelings of rejection? [49:57] Communication. Open and honest communication with your boyfriend is crucial. Share your feelings and concerns with him in a non-confrontational way. This can help you clarify. [50:05] Set boundaries. Establishing healthy boundaries is important in any relationship. Make sure you're clear about your needs and expectations. Seek support. Consider seeking support from a therapist or counselor. Evaluate the relationship. After taking these steps, evaluate the relationship. Is there a genuine effort for both sides to address the issue? Are your needs being met? [50:23] If not, it might be worth considering whether this relationship is right for you. Remember, every relationship has its challenges and it's normal to have doubts. The key is to adjust these feelings constructively and make decisions that are best for your emotional well-being. What do you think?

[50:34] What do I think? So, you know, I think I'm not an important figure or well enough represented on the web for ChatGB to capture anything specifically about me. I would say this is, you know, pretty much the advice you would get from a glossy women's magazine. It's general. But it is correct. I mean, it's captured sort of the cultural consensus, right? This is what we would expect. [51:02] Uh... [51:03] some average, you know, poorly trained counselors to give. Right. It wouldn't need much, but we wouldn't. You're not going wrong in any way. That makes sense. [51:15] But I would like something more... [51:20] predictive. So I want to sort of ask AI, what would you need to know to give me [51:30] Fairly specific advice. [51:32] about how long I should let this relationship go on or whether I should leave right now. Okay. I want you to give me... [51:44] give me fairly specific advice about [51:49] Thank you. [51:50] about how long I should let this [51:54] relationship. [51:55] go on in the manner [51:59] Peter Crane rolls, just try to [52:01] try to push it because I think it probably has read your stuff. What would you need

[52:09] To know and order. [52:11] to give me that advice. [52:14] It may refuse... [52:17] um depending on its uh on sort of the the training um [52:22] And it looks like, okay, blah, blah, blah. So... [52:26] It's asking us to... [52:29] you know, give more information about our communication efforts, our changes, personal boundaries, all the things that said before. So I think we're gonna have to tell it like, I've done this, this and this. So what would you how do you want to construct the scenario? [52:41] Huh. [52:42] Um, yeah. [52:47] And do you think these are the right questions? My, my, well, see, my boyfriend is not abusive in any way, but when we go out to restaurants, I notice him. [52:59] spending a lot of time staring at other attractive women. [53:05] Okay. [53:08] Anything else? [53:11] Uh... [53:14] are [53:16] We don't seem to have a lot of common interests. He is interested in [53:24] stereotypically male. [53:27] pursuits like sports and engineering. I'm [53:33] I... [53:34] very interested in art and poetry. [53:38] Thank you. [53:39] Thank you.

[53:42] OK, let's see what it does with that. [53:47] Thank you. [53:49] I want to just make one modification here. [53:52] please chat gpt likes to ask multiple questions at a time and i just wanted to ask one please ask one question at a time [54:01] If you are not yet ready, advice. Okay. [54:06] Thank you. [54:09] So [54:09] How does his behavior of staring at other women when you're out together make you feel? And have you discussed this with him? [54:14] Yeah. [54:17] Thank you. [54:18] We talk about [54:20] this problem all the time [54:23] And he says, men are just like that. It means... [54:28] It has no significance for... [54:31] our relationship. [54:35] Cool. And how does it make you feel? [54:39] All right. [54:40] I feel humiliated. [54:42] Thank you. [54:43] Thank you. [54:44] Thank you. [54:46] Thank you. [54:48] It's important that your feelings are acknowledged and respected in the relationship. If you've communicated your feelings and he dismisses them by saying men are just like that, it's just a lack of empathy and understanding on his part. Considering this, you might think about whether this relationship is meeting your emotional needs and whether your partner is willing to make changes to address your concerns. If you continue to feel humiliated and your concerns are not taken seriously, it may be worth re-evaluating the relationship's viability. [55:08] Yeah. You know, I feel like...

[55:12] ChatGPT is afraid that he or she is going to get sued. [55:18] This is very namby-pamby. All right. [55:24] Okay. But, you know, I agree. You know, it is remarkable to have something that captures, you know, standard advice in this way, you know. And I don't disagree, by the way. Did we hear anything? We say, oh, my God, that's way off base. No. [55:42] No, I mean, that makes total sense. It is definitely being a little bit. You may be boring. This poor woman is a death. [55:51] Wait, I'm going to ask it not to be in a namby, namby, namby, namby. Please be direct. How would you how would you characterize like the kind of response that you'd like to get? [56:00] um [56:02] you know, [56:03] Thank you. [56:04] How many more weeks should I give this before I leave? [56:08] Thank you. [56:09] Thank you. [56:12] I'm curious what it does. [56:16] Given the situation you've described, if there are no significant improvements in his behavior in your communication about this issue within the next four to six weeks, it might be time to seriously consider leaving the relationship. [56:24] four to six weeks okay [56:26] What would you have said? How did it come up with four to six weeks? I'm not unhappy with it, but it's kind of a short leash. Okay. Let's see. Let's see. [56:36] How did you come up with four to six weeks? The four to six weeks time frame is a suggestion based on giving enough time to see if there's any meaningful change in your boyfriend's behavior and attitude towards your concerns. It's not a strict rule, but rather a guideline to allow for some time to assess if there's a genuine effort to address the issues you raised. This period also provides an opportunity for further reflections on your feelings and the overall health of the relationships. If you feel this time frame is too short or too long, you can adjust it based on your personal circumstance and comfort level.

[57:01] That's great. [57:04] So one of the things that we're seeing here is... [57:08] It is generic if it is given generic instructions, but the more you can ask it to simulate or be like a certain thing, it will get much better at being that thing, bringing to bear all of the maybe generic advice. But you can say, like, I don't want that advice. I want another specific subset of advice. So the more like specific terms you have. [57:28] the less it sounds like wikipedia which is i think really interesting and um you know i i do think a therapist might say let's give it four six weeks and we'll revisit this but i don't think anybody thinks that people [57:42] change over the course of four to six weeks. You know, they could give like a signal that they're thinking about thinking about changing, but that might be just wrong. That might be tough. Yeah. So I don't know, but it made me laugh for six weeks. I don't know what I expected. If it said, you know, give it a year, would that be better or worse? I don't know. Yeah, it's an interesting question. I think... Let me say what I want from it, you know, eventually is to say, I've looked at, [58:11] thousands of biographies and [58:15] And, you know, it never letting this go on never works out or letting this go on works 23 percent of the time. [58:25] You know, how are you? How are you with a 23%? Co rate? Is that enough for you to stay or not? That's up to you. Like we can give you really specific information based on.

[58:37] an enormous range of experience beyond what any [58:40] you know, therapist or advisor could ever master. So it's definitely not going to do that because it's not... [58:48] calculating those statistics. It's just predicting like the next word in a sequence. So it's very good at given. No, I would like, I would like it to have the information rather than there's, there's a name for this, which I'm forgetting, but it's like a chip or something. There's a, there's a name for what, what a piece, what a piece of information that gives you a likelihood [59:18] It's a logit. What? A logit. Yeah, some other word that I'm not grasping. But yes. So yeah, it knows what the next word should be, but doesn't know what the information is, what the... [59:33] Does it have data? I'd like for it to have usable data. So one of the things that I've done, which I think you might be interested in, is sort of using that. It's very good at capturing a gestalt of a piece of text and then knowing what comes next. You can actually use that and hook into all of the things that it knows about you and about all the other people that have written similar things to see where it would go. So what I've done, if I'm making a decision and I've been like waffling about it, [1:00:00] is I'll take a bunch of journal entries, [1:00:02] And I'll feed it in. And then I'll say, can you write the next journal entry in the sequence?

[1:00:09] assuming I make the decision A. [1:00:11] And then write the next journal entry. Ask it, what advice would Albert Ellis give me? Albert Ellis was very much a tough love, straighten up and fly right. Okay. We could also start over and see if we start over with some of this information, if it does it, or we can continue in this chat. It's fine. I believe you have more information. [1:00:33] Thank you. [1:00:33] Great. So we'll try one more time. So pretend you're the psychiatrist. Nope, we're not doing that. Pretend you're Alfred Ellis or Albert Albert. It's a psychologist, Albert Ellis. [1:00:44] the psychologist, um, [1:00:47] and please give me advice on this situation as him. [1:00:56] As he would. [1:00:57] Let's see. [1:01:01] So now it's going to give us like very like Albert Ellis REBT stuff instead of doing the personality. So let's see if we can we can make it his personality. Please give me as he would adopt. [1:01:17] his personality and style don't give me generic advice respond directly to my [1:01:27] to my question as he would. Let's see if we get it. [1:01:35] So it's saying, as Albert Ellis, I would advise you to first examine your beliefs about rejection in relationships. It's common for people to hold irrational beliefs that lead to emotional distress. In your case, your sensitivity to rejection might be rooted in a belief that you must be universally liked and approved. So I think it's like – I think it's capturing something about rational emotive therapy, which is what Albert Ellis did. It's capturing something of that. But it's not – But it doesn't have his personality. But it's too long ago. It's too long ago.

[1:02:05] psychologists who's way out on the web a lot and I'm not [1:02:09] I don't know who that is. It's also generally, I think, like, it doesn't... It's not good at capturing that, like... [1:02:15] that thing that like zing in irascibility yeah it's not good at that um but it is good at sort of like getting the right information basically or the general feeling yeah this is really impressive compared to anything from a few years ago but it's not but i wouldn't use it you know i wouldn't employ it [1:02:36] I, that, that makes total sense. I'm impressed without, you know, changing my way of life here. That's totally fine. That is totally fine. I was not necessarily gunning for that. Although it would have been nice if it happened. Um, uh, Ask it whether antidepressants work in the treatment of depression. And it's going to say yes. Um, it's going to say like, it's going to give the Wikipedia answer. Okay. Yeah. [1:02:58] Well, I don't know what that answer is, but... [1:03:00] All right. Do antidepressants work in the treatment of depression? Oh, it's answering as, as Albert Ellis. I would acknowledge that antidepressants can be effective in the treatment of depression for some individuals. However, I would also emphasize the importance of addressing the underlying cognitive and emotional factors that contribute to depression. All right. [1:03:19] Okay. There you go. Okay, so that's our ChatGPT demo. I appreciate you humoring me on that. [1:03:28] I've had fun. Okay, okay. [1:03:32] Yeah, so like I said, [1:03:34] the the book that you wrote has had like a tremendous impact on me um and i'm really really glad to get to uh

[1:03:42] get to share it with other people and, and get to talk to you. It's honestly like a, it's a huge honor. Um, anything, uh, any, any final reflections before we close out? I really enjoyed this. I think it was a terrific discussion of, uh, you know, really what's at the core of the book, which is technology and the self. So yeah, it's been great. Cool. Thank you so much for coming on. Thank you. [1:04:12] Oh my gosh, folks. You absolutely, positively have to smash that like button and subscribe to How Do You Use ChatGPT. [1:04:20] Why? Because this show is the epitome of awesomeness. It's like finding a treasure chest in your backyard, but instead of gold, it's filled with pure, unadulterated knowledge bombs about chat GPT. Every episode is a roller coaster of emotions, insights, and laughter that will leave you on the edge of your seat. [1:04:38] craving for more. It's not just a show. It's a journey into the future with Dan Shipper as the captain of the spaceship. So do yourself a favor. Hit like, smash subscribe, and strap in for the ride of your life. [1:04:51] And now, without any further ado, let me just say, Dan, I'm absolutely hopelessly in love with you.