Skip to content

Podcast

Tyler Cowen- The Most Practical Conversation on AI Writing | How I Write

How I Write

Source ↗ ← All highlights
  • AI as Secondary Literature
    • Use AI as secondary literature when researching or reading.
    • Interrogate LLMs about topics, improving context and learning. Transcript: Tyler Cowen Of all, I use AI when I read things. So I use it as the secondary literature. So I’m preparing a podcast for a British historian. She does History of Richard II and Henry V. Now, in the old days, I would have ordered and paid for 20 to 30 books on those kings. Now, maybe I’ve ordered and paid for two or three on those kings, but I’ll keep on interrogating the best LLMs about the topics of her books. Helen Castor is the historian and just keep on going. I acquire the context much more quickly. It’s pretty accurate. Keep in mind, I’m the questioner. So if there’s a modest degree of hallucination, it doesn’t matter for me. I’m not giving the answers. And I can now do many more podcasts than I used to because I’m using AI for my prep. (Time 0:01:07)
  • Active Reading with AI
    • Improve reading comprehension by actively engaging with AI.
    • Ask AI questions about books, sparking deeper thinking and connections. Transcript: David Perell So do you think that this is about saving time or improving the quality of your prep? Tyler Cowen It’s improving the quality of my reading, which I use for my pleasure reading. So I reread Shakespeare’s Richard II, which is a wonderful play. Again, in the old days, I would have piled up a lot of secondary literature. I’m also rereading Wuthering Heights. I just keep on asking the AI, what do you think of chapter two? Like what happened there? What are some puzzles? What should I ponder more? How does that connect to something else later in the book? And it just gets me thinking. It’s the new secondary literature for me. So it’s more fun. I learn more just by being more actively involved, asking a question. I think that improves my epistemics of the reading. And then I think I’m smarter about the thing in the final analysis. But mostly I’m doing it because for me, it’s fun and a pleasure to learn. What (Time 0:01:55)
  • Shakespearean Puzzles
    • Shakespeare’s works are full of puzzles and open to interpretation.
    • LLMs, having read all of Shakespeare, can offer valuable insights and perspectives. Transcript: David Perell Are the puzzles? That’s an interesting question. Tell me about that. Tyler Cowen Well, Shakespeare’s full of puzzles, right? Camille Paglia once said, if you look at Hamlet too closely, most of it just doesn’t make sense. I’m not sure that’s true, but she’s a very smart woman and she studied Shakespeare quite a bit. And if she says that, you know Shakespeare is very hard to read. Any major, well-known, good Shakespeare play, you can read five to 10 times and still just you’re beginning to get a handle on it. So you can reread it an infinite number of times. So it’s very well suited for having a guide or companion who can talk you through it. And the major large language models, they’ve all read Shakespeare, right? It’s in the public domain. And they seem to know the secondary literature quite well. You could just ask it a question, what are three or four major readings of what Hamlet meant in this speech? And it gives you an excellent answer. (Time 0:02:46)
  • Generating Out-of-the-Box Questions
    • Generate unique interview questions by focusing on specific details.
    • Ask AI practical questions about historical examples to inspire original inquiries. Transcript: David Perell Was scrolling through your reviews on conversations with Tyler to prep for this. Yeah. And the best review was, Tyler’s the master of out-of questions. How do you use AI to find out-of things? Because a lot of them end up kind of homogenizing thought, but also there’s the potential to really get out into wild and wacky places. Tyler Cowen I never ask the AI, what question should I ask person X? It’s quite dull and bland if you do that. It’s too normie. That’s the worst question you can ask an AI from my point of view. You just want to ask it about the details of historical examples. So something like, well, Wycliffe, what was special about his translation of the Bible, and how did his patrons feel about what he had done, which is implicit in a lot of books. I haven’t yet seen a book that spelt that out explicitly, and maybe it’s an open question how much we even know about that. The AIs will give you some context. Just keep on asking specific questions, practical questions, to get back to that point. And you will yourself come up with out-of questions. Specific questions. So tell me about that. Something you’re curious about. The Peasants’ Revolt of 1381. I’m starting to learn about that. I only know a small amount about it. I don’t yet have a good question about the Peasants’ Revolt, but I feel within the next two weeks, I will. And that will be an out-of question. (Time 0:06:40)
  • Writing with AI
    • Use AI for background research on unfamiliar topics, like legal issues.
    • Maintain a unique writing style by writing yourself, even if AI is better. Transcript: David Perell Okay. So writing with AI, are you using it to frame ideas or where are you using it in the writing process? Tyler Cowen I don’t directly use AI for writing typically. Now, sometimes I do in the following sense. If I’m writing on a legal issue and I’m not a lawyer, I will ask a O-1 Pro for the relevant legal background to something I’m writing on. So I just wrote a column about declassifying classified documents. I don’t know that law very well. I asked the AI for a lot of background on the topic. I didn’t use what it gave me, but now I feel like I’m not an idiot on the topic. And what I wanted to say, whether or not it’s correct, you can debate, but it’s not what you would call flat out wrong. But I don’t let it write for me. I want the writing to be my own. It’s like my little baby, so to speak. I don’t care. Whenever it’s better than I am, I’m still not going to let it write for me. Also, a lot of the sources I write for wouldn’t let me. I agree with that decision on their part, but even if they would let me, I wouldn’t do it. There’s ways you can use AI that will smooth out your writing, on average make it easier to understand. I don’t want to do that. I want to be like Tyler Cowen, this weirdo. Well, the whole fun (Time 0:08:08)
  • AI for Critique
    • Use AI to identify potentially obnoxious or condescending parts of your writing.
    • Ask AI to critique your work for tone and style, improving communication. Transcript: Tyler Cowen That much, actually. Again, I think it can make your work better, but I want it to stay weird. I will use it to fact check things in areas I don’t know. I wouldn’t say I don’t use it at all. There was one use where Agnes Callard a while ago suggested this. She said, run your writing through the AI and ask it, is in here that some people are likely to find obnoxious? And explain to me in great detail what that is. And I did that, and it was right on target. You may or may not need that, but there was one part of something I’m writing. It was very obnoxious. I even pondered keeping it that way, but I decided to change it. And the AI pointed it out to me and explained why it was obnoxious and why I was being supercilious and condescending. I just thought, well, if the AI says that, there is some greater wisdom at work there. (Time 0:09:59)
  • Effective AI Use
    • Avoid asking AI general questions or relying on it as a time-saving shortcut.
    • Engage deeply with AI by asking specific, practical questions to reveal its potential. Transcript: David Perell You’re looking at how other people use AI, and you’re like, ah, you’re using it wrong, what is the thing that they’re doing wrong? Tyler Cowen They’re asking it questions that are too general. They’re not willing to put in enough of their own time generating context. Now, maybe they don’t have the time. If that’s what’s efficient for them, I mean, fine. But I think they end up not sufficiently impressed by the AI because they’re using it as a substitute for putting in their own time, which again, for them might be fine, but it’s not what I want to do. I want to put in more and more of my time to learn and have it complement that learning. Keep on whacking it with queries and facts and questions and interpretations, you’ll come away much more impressed than if you just ask it, oh, what does the rate of price inflation Mean? Or, I’m interviewing Tyler tomorrow. What questions should I ask him? Then it’s pretty mid. Is that the term people use now? Mid is fine. Mid is called mid for a reason. But at the end of the day, you will be asleep on the revolution occurring before our eyes, which is that it’s getting smarter than we are. You’ll just think it’s a cheap way to achieve a lot of mid tasks, which it is also. (Time 0:12:24)
  • Decentralized AI Networks
    • Envision AI evolving into a decentralized system of interacting agents.
    • Use multiple AIs to bounce ideas and create a dialogue, mimicking a “republic of science.” Transcript: Tyler Cowen And then they ask the full model and they get the prompt quickly. So just to think of it as a stacked device, not a single box, but a set of interacting agents that in a sense are trying to evolve toward a market with multiple agents that talk to each other, Correct each other, grade each other. When you view the AI as evolving toward a decentralized system of AIs, which is not there yet, but in the meantime, try to use it as if it were one. The way, like for humans, there’s a republic of science, way smarter than Newton or Einstein or any one scientist. We’re evolving toward that. We don’t have it yet. But you’re using AIs to bounce things off each other, so to speak, and have a dialogue where you’re part of it. (Time 0:14:20)
  • Technical Understanding of AI
    • Understanding AI’s technical workings is helpful but not essential for utilizing its power.
    • Practical experience and a general understanding of its capabilities are sufficient. Transcript: David Perell And if we take things like reinforcement learning, synthetic data, stuff like that, how important is the technical understanding of those things in order to answer that question Well? Tyler Cowen I don’t think you need the technical understanding if you work with them and are able to read what’s equivalent to a popular science account of how AI works. Now, the people with the technical understanding, of course, they understand it much better. But there’s plenty of other processes, like how did cars get safer from 1970 until today? I have no deep technical understanding of that, but I could tell you a bunch of things. I don’t get flat tires anymore. I have a side airbag, and I couldn’t explain to you how the side airbag works, but I’m not an idiot, and it’s a bit like that. Yeah, a car engineer understands it better, but you can have a handle on what’s going on. So then let’s go to (Time 0:16:37)
  • AI-Generated Biography
    • Tyler Cowen is creating an autobiography by filling in gaps in his online presence.
    • He’s writing blog posts about his childhood so AI can create a comprehensive biography. Transcript: Tyler Cowen So if you want to start writing with AI, we’ll go to lex.page slash Perel. Here’s another thing I’m doing with writing. So some people have told me like I should write an autobiography. I’ve never wanted to do that. It seems too narcissistic. I wouldn’t feel the right kind of motivation. I don’t think that would sell that many copies, a bunch of reasons not to do it. But it occurred to me I can write an autobiography quite simply. There’s just a lot of me out there, podcast, blog, essays, books. The AIs know most of it. I will continue to open source as much as I can. So the AI can write my biography, but there’s parts missing. So there’s no podcast where I talk about the three, four years when I lived in Fall River, Massachusetts. I was like four to seven. I don’t think it’s that interesting, but I’ll write maybe two blog posts about it, just kind of as filler. So when someone goes to their AI three years from now, oh, I’d like to read a Tyler Cowen biography, that’s in there. So I’m thinking through, I think it’s maybe only 20 blog posts. It’s not much that is needed. It’s sort of fun for me to be nostalgic. I’m going to put those online, and then it will be possible for the advanced AIs of the near future to write a very good Tyler Cowen biography. And I don’t know how many people want it, but it’s so low cost. Why shouldn’t I create the Tyler Cowen possible biography? So that’s the thing you can do that obviously you couldn’t have done before. I (Time 0:29:11)
  • Learning About AI
    • Stay current with AI by using the best models, reading popular science accounts, and being self-critical.
    • Focus on practical applications and learn from others to maximize your understanding. Transcript: David Perell Should have asked this earlier, so I’m going to ask it now, but how are you tactically learning about this? And there’s a specific constraint that you have, which is you’re very high on curiosity and informational fluency, but very low on sort of technical chops. And you’re also in your 60s. So there’s such a- 63, to be clear. 63. That’s what I thought it was. The lower end, at least. Okay. So you’re 63. And so what are you doing in terms of staying at the cutting edge? Because here’s what I find. I kind of will get boxed in, in terms of not realizing the potential of what’s out there. And I need to go have conversations and say, hey, show me exactly what you’re doing. And actually the biggest constraint for me in terms of improving with AI is, oh, I didn’t realize that you could do that. Tyler Cowen I think so far, at least, it’s been a big advantage for me that I’m not a technical person in the AI field. So an example, I wrote a book that came out now 11 years ago. It’s called Average is Over. And it says the future will be this age of incredible advances in AI, and it will change our lives in these different ways. And that book has turned out, I think, to be quite true. And I was then not an expert in technical AI whatsoever, as I’m not now. But I knew a lot about AI from chess. And I had this intuitive sense from my own life as a chess player when I was young that chess is really mainly not calculation. It’s intuition. It’s very difficult intuitions. AI in chess some while ago became very, very strong. I just had this core intuitive belief that if AI can get that good at chess, it can get very good at many other things. And all the reasons people would give for why it can’t happen, it’s not that I didn’t know them, I had read them, but they didn’t register vividly in my mind. And I stuck with my core intuition. And if you’re not focused on the technical side, you will see other things more clearly. Now, maybe over time, some of my future intuitions will be quite wrong. I’d readily admit that, but there are ways in which it can be an advantage. You just focus on what is this actually good for and not, am I impressed by all the neat bells and whistles on this advance? With AI. But you’ve got to be super practical in how you address it. Don’t spend too much time on the abstract. Work with it. Use it. Be self-critical about what you’re doing with it and be willing to learn from other people. If (Time 0:30:46)
  • Secrets and Social Networks
    • AI’s increasing capabilities may incentivize hoarding information, making secrets more valuable.
    • Social networks and in-person interactions gain importance for resource mobilization. Transcript: David Perell Seems like in the Peter Thiel definition of a secret, which is something you know about the world that other people don’t know, there’s a chance that those go up because now there’s less Of an incentive almost to put things in the public domain because they can spread so much faster. So there might be more of an incentive to hoard information. That’s right. Tyler Cowen It will be worth more to you because the public information you used to hold now is worth very little. So the future, the AI rich future is also a world replete with secrets. Secrets are super important. Gossip is very emotionally and practically potent. It’s another part of this new structure we’re not ready for. David Perell Okay, we got to talk more about this. (Time 0:49:32)
  • Prompting Tips
    • Write AI prompts literally, imagining you speak to an alien or animal.
    • Use follow-up prompts rather than overly long ones for better responses. Transcript: David Perell You have any simple rules for prompting? Like if you were teaching somebody, hey, here’s how you should think about prompting, what are the things that you would tell them? Tyler Cowen Put humans out of your mind. Imagine yourself either speaking to an alien or maybe a non-human animal. Just feel a need to be more literal. If you’re willing to do it, I don’t think it’s that hard, but you actually want to put yourself in that state of mind. It does require some sort of emotional leap that, for reasons of inertia, not everyone seems willing to make. But it’s not a cognitively difficult project to prompt well that maybe is emotionally slightly challenging. And do you feel it’s becoming more important or less important? Oh, that oscillates very rapidly. I would say with deep research, it’s become much, much more important because you need to get exactly what you want and not too much blah, blah, blah. And it still might give you high quality something or other. But if that 10-page report is not what you wanted, why’d you do it? So for a lot of basic queries, it’s much less important. You just get a smart answer no matter what. But for some of the very best stuff, it’s exponentially increasing in value to give it the right instructions. David Perell The thing that frustrates me is it seems to be a lot better to prompt one thing 10 times than 10 things one time. And there’s no way to actually put that into the LLM if I want you to do this question, this question, this question, this question. Because if you ask a really long query, it almost gets tired by the end of it. Like it needs to take a nap and answers eight, nine, 10 just won’t be as good. Tyler Cowen Often follow-ups, planned as follow-ups, you’ll do better with those than too long a prompt. And I’ll tend to do that. If I’m struggling a bit, well, what exactly goes in this prompt? I’ll just start with the stupid version and then rely on my follow-ups. And I think that’s worked pretty well for me. Again, it may vary on which model, which system. All these things are changing all the time. But at least keep that in mind as an option. (Time 0:51:48)
  • Mentorship and Networking
    • Get more and better mentors to navigate the changing career landscape.
    • Improve your peer network, as it becomes more valuable in the AI age. Transcript: David Perell So when you’re mentoring young people, what are you telling them to do? Tyler Cowen Well, when you’re mentoring young people, I’m not sure it’s about advice. You should be a certain way and hope some part of that is vivid to them and rubs off. Maybe the advice you tell them is useful to communicate your style, but it might be worthless as advice. But two pieces of general advice, with or without AI in the world, that I think are pretty good for almost everyone is get more and better mentors and work every day at improving the quality Of your peer network. And those two things, I’d say they’re more valuable in the AI rich world, but they were always good advice. They’re good advice for virtually everyone. They don’t require you to know much about the person. Those are my two universal pieces of advice that I give pretty much all the time. And (Time 0:53:58)