Skip to content

By playing, you agree to uListen's Terms and Privacy Policy and YouTube's Terms of Service.

Latent SpaceLatent Space

draft Claude Code Psychosis + The Global Memory Shortage: Doug O'Laughlin, SemiAnalysis

descirption pending

swyxhostDoug O'Laughlinguest
Feb 24, 20262h 6mWatch on YouTube ↗

Summaries, chapters, transcripts, and FAQs on this page are made by uListen, not YouTube.

Partial transcript

  1. 0:00 – 0:04

    Intro

    1. SW

      [gentle music]

  2. 0:04 – 2:44

    Old Twitter days, conference run-ins, and staying semi-anonymous

    1. SW

      Doug O'Laughlin, welcome to LeanSpace.

    2. DO

      Yeah, thank you for having me.

    3. SW

      Yeah. [laughs]

    4. DO

      Um, I, after all this time, I just... Is it okay if I just call you swyx? I feel-

    5. SW

      Yeah, of course

    6. DO

      ... yeah, it's the, that's, that's where my brain is 'cause I've known you for so long. You can call me Mule if you want.

    7. SW

      [laughs]

    8. DO

      I'm not care. Um, you know.

    9. SW

      Yeah.

    10. DO

      Yeah, I mean, it's been, it's been a long time.

    11. SW

      It's been a, it's been a long time coming. I think I first met you at, like, New Orleans or, like, one of the, one of the NeurIPSes.

    12. DO

      Yeah, yeah. I met you at one of the NeurIPSes in per- I think it was Vancouver, right?

    13. SW

      Was that?

    14. DO

      Yeah, no.

    15. SW

      I don't know.

    16. DO

      I think it was actually-

    17. SW

      It was like some after party.

    18. DO

      Yeah, yeah, yeah.

    19. SW

      And you were like, "Hey," like-

    20. DO

      Yeah

    21. SW

      ... "Who's the tall dude?" I'm like, "Whoa, okay." [laughs]

    22. DO

      Yeah. [laughs] Yeah, well, I mean, it's just like I, I knew about you, and we, we've, like, been internet, you know, pen pals for a long time, so it was, like, cool meeting in person. I mean, yeah, yeah. I think that was the first time I ever met you in person, so yeah.

    23. SW

      Amazing.

    24. DO

      I n- I didn't go to the New Orleans one. I really wish I did. I love New Orleans, honestly.

    25. SW

      Yeah.

    26. DO

      Yeah, so.

    27. SW

      Go to New Orleans just in a row and, um, yeah, obviously we should go back there.

    28. DO

      Yeah.

    29. SW

      Um, are you guys going to Melbourne or-

    30. DO

      I-

  3. 2:44 – 5:39

    From quality/value investing to getting “single-shot” by semiconductors via ASML

    1. SW

      Yeah. So, um, le- let's, let's do a little bit of the Doug story 'cause a lot of people hear about Dylan, uh, and I wanted to just make this the Doug story, make, make the Fat Knowledge story. You used to be a value investor. That's kind of how you, you were Value Mule.

    2. DO

      Mm-hmm.

    3. SW

      And you had a mentor or something that nerd sniped you into semis. Is that the, the story?

    4. DO

      Um, no. Actually, I solo nerd sniped myself.

    5. SW

      You soloed. Okay.

    6. DO

      Um, so I, I wouldn't say value because, uh... Well, well, for, for everyone who's listening to this podcast, might as well be value, right? Maybe quality focus back in the day. But we had this whole thing where we wanted to buy quality compounder companies and, um, the one I found that nerd sniped me, all the, like, single shot me, is I found ASML.

    7. SW

      Yeah.

    8. DO

      And then I, like, fell in love with it, and then I, like, after ASML, I just, like, read about all this stuff, how complicated it is to make these, who are the people who are able to make them. And then I, you know, semiconductors, the whole downstream's all from there. But it started with ASML in 2018. I really fell, fell in love with it, and then I read, like, textbooks, and I just, like, kept going deeper. And my favorite part about doing that-

    9. SW

      I'm gonna pull out the Asianometry video.

    10. DO

      Yeah, yeah. That's perfect. That's a perfect one right here.

    11. SW

      [laughs] That's John. Fucking amazing.

    12. DO

      John's a monster, honestly.

    13. SW

      This one, right? Uh.

    14. DO

      Yeah, yeah.

    15. SW

      Yeah.

    16. DO

      Um, I mean, the thing that's crazy is he has, um... I don't know. He has a whole playlist about it, every single aspect of what goes into it. And what, what's truly great about it, it's all science fiction. Like, that's my favorite thing is, like, science fiction exists other than, you know, the talking perfectly intelligent robot, whatever information, LLM. Yeah, ASML is all science fiction. So the semiconductor stuff's always been science fiction. Always loved it, always thought it was cool. Thought it was the most important thing that we ever made, and, uh, yeah, kind of followed from that. Um-

    17. SW

      Yeah. I don't know if you know, but obviously, you know I used to be a inve-

    18. DO

      Yeah

    19. SW

      ... uh, an analyst myself.

    20. DO

      Yeah, I didn't know.

    21. SW

      I covered TMT-

    22. DO

      Mm-hmm

    23. SW

      ... which is a freaking huge sector to cover. It is absurdly huge.

    24. DO

      Yes.

    25. SW

      Like-

    26. DO

      Very large

    27. SW

      ... like, I was covering Sprint-

    28. DO

      Yeah, yeah

    29. SW

      ... and [laughs] got, like, uh, you know, Viacom.

    30. DO

      Yep.

  4. 5:39 – 7:43

    “Moore’s law is dead” as the thesis that rewired the playbook

    1. DO

      You, you, you assume that all the Taiwanese people who are buying and selling the rumors of capacity are pretty well-informed. You assume all the people who are TMT investors in the United States are pretty well-informed. I think the thing that was, like, the foundational difference for me is, like, you know, real thesis around, um, one I think being- [inhales] young and brash and believing in yourself to be like, "No, this is something that's really matters, and everyone else doesn't see it," really helps. But for me, the thing that was like, I guess, radicalizing was, um, I really believed Moore's law was dead. Um, and I was like, "Oh my God, not only is it this cool new technology that's super hard to make and very interesting and technologically very fun to understand, and, and like I get it intuitively, but, um, also everything... All the old playbook is about to be thrown out because it's been like this is a super mature industry. You really need these primers about it. Like, that's how you learned about things back before ChatGPT knew everything-

    2. SW

      [laughs]

    3. DO

      ... or, um, you had to go and read these primers of all this information. They're like, "Oh, it's a very mature industry. It matured. It used to be really immature in the '80s and '90s and 2000s, but now you're consolidated. Growth doesn't go up a lot." And everyone kinda had this old playbook from the early 2000s. A lot of people hated hardware. Um, there was just this perception that semiconductors weren't valuable, weren't as valuable. Actually, software was the most valuable thing. Now software is getting shit on, but that's like outside of the scope of this. But, um, people just thought it was this old, mature business that had nothing new under the sun. Meanwhile, every single day, just making a new chip was like science fiction. Um, people took that for granted, and when the science fiction ends because you can't make the chips as small as you c- you could, all of a sudden, all those free gains you got go away, and you have to think about it. And what happened for semiconductors specifically is it created a lot of pricing power or value for everyone who knew how to make a good chip. So NVIDIA's probably the best case. You could talk about parallel computing and all that stuff. But it's not just... Like, they know every aspect of it, from the chip to the networking, to the design, to the scale-up, the whole thing. It, it is like, you know, versus w- in, in the past, it was just CPU gets better and better, right?

    4. SW

      Mm-hmm.

    5. DO

      And so I think that I had a really deep belief that-

    6. SW

      In this case

  5. 7:43 – 12:46

    Early AI scaling view, meeting Dylan, and being shocked by the magnitude

    1. DO

      ... that, uh, M- Moore's law was, uh, Moore's law was ending, and everything would change. And so coming in with that, like, thesis at the top level just, like, made me wanna attack every little assumption. And something that really changed as well... I... And dude, this is honestly my, my favorite post I've ever written. It's like 20- uh, it's like, uh, ChatGPT-3 and the writing on the wall. In like 2- 2020, you know, my early... I get a early pitch to, um, for fabricated knowledge, and I'm like, "Hey, you know, I'm gonna make a release. You know, Moore's law's over. Scaling laws seem like a big deal." If you simplify it all the way through, it's like, okay, supply, uh, you know, supply divide, uh, you know, demand, right?

    2. SW

      Yeah.

    3. DO

      Demand is growing a lot because of scaling laws. Uh, supply is actually slowing down because Moore's law is completely screwed. Um, that's probably really good for semiconductors, and parallel compute is gonna be a big deal, blah, blah, blah, blah, blah. Um, my conclusion then was, um, you should just... Like, NVIDIA's pretty much the only one who's gonna benefit. Um, and, and you know, so that's why my, my, my, my like good long range prediction, I feel like. I-

    4. SW

      Just

    5. DO

      ... I, yeah, I just don't think, I don't think I would've expected the magnitude. I think that that's been the kinda the craziest part about this whole story is, like, I had all these beliefs and thesis and, like, I really, really, really believed. The reason why I met Dylan is he was the only person who was as semiconductor pilled in the entire world as me, is how I felt. Um, so I remember, like, yelling at him, arguing about all these kinds of things in, like, our, our DMs and stuff like that.

    6. SW

      Was it just online, or did-

    7. DO

      It was on-

    8. SW

      ... you also-

    9. DO

      Online. We met in person

    10. SW

      ... in Taiwan and-

    11. DO

      No, no, no. I, I've, I've actually only been to Taiwan with him one time, I think.

    12. SW

      Yeah.

    13. DO

      Um, so, so, uh, I mean, like, look, we, we just met in person. We yapped. We went to conferences. Um, but I think that that's, like, kinda we were both really early to the thesis, kinda have a different background and perspective. Uh, Dylan is technology first, and you know, obviously technology matters. I have a little bit more of a financial background, but always around him, and it was just like, you know, he's the only one- guy who, like, cared the, to the same level. Um, so yeah, this, the, the thing that's crazy is, like, we called it. We were right, blah, blah, blah, blah, blah. But, like, the thing that I think that still shocks me all the time is the magnitude of how right we are, you know? Like, it'd be like, oh, NVIDIA was good, right? NVIDIA's pretty good. Um, and then it's like, no, NVIDIA's now the most valuable company in the world.

    14. SW

      [laughs]

    15. DO

      And I think if you had me read that and, like, truly, "Hey, I wrote that. I believed it"-

    16. SW

      Yeah

    17. DO

      ... um, I still wouldn't have put that together, or, like, I wouldn't have believed it if you-

    18. SW

      This was one of many thesis at the time.

    19. DO

      Exactly. Yeah, yeah.

    20. SW

      Right?

    21. DO

      Like, there's so many things-

    22. SW

      Like, what else are you writing at the time, right, that didn't-

    23. DO

      Oh-

    24. SW

      ... work out, you know?

    25. DO

      Um, yeah, yeah.

    26. SW

      We can look, we can look back, but-

    27. DO

      I, I, I, I'm pretty happy with my m- with my long-term track record.

    28. SW

      [laughs]

    29. DO

      I really am. Um, but yeah, I'm just really surprised the magnitude of how everything happened. Like, it's crazy to me that, like, CoWoS is, like, a, a, not a household term, but, like, we- relatively well-known. It was, like, an exotic technology.

    30. SW

      Mm-hmm.

  6. 12:46 – 20:55

    Why Claude Code grabbed a semiconductor analyst: tools as competitive edge

    1. DO

      So yeah, I think here's the thing, is, um, if you wanna be good at any game... We're, we're tool users at the end of the day, right?

    2. SW

      Mm-hmm.

    3. DO

      If you are a good... If you wanna be, like... A- and, and obviously this is, like, outside of my job at SemiAnalysis. Like, I have all these other things I need to do to, to grow and make SemiAnalysis the best research firm ever. But, like, let's say you're a fund manager or an analyst, right? Your job is to find information edges and, like, n- new ways to put information together that no one else has done. Um, and so, like, I've always thought it's really important to know the most important weapons-grade, uh, tool that you can do all the time, which is essentially ChatGPT, Anthropic, all this kinda stuff. And I've been pretty... Like, I'm a, I'm a early adopter in tools as much as I can be. And, um, like for example, I've been running the... our, our case study that we have into Claude Code since it first came out. Like, you know, I think over a year, like, you know, I wanna say March, April I started to do-

    4. SW

      Sorry, which case study?

    5. DO

      Uh, so the case study for people when we're, we're hiring, like, a financial analyst, like a- our core research seat or something.

    6. SW

      Okay.

    7. DO

      "Hey, um, you know, can you, can you take this company and do some analysis, blah, blah, blah, give us this format back?" Um, and I've been running it through, like, the agentic things, and I'm like, "Hey, what, what..." When agents really come around, they should be able to one-shot multi-step hard things to do, things that would take a human 24 hours to do, right? And I always wondered, 'cause I... You know, there's some good submissions and there's some bad submissions. We pride ourselves in the case study in being good. And, and honestly I always joked, like, well, you know, they're gonna start to beat the worst submissions. And so, like, that was our... that was always my base level. I have a base level of ca- is it better than a ChatGPT agent mode or Anthropic's Claude Code-

    8. SW

      Yeah

    9. DO

      ... or Gemini CLI, whatever. And so I started running these benchmarks a little bit. And so I was very familiar with how good it could be, but then I was like, "Oh, it isn't quite there." Um, I've web coded some stuff on Opus 4 for sure, but like, you know, it was, like, kinda interesting projects on the side. It was really hard. It took a lot of feedback. They would, they would mess up. It just didn't... And then, um, you know, everyone was freaking out about Claude Code 4.5, and I, like, took it for a spin, especially around the holidays. I had some free time. And then I was like, "Okay. Well, like, how good is this?" And then just, like, one... It started, like, one-shotting everything, right? Like, all these MVPs that, like, you know, you have to be like, well, the UIs, whatever. It's like, no, it just one-shots it. And then you ask it to do something better, and it explains what you're doing, and you're like, "That's actually really good." And so I was like, wow, generalized, easily one-shot MVP of these, like, projects, and able to, like, really build things on top of it 'cause you can trust what it's doing to a certain extent.

    10. SW

      Mm-hmm.

    11. DO

      And it felt like some level of capability was beaten. It was very different than what I'd done in the past. Oh, I also tried Codex 2 before this, like, um, like when it was 5.2. Never really got it to work in the way seamlessly, agentically. Like-

    12. SW

      Oh, of course. So this is af- this, this was recent

    13. DO

      ... Oh, n- no, no, no. So, so, so, uh, this, uh... My re- most recent when I was like, "Oh, man," the, the awakening, um, probably December 27th.

    14. SW

      Okay.

    15. DO

      December 26-

    16. SW

      You know it to the day. [laughs]

    17. DO

      Something like that. Something like that. I'm thinking 'cause it's between the days, and-

    18. SW

      Oh

    19. DO

      ... I, I got home from Chri- Christmas, and I was like, "Oh," um, my fiance wasn't feeling so well, so I had some time to mess around just by myself.

    20. SW

      Yeah, yeah.

    21. DO

      And, and then also there's 2x usage limits. Oh my God, I miss those days. But I mean, now I'm addicted to Fast. Um, but, but look, I, I was playing around with these coding agents just like everyone else should or d- or should in the space, and, like, Claude Code versus Codex. I was, like, doing, you know, simple testing to see if they can make a thing, and it never really, like, one-shotted, like, a total idiot's thing. And then 4.5 just started one-shotting stuff, and that to me was, like, a huge difference. And so, um, I was like, wow, it could just, like, one-shot stuff. I have all these interesting ideas I can pursue.

    22. SW

      And, and can I... Uh, is it Excel, uh, sheets in- primarily?

    23. DO

      Uh, no, no, no. Not Excel sh- uh, sheets primarily. I would say it's usually a mix of, like, a dashboard or Excel or something like that. But a good example where I... Like, I, I think Excel, it's moderately okay at, like, let's say one-shotting a basic financial model or, like, just taking and, and putting information from one place to another. It's not at human level, but honestly, i- if you know much about investing in the, being in the business, it's like, is your model, you know, being 5% more accurate really gonna ever make a good investment decision or not? No. Never, not once. Like, no one's saying, "Oh, yeah, my estimate is always one cent more tighter than everyone else-

    24. SW

      [laughs]

    25. DO

      ... and that's why I'm good at stocks." No. It d- it doesn't matter.

    26. SW

      It's like sell-side is ridiculous 'cause, like, everyone's like, "Yeah, I'm bullish 'cause, like, my EPS estimate is, is, like, 10% higher than, than the Street."

    27. DO

      Yeah.

    28. SW

      And I'm like, "Oh, who cares?" [laughs]

    29. DO

      Well, I mean, as you know, sell-side... If we're gonna do this as, like, shots in, a- across the bow on sa- on sell-side, I mean, look, one of the reasons why SemiAnalysis has such a, like, a successful business is because I think sell-side as a concept is very broken. If you're talking about waves and things that are changing, uh, sell-side in a lot of ways is this hereditary child of, like, let's say 30 or 40 years of banking where you had, um, you know, a company go public, so you needed someone to talk about it to issue securities, and you had to-

    30. SW

      So you're selling the stock

  7. 20:55 – 26:23

    Claude Code “psychosis” in practice: portfolios, frameworks, and GitHub commit tracking

    1. DO

      Yeah, so let me specifically talk about my use case, 'cause, hey, I am still a stock guy. I can't trade or do anything in semiconductor or, or, uh, AI world. But, you know, I do still really enjoy stocks. It's one of the reasons... Like, I'm passionate about it, and it's probably my, my defining skill, what makes me good or bad at stocks, quote, unquote. You, you know the people who are really, like, stocks, they're, like, lifers. They just love this shit. Um-

    2. SW

      [laughs]

    3. DO

      ... it's, it's like an addiction, okay? Um, so I, I'm like, "Hey, you know, um, here's, like, all my positions, and, like, here's some, like, thoughts on it. Can you just, like, kinda, like, start copy-pasting some notes over and putting it all together?" It's like, yeah, it does-

    4. SW

      That's why do you give Claude Code?

    5. DO

      Yeah.

    6. SW

      Okay. [laughs]

    7. DO

      So I started doing this, and then I'm like, "Okay, but, like, add it, make the portfolio, run some basic risk stuff." And it's like, "Yeah, sure, fine, whatever." And then also, like, everything you do is perfect. I'm like, "Okay, well, like, actually, can we, like, make an investment framework for my investment style and start to grade all this stuff, and then, like, attack it and do stuff like that?" You can just do, like, iterative work. And then I was like, "Whoa, whoa, whoa, this is, like, a crazy useful tool that systemized how I think really quickly." Like, "Okay, what else can I do with it?" And the answer is, like, fucking anything, right? And my joke on the, the podcast is it's all a skill issue now. Um, and so I, I've been, I've been doing this systematically for every aspect that I can think of. Like, hey, now it's so much easy, easier. Like, I was, um... Actually, a perfect example is this, is this chart, right? Hey, Claude Code is a really big deal. Everything's one-shotting. I'm reading everyone going into psychosis like me at the same time on the internet. How do I actually know what's real and what's what?

    8. SW

      I wonder, right?

    9. DO

      Yeah.

    10. SW

      Yeah.

    11. DO

      I wonder, right? So I'm like, "Okay, uh, I heard about the fact that the Claude Code has the commits, right, o- onto the public r- uh, onto your, your commit." It says, "Hey, signed off with, um, whatshamacallit." I'm like, "Well, why... Claude Code, scrape me all the commits," right? And, uh, you know what? Lo and behold, it pretty much did. Like-

    12. SW

      [laughs]

    13. DO

      ... and it's like, okay, well, like, I'm looking for this signature right here, copy-paste. It was like, how would you systematically go about doing it? Did, like, a big query pull for all the stuff, pulls all the, uh, like, every single day. The API's relatively open. And then I'm like, "Oh, my God, let's see how much this is growing." And it's like, okay, chart go up. And you're like, "How big is it as a percent- percentage of GitHub?" You're like, chart go up.

    14. SW

      [laughs]

    15. DO

      It's a huge deal. And I'm just, like, watching her. Uh, you know, I have, like, a cron job updating it every single day, blah, blah, blah. And I'm like, "This is a huge deal." Like, this is the b- the biggest deal. I, I love watching trends. I love watching exponential trends, and I've never seen one even remotely at this rate. You would, r- you know, 4% in, like, two weeks for-

    16. SW

      Do, do you know of PR Arena?

    17. DO

      Uh, yeah.

    18. SW

      It's, it's a previous attempt, uh, prior to you. But somehow they didn't, they didn't, uh, they didn't talk about... They, they just talk about merge rates. They didn't, they didn't, they just [laughs] they don't, they don't plot it as nicely as you do.

    19. DO

      Yeah. Well, the... And also you wanna... Okay-

    20. SW

      'Cause you, you, you asked, you had the t- you, you had the, uh, you asked the question of what is this as a percentage of GitHub, and this, this guy didn't.

    21. DO

      Yeah.

    22. SW

      That's it.

    23. DO

      Yeah. And, and also, um, I mean, the other thing, too, is, yeah, I have a lot of those as well.

    24. SW

      Yeah.

    25. DO

      Um, but, but I thought the Claude Code 'cause I'm just trying to really, really, really focus on that specifically. Yeah. Well, and also you wanna g- give an example. Um, bro, I didn't make that chart. Uh, Opus 4.5 did

    26. SW

      Yeah

    27. DO

      Uh, or, or I think 4.6. I'm like, "Hey, um, I want you to do it in this style. This is the SemiAnalysis color scheme."

    28. SW

      Yeah

    29. DO

      "This..." Uh, re- I, like, summarize books about visualization-

    30. SW

      Yeah

  8. 26:23 – 32:25

    Rubrics, context rot, and working styles that reduce drift

    1. SW

      Do you, do you put it all in one prompt, like the, the, the, the task and the rubric for the task-

    2. DO

      S-

    3. SW

      ... or do you put the rubric after all the task is done?

    4. DO

      I, I actually have two versions of this.

    5. SW

      Okay.

    6. DO

      I'm like, "Hey, you can pull all this stuff together. Just ru- run the pr-

    7. SW

      Yeah, yeah

    8. DO

      ... uh, the rubric or whatever."

    9. SW

      Yeah.

    10. DO

      "Or you can, uh, do the task and the rubric." It just depends on how you wanna do it. Um-

    11. SW

      Yeah, because obviously if you put it task and the rubric, then it can iterate itself.

    12. DO

      Mm-hmm.

    13. SW

      But if you put it after, then it's probably more likely to pay attention to the, the rubric.

    14. DO

      Yeah, exactly.

    15. SW

      You know?

    16. DO

      And well, and the other part, part of it, too, um, yeah, it, it will iterate, but, like, the context rot doesn't ma- I kind of like it to be separate because the thing is it's like, okay, it needs to be this, like, fresh look at it. You have to think of it kind of like it would perceive anything anywhere, right? It just, each context window is just opening it up, and I think sometimes, um, if you have do- if you do it together, it commingles the information to the point where it becomes biased or sus- susceptible. Opus 4.6, as you know, is, like, super sycophantic. Like, it loves to, like, say, "Yes, okay, yeah, I'll do this for you."

    17. SW

      Yeah.

    18. DO

      Um, I think having it separate keeps it, like, keeps some of that drifts kind of away, and that's, like, one of the things that I've really... Personally, I like the results better, but it's, it's just complicated. Like, part of this is really weird because I am, I'm weirdly now opinionated on taste in terms of how you should design things because you can, like... For example, the context rot thing, until someone explained it, I was like, "Oh my God."

    19. SW

      [laughs]

    20. DO

      "Just thank God someone said it." This is a huge deal. Um, there's this, like, meme where it's like, uh-

    21. SW

      Oh, yeah

    22. DO

      ... these guys-

    23. SW

      Yeah.

    24. DO

      Um, well, do you see the meme? It's like, um, of mice of men, and at the end of, um... You know, at the end of the book, of... I can't remember which character shoots who.

    25. SW

      I've never read it.

    26. DO

      Yeah. So, so one ch- character shoots the other guy, and it's like some guy made a meme about it, being like, "Oh, this is..." After your, um, after your Claude code is garbled, you know, five million tokens, you're like, "Okay, it's time to put you down."

    27. SW

      [laughs]

    28. DO

      Um, because the context rot is huge. Um, so yeah, this, yeah, this is an example where-

    29. SW

      So what, what are your compacts practices? Do you s- sort of aggressively compact manually or...?

    30. DO

      Um, so I personally, with the one- new 1 mil, it... I feel like I try to do it at all in one context window. Um, I'm not doing ginormous projects.

  9. 32:25 – 36:47

    Sub-agents vs agent teams vs swarms: what works and what fails

    1. SW

      ... right? One of the, the biggest sort of Claude Code, uh, shows in the world, uh, which is sub-agents and agent swarms. Maybe if you, I don't know if you've tried-

    2. DO

      I have tried them

    3. SW

      ... any. Pick, pick either one, uh, whatever you want.

    4. DO

      I have a controversial opinion that Claude does not do RL on the agent swarms or agent teams.

    5. SW

      Yeah, it's just an experiment

    6. DO

      It's, it's just an experiment. Um-

    7. SW

      Yeah

    8. DO

      ... thank you, thank you, 'cause no one-

    9. SW

      No, not [laughs] he, he-

    10. DO

      We, exactly, 'cause the pro- it's just via prompt and it's actually very bad.

    11. SW

      [laughs]

    12. DO

      Um, I think sub-agents are okay because they usually have a Claude MD to go do whatever. Um, but the agent team is h- is actually really bad

    13. SW

      Okay. Well, well, you know-

    14. DO

      It's, it's-

    15. SW

      ... it, we can't, we can't knock it 'cause it's experimental, so-

    16. DO

      Yeah. Yeah, no, no, it is-

    17. SW

      But w- what do you, what do you try it on?

    18. DO

      Um, uh, well c- it was, like, some big data analysis of, like, many, many different companies with different KPIs into a dashboard all in one.

    19. SW

      Mm-hmm. Mm-hmm

    20. DO

      Um, I was like, "Hey, can you just make this all whatever, split up the teams?" You know, speaking of that though, you say that, but Kimi, Kimi 21 agent swarm is actually good.

    21. SW

      I have also tried that

    22. DO

      It, it is a- that is actually really good, so I did some, like, in- oh, example of things I, I was never available to me, like internal benchmarking of these models and be like, "Hey, here's a set of problems I would like you to do 20 times. Um, can you do them?" And then I can measure the performance between them and then, like, do qualitative like what's the difference between X and Y.

    23. SW

      Yeah.

    24. DO

      That, that was completely out of the hands of me, a normal guy, like three months ago.

    25. SW

      [laughs]

    26. DO

      Okay? Now it is completely available to me. That's awesome. Like, I am very-- I care about this stuff and now I have the tools that's able to automate and do a lot of this stuff because, hey, all of software engineering is, like, partially automated. And so, I mean, my experience is the 2.5 swarm actually improves the model's performance meaningfully. Um, the agent team makes it meaningfully worse because there's clearly not RL done, so it isn't context-

    27. SW

      Yeah

    28. DO

      ... aware of what's the best-

    29. SW

      Yeah

    30. DO

      ... thing to be done. And yeah, so I think, I think it's interesting. I like sub-agents 'cause it's usually a little bit cleaner on a task, uh-

  10. 36:47 – 46:16

    Security and automation reality checks: ClaudeBot/OpenClaw, Zapier comparisons

    1. DO

      Yeah, I know Kimi Claw. I haven't... Yeah. Dude, I was gonna say, um, have you messed around with OpenClaw? 'Cause I did, I-

    2. SW

      Yeah

    3. DO

      ... oh, gosh, I remember, um, what was it first called? Claw.

    4. SW

      ClaudeBot.

    5. DO

      ClaudeBot, yeah. Dude, I was gonna say it was really, really euphoric. I was like having it read all my emails and my calendar and do all this stuff, and then I was like, "Wait, wait, wait. This is really, really, really prompt injectable." And I was like, "This is pretty secure and important stuff." So I like, I was like, you know, Claude Code Psychosis is good enough for me at this point in time.

    6. SW

      Yeah. I mean, so what I do is I just have multiple emails, right?

    7. DO

      Yeah.

    8. SW

      And there's, there's a safer email to give to the bots-

    9. DO

      Yeah

    10. SW

      ... and I can let it use that, and if it impresses me, then I can upgrade it. Uh, but Claude Bot didn't impress me at the, at-

    11. DO

      I, I'm gonna be honest with you, I'm gonna be honest with you, I wasn't impressed either.

    12. SW

      Yeah.

    13. DO

      That was the reason why people were freaking out about this mobile book. I was like, "Bro, have you actually used this shit?" 'Cause it's not... Even right now on Claude Code in a relatively focused terminal, it will be like, oh, blah, blah, blah. I'm like, "Dude, in the .env there is an... Like in the .env there is an API I told you to use for this sub-case of problems, and it's in your Claude MD. Like please focus up." Like it still is like making mistakes.

    14. SW

      Yeah.

    15. DO

      This is not like truly AGI, and there is harnesswork. You still have to wrangle this thing. But, um, it's not like a perfect skill follower, and the, the context in each attention window is gonna like change, and sometimes it'll be lazy, sometimes it won't be, but it's definitely good enough to do a lot of information with.

    16. SW

      Yeah. I was gonna, uh... So I, I use, I use our, um, I use our Discord as basically like a, a, a way to just bring information in and out. I, I, I just saw, I saw this too where, where basically like a lot of people are just setting up things that they could have done in Zapier-

    17. DO

      Mm-hmm

    18. SW

      ... with Claude Bot because they're like, "Well, you know, now I'm like AI pilled," but actually they just done it more securely with Zapier.

    19. DO

      [laughs] I think-

    20. SW

      Which I think is kind of interesting.

    21. DO

      I guess. I, I do think it's kinda interesting, but I think there's... But the, the difference though is Zapier, I mean, I remember I've tried to use Zapier before-

    22. SW

      Yeah, it's, and it's also not very good

    23. DO

      ... it's not, also not very good. The difference though is like, and that's okay. Like it's okay to be early to something and just wrong because you weren't the one that made it happen, right? Claude Bot, the Claude Code, Claude Bot, whatever, all this stuff, the reason why it's so powerful is it gets to completion, right? And, and like, okay, Zapier, maybe you can get to completion all the time, but like man, it probably took you like eight hours of clicking through things and like copy-pasting crap to make sure it all works and it's all secure. And it's like well Claude Bot did it or Claude Code did it in like, you know, four and a half minutes-

    24. SW

      Mm

    25. DO

      ... and that's good enough for me. You know? That, that's a faster achievement. And so like it's totally okay that they were, they're right, but they were just not the right mechanism-

    26. SW

      Yeah

    27. DO

      ... right? You, you see this happen in information, like in the history of like compute or-

    28. SW

      I, I think there's also like an innovator's dilemma. I think where Zapier as a preexisting business had this view of the world of automations as like very strict sort of on rails workflow-

    29. DO

      Yeah

    30. SW

      ... type things that their giant user base already uses. They couldn't like really pivot that much.

  11. 46:16 – 1:03:57

    AGI framing, GDPow, and fears about deflation and GDP measurement

    1. SW

      By the way, that's also existential for you guys if you get caught doing, like, putting out some slop to your clients, right?

    2. DO

      Yeah.

    3. SW

      Like, you, you have to-

    4. DO

      Yep

    5. SW

      ... at, at one point be, like, extremely AI pilled and, like, you know-

    6. DO

      Yeah

    7. SW

      ... you, number one in the world at applying AI to your productivity, great, but also, like, you gotta-

    8. DO

      Yeah. You have to... So, so I think, I think the thing that's really interesting is this whole thing is like a game of hygiene now. Um-

    9. SW

      Yeah

    10. DO

      ... because I, I think it's like this is really hard, and I think about it all the time. I feel very comfortable with doing all this work because the thing is my-- at the end of the day-

    11. SW

      So it's done the work

    12. DO

      ... and I've done the work. I have, like, a lot of, like, embeddings in my brain-

    13. SW

      Yeah

    14. DO

      ... a lot of information. The vibes that have got me in here is actually, like, tons and tons and tons of information, set up scenarios, and, like, pattern recognition, right? But, um, yeah, you're right. This, this crap makes mistakes all the time.

    15. SW

      [laughs]

    16. DO

      All the time. It is still just like a, like, I think of it once again as, like, a junior analyst, right? The analyst goes and does all this, like, really pain in the ass information. You bring it all together to make a good decision at the top. Um, but the problem is, um, historically what happens is that junior analyst, who I once was, went and gathered all that information, and after doing this enough times, there's a meta level thinking that's happening where it's like, okay, here is what I really understand and how this type of analysis I'm an expert in, actually, I'm very good at. I consistently have a hit rate. Now I'm the expert, right? I don't think that meta level learning is there yet. Um, we'll see if LLMs do it, right? Everyone who's spending $1 quadrillion in the world thinks it will. It, it better, it better happen, right?

    17. SW

      [laughs]

    18. DO

      If you're spending, you know, a trillion dollars and there's not meta level learning. But for me in our firm, that massively amplifies everyone who is an expert, right? And we are a firm filled with experts. And so it's this hard part where I wonder if new people we will be less lenient in terms of, like, how much AI tools you-

    19. SW

      New, like junior-

    20. DO

      Yeah

    21. SW

      ... or new to the firm?

    22. DO

      Junior.

    23. SW

      Or, oh.

    24. DO

      Uh, junior to the firm.

    25. SW

      Yeah.

    26. DO

      A junior, and like, like, 'cause, like, you have to still do something that you can't just, like, slop it up. It's very obvious to me when it's slopped.

    27. SW

      Yeah.

    28. DO

      Right? When it's slopped and there's no cognition, then it's like, like, whatever, the artisanal last 5% is, like, that really matters.

    29. SW

      Yeah.

    30. DO

      But for me, I know inherently what the 5% is. I can, like, write it away with some really easy heuristics and time and, like, be like, "Okay, well, this is the last 5% you fixed. This is what I believe. Just fucking make up these assumptions instead. Press Enter. Okay, cool. We're good to go." You know?

  12. 1:03:57 – 1:22:47

    Capital cycles and the AI buildout: railroads as the analogy, debt as a bottleneck

    1. DO

      Yeah. Well, I- I wrote this whole thing about railroad stuff 'cause it's my favorite-

    2. SW

      Okay

    3. DO

      ... my- my favorite capital cycle.

    4. SW

      Is this on Fab or?

    5. DO

      It's on Fab, yeah.

    6. SW

      Okay.

    7. DO

      Um, I can't rem- uh, it's like railroad Fab... Uh, it's about all the railroad stuff over time, okay? Pretty much because, um, we're, like, everyone was first looking for the internet. We've well massively passed the internet in terms of the absolute size of the build-out.

    8. SW

      Mm-hmm.

    9. DO

      It's not even close. Like, we-

    10. SW

      What, what numbers are, are you thinking of?

    11. DO

      Um-

    12. SW

      Like, what, what's the-

    13. DO

      I think, I think a trillion was, a trillion all in was essentially the real dollars for-

    14. SW

      Okay

    15. DO

      ... version, and I think we are well past. Like, we, like, whatever this year, and it's cumulative, right? We were well past that. I think railroads, the reason why it's so interesting is 'cause, um, honestly it's way crazier, but- but prob- part of the problem and craziness of it too is, like, railroad was literally, like, one of the first added layers of the layer cake if you think about it. Before, it was agriculture, and railroad was like, "Okay, well, how do we move this agriculture around faster?"

    16. SW

      Yeah.

    17. DO

      Um, and then banking got, I- I- I kid you not, like, one of my big takeaways is banking effectively got invented by railroads.

    18. SW

      Oh.

    19. DO

      Because there's no need to-

    20. SW

      You have to finance it

    21. DO

      ... finance it. Yeah. So much money was needed that, like, effectively 85% of all paper whatever was essentially just railroad debt. Um-

    22. SW

      Yeah. Um, one of my favorite anecdotes was before there was a federal bank, uh, a federal reserve, Andrew Carnegie was the federal reserve. [laughs]

    23. DO

      Yes. Yeah, there were individuals. Yes.

    24. SW

      [laughs]

    25. DO

      Um, yeah, and so all this stuff, uh, so it's like the whole thing, I kind of did some work on the Gilded Age, all this stuff, but, like, my takeaway is, like, that was a really interesting cycle because it was so big and took so long to deploy. It actually was 45 years of, like... There's three cycles actually. There's three boom busts.

    26. SW

      Damn.

    27. DO

      Um, I don't know if it'll be quite that long. All the cycles kind of collapse.

    28. SW

      Yeah.

    29. DO

      Um, are that, uh-

    30. SW

      Because, you know, information-

  13. 1:22:47 – 1:33:11

    Microsoft’s dilemma: “renting barbarians,” Azure vs moat defense, and execution skepticism

    1. SW

      Okay, I wanted to transition to a little bit of a spicy thing where you were on TVPN and their title that they chose for you was, uh, "Doug O'Laughlin thinks Microsoft is out of AI" and ooh, did you, did you not see this?

    2. DO

      Okay, so, so, so I wouldn't say out of AI. No, I did s- Okay, so I didn't watch it. I never re-watch these things.

    3. SW

      It's-

    4. DO

      Okay, so how I think about it is-

    5. SW

      But like, uh, uh, you, you said things like-

    6. DO

      I-

    7. SW

      ... Microsoft is scaling back investment and-

    8. DO

      Yep

    9. SW

      ... you know.

    10. DO

      So, so, so it was the previous conversation I was talking about-

    11. SW

      Yes

    12. DO

      ... how Microsoft has the most to lose.

    13. SW

      Mm.

    14. DO

      They have the most to lose of everyone in the entire world if you-

    15. SW

      'Cause they're the, they're, they are-

    16. DO

      They're the software company

    17. SW

      ... the horizontal software company.

    18. DO

      If ChatGPT, they're fucked. Yeah, exactly. They're the horizontal software company that humans use their software to do information work.

    19. SW

      [laughs]

    20. DO

      Okay? No... Like, I cannot paint a bigger target, okay? I cannot paint a bigger target. Um, and my, my-

    21. SW

      Sa- Salesforce.

    22. DO

      Yeah. Uh, well s- Okay, that's another two number-

    23. SW

      Well, Microsoft is automatically a bigger than Salesforce.

    24. DO

      Yeah.

    25. SW

      Yeah.

    26. DO

      But the other thing too is they have this Azure business.

    27. SW

      Mm.

    28. DO

      Um, I don't think they're completely out of the race. I'm like, you know, it's a really great clickbait title, but the, the problem is the Azure business with OpenAI, right? You're essentially renting barbarians at the gate. You're, you're like, you know, this is r- ancient Rome, and you're like, "Hey, we need some extra guys, so we're gonna, we're gonna pay money for these barbarians to guard-"

    29. SW

      The Golden Army.

    30. DO

      Exactly.

  14. 1:33:11 – 1:40:57

    TPUs opening up, supply chain realities, and why HBM drives the next gap

    1. DO

      Mm-hmm.

    2. SW

      TPUs will hopefully... I, I don't know, maybe, maybe a short one, but, like, you know, uh, for a long time you could not buy TPUs, uh, at least like current gen TPUs externally, and now you can. And Google's open as a, as a, as a supplier, I guess. [laughs]

    3. DO

      I think Sergey doesn't want to lose.

    4. SW

      Yeah.

    5. DO

      And I think the thing that happened was, um, up until... Like, you know, he wasn't-- no one was there.

    6. SW

      A part of the whole DeepMind story was we will hoard all the TPUs-

    7. DO

      Yes

    8. SW

      ... because we were first. Uh, we, you know?

    9. DO

      Yeah.

    10. SW

      And, and so, like, why so? You know? Why, why, why give anything to Anthropic?

    11. DO

      I think it's because at least last year it became, um, pre-Gemini 3, it was like, "Dude, we have all these TPUs. We're gonna hoard them all," but, like, people aren't using our products anyways. [laughs] And, and like, like, "Hey, what's all, what, what good is all these TPUs if, um, we're getting our asses kicked in consumer?" I think it's an interesting thing, too, 'cause the other thing I think about is there's a lot of different ways to, to, like, break this down. One, we wrote about it in TPVA, like whatever, we think Rubin will be much more competitive. I think Ironwood, uh, V7 is the peak gap between on- between TCO, between Nvidia and, um, TPU, right? So if you are at your absolute strongest point, what do you do? There's two ways you could do it. You could try to maximize and, like, squeeze the juice and, like, make margins, or you can, you can gain market share. I think the perspective of doing this externally with, with Anthropic is to gain market share because the biggest gap you have, um... And, and one of the reasons why there hasn't been a second merchant chip, and also you can argue Nvidia's the most valuable company in the world, what's the value of TPU in Google? It's, it's huge.

    12. SW

      You must have done the math.

    13. DO

      I've done the math. It could be like, it's like-

    14. SW

      A trillion?

    15. DO

      It's like a trillion. Yeah. It's like a trillion or something like that, assuming it gets, like, 30% market share or something like that.

    16. SW

      Yeah.

    17. DO

      Everyone has been trying to crack the merchant silicon mode, right? And now they have the biggest absolute outperformance. All- a lot of the people who did the original TPU program are, like, now at OpenAI.

    18. SW

      Some of them are Medics.

    19. DO

      Some, some of them are. Yeah. Yeah. Exactly. Some of them are Med- They're all over, right?

    20. SW

      Yeah.

    21. DO

      Like, the, the core team that did most of the engineering have, like, since really dispersed. And so I think the gap might, might close over time. And so at this absolute period of time, they're gonna, they're gonna win market share. And then, then what happens is if you have an install base, you have an incentive to upgrade your install base. That's, like, the hugest problem with AMD, for example. No one wants to buy new AMD chips 'cause it's not like they have old AMD chips.

    22. SW

      Hmm.

    23. DO

      No. They're not upgrading from anything.

    24. SW

      Hmm.

    25. DO

      And so when you have that number two place, you have to, like, you have to win definitively and then also you have an opportunity to win, win again next year. I think the install base issue has been a kinda huge one. And so TPU is at the point where the software ecosystem is mature enough. The hardware is definitely mature. The networking's really mature. You have a really good external customer who actually knows how to use your product. If you want market share, now's the time.

    26. SW

      Yeah. That would be insane if they, if they actually sort of pump the, pump the gas on that stuff. Um, are you also hearing-- I, I don't know if this is something that affects your analysis at all because I don't have any appreciation for the, or the, the sizes that we're talking about here-

    27. DO

      Mm-hmm

    28. SW

      ... that JAX is helping TPUs win, or, or JAX is winning relatively to PyTorch, at least in, like, the academic arena, which is a leading indicator of what it's gonna be used in, in-

    29. DO

      I do not have as-- I, I don't have-

    30. SW

      Okay

  15. 1:40:57 – 1:56:47

    Memory mania and the global squeeze: HBM tradeoffs, rising DRAM risk, and downstream impacts

    1. SW

      One thing I love about your analysis is it's not actually just the context windows. It's not just the KV cache. We also have to offload it to non-HBM.

    2. DO

      Yeah.

    3. SW

      Every other part of the memory, it, um, the, the- it's, it's like su- such an interesting cascade, uh, waterfall of like just like a de- a short squeeze and, and everything. It's not a short squeeze. It's like a supply squeeze.

    4. DO

      Yeah. A sup- I mean-

    5. SW

      There's like, uh, w- I just wanna like-

    6. DO

      I mean, effectively-

    7. SW

      Three to one ratio of like-

    8. DO

      I mean, yeah, yeah. Okay, so it's, uh-

    9. SW

      Three to one-

    10. DO

      To quantify to-

    11. SW

      Sorry

    12. DO

      ... three to one to four to one ratio. I think, I think make sure- so, so it's in the Memory Mania, um, post that we just put out of like the four to one or the trade-off ratio.

    13. SW

      Yeah.

    14. DO

      Um, scroll down somewhere and you'll see.

    15. SW

      Yeah. So, so basically for, for listeners, it's the idea that like when you convert to HBM because there's a huge demand for HBM, it takes three times, uh, one HBM sort of units is like three times, uh, of the other sort of DDR or whatever, right?

    16. DO

      Yeah. So some amount will always be lost in production because yield isn't perfect. And so effectively you're trading some, like you're trading, uh... I, I ma- I w- actually wrote a really funny piece like I, I called it like super oil, but let's say this is a better one. Um, but pretty much like you- in order for this higher grade of jet fuel has been invented, and the only way to make it is to like actually, uh, get rid of all, all your other fuel and you have to like massively condense it and refine it, okay? So, um, now what happens is if there's any demand here, it's an instant shortage. And so we, we hilariously enough came out of like the biggest shortage ever in NAND and DRAM. Like terrible, like catastrophic, the worst one ever. Like the, the, the last analysis I could put to is like '96 or something like that. Seriously, it's like a, an, a historied one. And then meanwhile we have all this new demand, HBM specifically, the highest end, you need the most memory, the, the trade ratio is crazy. So each, you know, each bit of, uh, of HBM is essentially a 4X multiplier onto DRAM. And then now, so we, we've completely constrained, took all the DRAM capacity. We just came out of this shortage, so no one invested in any clean rooms or capital equipment or anything like that. People got like massively free cash flow negative. No one's spending a cent, okay? People could go bankrupt, you know?

    17. SW

      Yeah.

    18. DO

      So you, they haven't invested in these three-year-long lead time items, and then now there's the like more demand than God, and it also evaporates the middle layer because the KV cache offload, and then boom, you're just looking at the supply-demand and you're like, "Yeah, this is not gonna catch up for like two years." I think the thing that's like so interesting is the supply chain squeeze because these clean rooms take two years to make, man. And effectively everyone paused, and how bad the last cycle was really forced everyone to completely pause altogether in terms of adding any new capacity.

    19. SW

      Yeah.

    20. DO

      And so now we're a few years later and all the supply is gone. So I mean, people are- I mean, it's just, it's crazy. We- I, uh, our post, our conclusion is like we, we could see DRAM prices like go up 100% again. Like it's, it's gonna be the point where... And this is like also example like really interesting in the whole thing. Another 100% I think is demand destruction. I think you will start to have demand destruction from-

    21. SW

      What does that look like?

    22. DO

      Um, where hyperscalers maybe purchase less or something like that on the margin. On the margin.

    23. SW

      Yeah.

    24. DO

      Right? Because they're like, "Okay, well, what if I just really focus on this energy aspect instead?" And also ironically, all the energy, um, so like every- not every data center in America, but like many, many, many, most of the data centers in America are delayed. So you had this thing that's supposed to come on in 12 li- months, it's coming on in 18. Maybe what you can do is you can play chicken with memory prices and you can kind of push out. Of course, everything you have in the pipeline you, you pull forward as hard as you can, okay? You pull forward, you double, triple order, and then the DRAM and the HBM guys are like, "Oh my God, how? Look at all this demand." And then at some point in time what happens is you say, "Well, we pulled this all forward. You know, we have- the power's gonna constrain us anyways. We're gonna like kinda chill out the orders." And historically that's when the memory market- that, that's what causes the crisis, uh, the, the prices to drop. Realistically, just looking at, at the aggregate demand of how much we've- Purchase in term- terms of power. It just seems like the gap is just huge. It's completely off to the point where the most obvious logical leg of the AI- the AI trade is effectively investing in memory-

    25. SW

      Is-

    26. DO

      ... capacity, yeah.

    27. SW

      Well, not, not to ... Okay, maybe it's, uh, you could say SK hynix and, and Samsung-

    28. DO

      Uh, Micron

    29. SW

      ... Micron, and all the- all the semi... Like, Semicap has been ripping. Which like, uh, b- by the way, when I was in, uh, Valley as me, we ... A majority of ... A lot of money we made was just being on Micron-

    30. DO

      Yeah

  16. 1:56:47 – 2:06:12

    Writing habits and why he still hikes: weekly cadence, low slop tolerance, and self-mastery

    1. SW

      Uh, let's do the transition to a couple personal things and-

    2. DO

      Yeah, sure

    3. SW

      ... as the, the end. How do you write? 'Cause you, you write-

    4. DO

      A fuck ton.

    5. SW

      Yeah, I do. I have been writing a little bit less these days now that I'm, like, in the SemiAnalysis, uh, mega mind. I definitely write a lot. Um-

    6. DO

      Z- a- and, like, you kept going with Fab-

    7. SW

      'Cause I-

    8. DO

      ... for a while. Okay, dude, to clear, that was really... So- so- so look, I'm still trying to do Fab 'cause I- I- I do feel deeply connected to writing. Um, let's just specifically talk o- on this a little bit.

    9. SW

      Yeah. Just- just- just, like, explain yourself, you know? [laughs]

    10. DO

      Okay. So, um, the thing, uh... Before L- LLMs came around, the thing I felt the strongest about, my- my number one information skill, is I was able to read and synthesize and process at, like, really high speed, really high throughput, decently high comprehension, the adjustment is speed in terms of comprehension, almost anything. Like, when my... Like, when my friend gets a PhD, I go read their paper. I was like, "Oh, I have a pretty good i- idea of what you're doing." I was like- like, hey, when I was interested in semiconductor book, I literally raw-dogged some textbooks. Whatever, the comprehension was not very high, but, like, hey, whose comprehension is, you know? Um, but I was able just to, like, push through these books and learn. So I've always loved reading. That's, like, my- my number one original competitive skill set differentiator, and also something I, like, loved as a kid. Crazy reader when I was a kid, always have been. And then, um, starting the Substack, which has been really fun actually, 'cause I just really wanted to get my story out. Like, the things I cared about. Closed the loop for writing for me, 'cause I love... I love reading so much, it makes a lot of sense that I love writing. I think what really helped is I wrote every single week for, like, since October 21. Like, consecutive streak for a long time. The streak has been a little broken as of late. SemiAnalysis plus Fabricated Knowledge is pretty hard to do.

    11. SW

      Yeah.

    12. DO

      But, like, all of '24, I think, like, we're just talking just, like, every single da- every single week I will put something out, right?

    13. SW

      Is it, like, a hard rule, like one a week?

    14. DO

      It was a hard rule-

    15. SW

      Okay

    16. DO

      ... one a week.

    17. SW

      Yeah.

    18. DO

      Uh, at least an attempt to two.

    19. SW

      Yeah.

    20. DO

      And so, uh, I think one of the best ways all the people who write about... who write about writing all say the same thing. You need to just be writing. Um [laughs] -

    21. SW

      Yeah

    22. DO

      ... and so that's how I- that's how I start.

    23. SW

      So writing every week, then, huh?

    24. DO

      Yeah, it really helps. Um-

    25. SW

      [laughs]

    26. DO

      Well, I was gonna say, what's crazy is, like, it's- it's kind of hard these days, and I... and LLMs kind of have really... I don't know. I don't like LLM writing.

    27. SW

      Yeah.

    28. DO

      I do like it for ideation, like making outlines.

    29. SW

      Yeah, yeah, research.

    30. DO

      Here- here's my un- un- organized thoughts, make it into an outline, and then, like, you know, I'll even be like, put bullet points in the outline, and I'll literally read the outline and then, like, ideate and write in parallel. But yeah, that's- that's how I feel about writing, I guess. Write more. I have a strong... Uh, for nonfiction writing, I really like this book called On Writing Well.

Episode duration: 2:06:43

In the uListen app, the transcript lights up word by word as you listen. Get uListen

The published transcript ends here. Continue watching on YouTube

Transcript of episode nE32Zu_SZ1Y

Get more out of YouTube videos.

Read along on your phone, search it beside the video, or ask your favorite AI app what was said.

iOSAndroidClaudeChatGPTChrome