Dan Shipper interviews podcaster Dwarkesh Patel about how he uses AI—especially Claude, Claude Projects, and custom tools he has built—to read, learn, think, and prepare for interviews. Topics covered: using LLMs to remember everything; his podcast prep workflow for understanding complex topics (AI hardware, geopolitical crises, the genetics of human origins); why being an early adopter of technology matters; his taste in books and how he uses LLMs to learn from them; how he thinks about building a worldview; and his quick takes on AGI and P(doom). The episode ends with Dan and Dwarkesh using Claude live to research for an upcoming podcast recording. Resources mentioned include Dwarkesh's interview with Andy Matuschak on spaced repetition, the books Medieval Technology and Social Change, Will Durant's Fallen Leaves, and The Great Divide, and upcoming guests David Reich and Daniel Yergin. # Channel Presentation Observations: "Best of the Pod: Dwarkesh Patel's Quest to Learn Everything" ## Video Format - **Interview/conversation format**: The host (referred to as "Dan") interviews Dwarkesh Patel about his AI-assisted learning workflows. Evidence: "Doresh, welcome to the show. Thanks for having me, Dan." - **Sponsored content**: The video includes a mid-roll sponsor read for Google Gemini. Evidence: "This podcast is supported by Google... one of the product leads for Google Gemini." - **Screen-share demonstration style**: Guests share screens to show live tools (Mochi spaced-repetition app, Claude projects). Evidence: "I'll share my screen... it literally is just like I'm going through." ## Host Self-Presentation (Observable) - **The host identifies as a weekly writer and interviewer**: "I have to write every week... I'm forced to take a view on something." - **Host expresses alignment with "smart content" creation**: "You're one of the people that inspire me to make smart content." ## Intended Audience - **Intellectually curious creators and readers** interested in AI tools for learning, reading, and interview preparation. Evidence: the deep-dive discussion of spaced repetition, Claude projects, and reading workflows; host's aside "for the audience who is listening." - **Audience assumed familiar with podcast/intellectual figures**: References to Andy Matushak, Tyler Cowen, Carl Shulman, Nick Land without extended introduction. ## Claimed Scope (Guest's Description of His Own Channel, Quoted on This Channel) - Dwarkesh describes his podcast's mission as improving through accumulated knowledge: "I think of the larger mission of the podcast... Why does the podcast get better over time? It's because basically I'm getting smarter or learning more things." - His self-stated motivation: "I really just want to know everything." - Host's characterization of the guest's show: "the go-to show for smart people to learn about AI, but you also kind of branch out into lots of other things like geopolitics and history." ## Content Scope Demonstrated - **Topics covered**: AI tools in workflows (Claude, spaced repetition with Mochi, Hugging Face), history (Medieval Technology and Social Change, Caro's LBJ, Kotkin's Stalin), genetics (David Reich), philosophy (Wittgenstein, Plato, Rorty), AI hardware (Dylan Patel, semiconductors), and AI research (Collin Burns interpretability). - **Cross-disciplinary breadth is demonstrated, not just claimed**: The conversation spans semiconductors, ancient DNA, feudalism, and pragmatism within one episode. ## Explicit Self-Description vs. Demonstrated Pattern - **Self-description (by guest)**: Interview show aiming for questions "I would like to have if I was getting dinner with one of these professors or CEOs." - **Demonstrated**: Guest shows concrete preparation artifacts — question lists grouped by theme, uploaded book EPUBs in Claude projects, spaced-repetition decks — supporting the claimed research-intensive prep process. # Delivery Observations: Dwarkesh Patel Interview Segment ## Overall Format - **Two-person interview with live screen sharing.** The host (referred to as "Dan") interviews Dwarkesh, who repeatedly pulls up his actual tools mid-conversation (Claude chats, a Hugging Face space, Mochi spaced-repetition deck, Claude projects, prep documents). - The conversation is **demo-driven**: abstract claims about workflow are almost immediately grounded in on-screen artifacts, e.g., > "let me just cla.ai uh projects. So, if I go to um I literally just like..." ## Tone and Register - **Casual, conversational, hedged.** Both speakers use heavy fillers ("um," "uh," "like," "you know") and restart sentences constantly. - **Mutually admiring and enthusiastic.** The host opens with praise: > "you do the best most, like honestly the smartest interviews in AI that I found." Dwarkesh reciprocates later: > "Yeah, I couldn't have said it better." - Dwarkesh frequently **downplays or self-interrupts**, e.g., > "I'm not trying to make this podcast all about AI hardware. It just happens to be the last podcast I did." ## Recurring Phrases and Verbal Habits (Dwarkesh) - **Question-asking as an explanatory device.** He repeatedly frames his AI usage as questions: - > "Wait, step back. Why is this necessary? What's going on? How do I think about the broader context of what's happening here?" - > "what's going on here? Can you help me explain this?" - **"Super helpful" / "incredibly useful"** appear repeatedly as his default evaluative phrases: - > "it's super helpful to chat with Claude to make sure I'm on the right track." - > "That's that ends up being incredibly useful" - > "it's incredibly useful to be able to like have this thing where..." - **"I would have totally forgotten"** as a recurring justification for his methods: - > "I would have totally forgotten about this if I hadn't made a card for this" - > "I would have totally forgotten he names all these different ancestral groups" - **Stuttered repetition for emphasis**, especially on pronouns: > "I I I I really just want to know everything, right?" and > "I I I I I find them to be super compelling as thinkers." - Frequent **rhetorical tag questions** ending assertions: "right?", "or whatever," "and so on," "that kind of stuff." ## Teaching Habits - **Concrete example after abstract claim.** When describing spaced repetition, he immediately demonstrates with real cards: > "um multi- query uh attention to not have to use KV huge KV values and then sharing KV values between layers..." - **Self-aware digression, then return.** He flags tangents explicitly: > "And sorry, I'm just going getting nerd sniped and just going on riffs here." - **Builds from simple to elaborate.** Pattern: name the tool → show it → explain the underlying principle ("It's not just about learning the terminology. It's about understanding the underlying concepts."). - **Uses counterfactual reasoning** to justify methods: > "it's like every day you're reread the same key terms the same concepts and you're you start over from scratch." ## Host's Communication Patterns - **Enthusiastic interjection and steering.** The host frequently interrupts with affirmations and redirects: > "I love this. This is super interesting." and > "That's really interesting. Wait." - **Recaps Dwarkesh's points** to transition: > "you're kind of like it's a reading companion. You're getting more out of the books you read from that." - Uses **"like" as a universal connector** and repeats words for emphasis: > "I I I love that. I love that feature." - Occasionally **admits ignorance** to prompt explanation: > "I'm a newbie to David Reich's work." ## Vocabulary - Tech-native vocabulary from both speakers: "context window," "embedding search," "EPUB," "prompt," "project knowledge," "workflows." - Dwarkesh mixes **technical and humanistic references** fluently — Wittgenstein, Plato vs. Aristotle, Robert Caro's LBJ biography, Will Durant's *Fallen Leaves* — alongside H100 clusters and attention mechanisms. ## Stable Patterns vs. Isolated Moments - **Stable (well-supported by repetition):** question-driven framing of AI use; "super helpful"/"incredibly useful" as evaluative defaults; demo-driven conversation; stutter-repetition emphasis; counterfactual justifications for learning tools. - **Isolated moments (insufficient repetition):** the "nerd sniped" self-description (used once); the "Claude 6 in the sense of" comparison for polymathic thinkers (once); the explicit request for advice ("Do you have suggestions on what I should be doing?") — a one-time vulnerability moment, not a pattern. ## Uncertainty Notes - Speaker attribution in the transcript is sometimes ambiguous after "> > >" markers; a few quotes (e.g., in the worldview discussion around [1849]–[1930]) are assigned based on content cues and could be misattributed. - Tone features (enthusiasm, warmth) are inferred from word choice and interjections only; no audio/visual delivery cues are available in this transcript. # Position Extraction: "Best of the Pod: Dwarkesh Patel's Quest to Learn Everything" ## Speakers - **Dwarkesh Patel** — podcast host (identified explicitly in transcript via host introduction of "Doresh"/Dwarkesh and discussion of his show) - **Dan** (host of this episode) — conducts the interview (identifies himself: "Thanks for having me, Dan") - **David** — Google Gemini product lead (ad read only) --- ## Positions & Reasoning ### On casual reading being low-value - **Dwarkesh**: Casual reading is "basically wasting time or entertaining myself." He attributes this insight partly to his interview with **Andy Matuschak** on spaced repetition — "if you pick up a random book and start reading, you're not getting that much out of it." - Supporting reasoning: casual reading means "every day you're rereading the same key terms... you start over from scratch." ### On AI's usefulness shift for research - **Dwarkesh**: A year ago (post-GPT-4 era), AI was "completely useless" for prep — producing "banal" questions. Newer Claude models are "intelligent and interrogative and can consider the context." - Qualification preserved: models are "still not that good at like what should I ask this person" — question generation remains his job; AI helps with research/understanding instead. ### Spaced repetition workflow (Mochi app + Claude) - **Dwarkesh**: Uses Claude (via a Hugging Face space or copied prompt) to generate spaced-repetition prompts in Matuschak's style; adds them to **Mochi**. - Example retention cards: multi-query attention / KV sharing; David Reich's ancestral-population facts; technical AI hardware concepts. - **Claim**: He regrets pre-Matuschak episodes — "in many cases, I didn't take that much away" from world experts. - **On why retain knowledge when Claude can answer anything**: retention is "not necessarily remembering this information" but enabling **future learning** — "learning compounds... you can't do that if you basically forgotten most things you've learned." He describes making cards about things he doesn't yet understand (e.g., Collin Burns on interpretability) that make sense later. ### Deep engagement with difficult texts via Claude - **Dwarkesh**: Uploads EPUBs to Claude Projects; interrogates arguments (e.g., Nick Land's accelerationism: "I don't get it. What does he think is wrong with human society...") to find "a blind spot in their thinking or is this just me being confused." - **Position on reading originals vs. AI**: If "you care about the ideas and you think the ideas are timeless," using Claude is "totally valid" — he rejects the "you need to read the specific syllables that Wittgenstein used" view. - **Dan** (corroborating): Used Claude to re-read Wittgenstein before interviewing Reid Hoffman; "I don't need that anymore" (i.e., grad-level study). Also notes uploading texts to projects when models don't know obscure books. Says Claude is "so good for reading old science books because it can tell you what's outdated." - **Dwarkesh** on Claude vs. ChatGPT: ChatGPT's context window "isn't that long... chops it up"; Claude lets you "throw a ton of stuff in the context window and that just makes a big difference." Also: invest in workflows now even if imperfect, since "as they keep getting better you're getting the returns from that." ### On "one thing explains everything" books - **Dan's challenge**: Cites *Guns, Germs, and Steel* as a case where the thesis "turned out to be totally wrong." - **Dwarkesh's response**: Concise answer — "just don't read the ones that do it poorly." Warns of a **public-intellectual failure mode**: strong discipline work → broad successful book → "theory of everything" follow-up that is "not that satisfying." - Counter-position: loves big-scope biographies — **Caro's LBJ** (opening with Comanche raids, Texas rural life, electrification) and **Kotkin's Stalin** (opening with Bismarck) — because "you cannot understand the very specific topic I care about unless I tell you everything." - Creator takeaway: fear of being pigeonholed is misplaced — "you can find the entire universe in the narrow." **Dan** agrees ("couldn't have said it better"). ### Motivation for learning - **Dwarkesh**: "I really just want to know everything." Cites a Will Durant passage (*Fallen Leaves*) about reaching a "plateau of higher understanding" as resonant, though he says he's "nowhere close." - Admires thinkers with "self-consistent and deeply interrogated world models": **Carl Shulman, Tyler Cowen, Byrne Hobart** — with the qualification "there's many things they can still be wrong about... you always have blind spots." Example: Tyler on finance-as-%-of-GDP; Carl estimating AI hardware growth via algae bloom growth rates. ### Developing a worldview / writing - **Dwarkesh**: Started publishing "riffs" on books on his website; example: Pinker's *The Language Instinct* and the later-found FOXP2 gene. He asks Dan for suggestions — an open question, not a settled position. - **Dan**: Blog posts force you to "take a view"; audience calls out self-contradiction. His current project: a ~10,000-word post "Seeing Like a Language Model" connecting LLMs to the appearance/reality distinction from Plato onward; uses a **Claude project** with an Apple Notes dump of fragments, a Rorty chapter (*Pragmatism as Anti-Authoritarianism*) as the spark, plus concept-clustering prompts ("Plato vs. the Sophists... how do language models differ from that paradigm"). Also maintains a "My Psychology" project with journal entries and goals so Claude "knows who I am." - Reciprocal effect: watching this, **Dwarkesh** says he should consolidate his research into writing accessible beyond the podcast; will publish via newsletter, possibly a mini-site ("I have to actually write it first"). ### Interview prep method - **Dwarkesh**: Prep docs are "just a bunch of questions grouped by category" — "not that complicated," but producing them is research-intensive. He memorizes questions and interviews off-the-cuff conversationally; the doc is a fallback/sending-ahead artifact. - **Dan's synthesis**: "writing the doc is the prep itself" — Dwarkesh agrees implicitly (no contradiction raised). ### Live demo: prepping for David Reich - **Dwarkesh** on Reich's work (Harvard geneticist): ancient DNA has "made many academic disciplines irrelevant" by providing empirical data on migrations and population replacements. Techniques cited: - Y-chromosome vs. mitochondrial DNA lines to distinguish intermingling from violent population replacement (invading male line overtakes; female line persists). - Detecting social stratification: e.g., Indian caste endogamy "thousands of years" without mixing at ~99%, more than expected even "from infidelity or rape" — modern Indian culture legible in the genetic record. - On sequencing: "they grind the bone" with extraction techniques (offered when he himself was unsure and asked Claude). - **Dwarkesh's side claim**: civilization emerged "rapidly and concurrently" in the New and Old Worlds after 10,000 BC; **Dan** states this was "totally new to me. I thought it was just in Mesopotamia." Dwarkesh cites **Peter Watson's *The Great Divide*** ("Peter Jackson" in transcript; book title given as *The Great Divide*) comparing New World (Caral/"coral," fishing-based, ~3000 BCE) vs. Old World civilization. --- ## Unresolved Tensions / Qualifications - Dwarkesh values AI tools but insists question-generation is still human work ("that's why I have a job"). - He admires "know everything" thinkers while explicitly denying infallibility ("I'm not one of these people who [think] you can just know everything and never be wrong"). - The "theory of everything" book failure mode coexists with his love of books that do require explaining everything — resolved only by his distinction (books driven by necessity of context vs. authors forcing grand theories). - Spaced repetition is framed as future-oriented, not nostalgic recall — a qualification he emphasizes twice. - Speaker uncertainty left visible: both Dan and Dwarkesh flag not knowing facts (Dan on concurrent civilization emergence; Dwarkesh on genome sequencing mechanics) and route questions to Claude rather than asserting. # Speaker Attribution Record — "Best of the Pod: Dwarkesh Patel's Quest to Learn Everything" ## Video Metadata - **Video ID**: `01a0f15a-dc84-7191-ac74-791114295d27` - **Title**: Best of the Pod: Dwarkesh Patel's Quest to Learn Everything - **Format**: Interview/clip episode with mid-roll promotional segment ## Identified Speakers & Roles | Speaker | Role | Evidence | |---|---|---| | **Dwarkesh Patel** (spelled "Doresh"/"Dwarkesh" in transcript) | **Guest** — host of the Dwarkesh Podcast | Introduced by host: "you do the best… most… smartest interviews in AI"; describes his own podcast workflow | | **Host ("Dan")** | **Creator/Host** — interviewer; likely the channel owner | Greets guest: "Doresh, welcome to the show… Thanks for having me, Dan" | | **"David"** | **Promotional voice** — self-identified "one of the product leads for Google Gemini" | Reads sponsor spot for Gemini/Veo ("V3 and Gemini") | > Note: The transcript does not explicitly state the host Dan's full name or channel identity beyond "Dan"; his status as creator is inferred from hosting and channel framing. ## Promotional Segments ⚠️ - **Google Gemini sponsorship** — explicit ad read: > "This podcast is supported by Google… Try it with the Google AI Pro plan or get the highest access with the Ultra plan. Sign up at gemini.google…" - **Anthropic/Claude product exposure** — Claude features (Projects, context window, cla.ai) are discussed extensively throughout; these are organically discussed by the speakers, not flagged as paid promotion in the transcript. ## Third-Party People & Works Referenced (Claims Attribution) - **Dylan Patel** — SemiAnalysis publication, semiconductor/AI hardware posts (guest's prior interview) - **Andy Matushak** — spaced repetition and prompt-writing methodology - **Mark Zuckerberg, Dennis Sabis(i), Patrick Collison, Reed Hoffman** — named as past Dwarkesh Podcast guests - **Carl Schulman, Tyler Cowan, Burn (Byrne) Hobart** — cited as admired thinkers with broad world models - **David Reich** — geneticist, Harvard, human origins (upcoming guest; his book is uploaded to a Claude project) - **Daniel Yergin** (transcript: "Daniel Jorgen") — author of *The Prize* - **Collin Burns** — alignment research papers - **Nick Land** — accelerationist writings - **Jared Diamond** — *Guns, Germs, and Steel* thesis (host characterizes it as "totally wrong" — the host's claim) - **Robert Caro** (transcript: "Ko/Carol") — LBJ biography; **Stephen Kotkin** ("Codkin") — Stalin biography - **Will Durant** — *Fallen Leaves* - **Steven Pinker** — *The Language Instinct*; FOXP2 gene discussion - **Richard Rorty** — *Pragmatism as Anti-Authoritarianism* - **"Peter Jackson"** — *The Great Divide* (per transcript spelling; not corrected) ## Tools & Platforms Cited - **Claude / cla.ai / Claude Projects** (Anthropic), **ChatGPT** (context-window comparison), **Mochi** (spaced repetition app), **Hugging Face Spaces**, **Jupyter notebooks**, **Apple Notes**, **Google Gemini / Veo** (sponsor) ## Provenance & Availability Limits - **Comment availability**: Not stated in source material. - **Curated metadata**: None supplied beyond transcript. - Transcript appears **truncated** mid-conversation ("that's really interesting.") — record covers only supplied portion. - Names with uncertain transcript spellings (e.g., "Dennis Sabis," "Codkin," "Doresh") are flagged as-is without correction beyond obvious phonetic matching. How is AI integrated into your work and in your life right now? \>\> So, a lot of topics I just find I have a vague sense of what's happening and it's super helpful to chat with Claude to make sure I'm on the right track. \>\> What is driving all of this? What do you think that's about? \>\> I really just want to know everything. Wait, step back. Why is this necessary? What's going on? How do I think about the broader context of what's happening here? Because I really can't ask good questions unless I have a good mental model of what they're talking about. This podcast is supported by Google. Hey everyone, David here, one of the product leads for Google Gemini. If you dream it and describe it, V3 and Gemini can help you bring it to life as a video now with incredible sound effects, background noise, and even dialogue. Try it with the Google AI Pro plan or get the highest access with the Ultra plan. Sign up at gemini.google to get started and show us what you create. \>\> Doresh, welcome to the show. \>\> Thanks for having me, Dan. \>\> I'm so excited to have you. For people who don't know you, I assume everyone knows you, but for people who don't, um, you do the best most, like honestly the smartest interviews in AI that I found. Um, you have like really incredible guests like Mark Zuckerberg, Dennis Sabis, Patrick Collison. Um, you you you've created like the go-to show for smart people to to learn about AI, but you also kind of branch out into lots of other things like geopolitics and history and stuff like that. It's it's really great and you're like you're just one of the one of the people that inspire me to like make smart content. So, I appreciate you coming on the show. \>\> Yeah, that's very kind of you to say. I mean, um, I've, uh, I've always been sort of trying to make have the conversations that I would like to have if I was getting dinner with one of these professors or CEOs. What would I want to ask them? And, um, I'm I'm glad other people enjoy them as well. \>\> Yeah, it comes through. Um, and I I think like it's it's really fun to get to like turn turn the tables on you a little bit because, uh, you've done some interviews, but but mostly you're interviewing other people. And I think um like it's probably on people's minds like how you use AI in your work in in your life and so and so that's what we're going to talk about today. So um maybe just stop start by giving us a little bit of an overview like um how is AI integrated into your work and in your life right now. \>\> Yeah. So it's actually changed a lot. I remember a year ago this was after I think it was after GPT4. Um I somebody asked me you know do you use AI to help you with your research or prep? And I was like not at all. It's completely useless in mid. it gives you these banal um you ask it like what should I ask so and so professor and it'll give you these banal where did you grow up what's your book about whatever so initially it was you know um terrible I think recently the models have gotten to just the point where with these like I don't know 40 or especially with the cl new cloud models they're intelligent and interrogative and can consider the context which you provide to them and so they're still not that good at like what should I ask this person because obviously See, that's why I have a job, right? So that I can come up with the questions. But for the research itself where you're, for me at least, I try to like ingest everything they've ever written. Um, all the rebuttals to their ideas, all the other considerations, and there's often a lot involved, especially given there's like many different fields I try to go deep into. Like the last interview I just did was with Dylan Patel, who writes semi analysis. It's a um it's a publication about semiconductors and AI hardware and so on. So like there's a bunch you have to learn and uh it it's I I mean I can go through my workflow, but it's incredibly useful to be able to like have this thing where I'm like what's going on here? Can you help me explain this? And I guess one bigger thing I've been thinking about is ever since I interviewed Andy Matushak, if you've if your audience is familiar, he's the guy who did um who talks a lot about how space repetition and other tools can enhance our ability to learn and how the normal mode of learning, you're actually not picking up that much. If you pick up a random book and start reading, you're not getting that much out of it. And I really have found that to very much to be the case to the extent that if I'm just like casually reading a book, I think I'm basically wasting time or entertaining myself. And I have come up with a couple of um different workflows and tools that help me really interrogate and make sure I've reinforced what I'm reading about or learning. And the a tool like and language model is very helpful cuz like it gives it it gives you the contact um the content in another context and you can like it makes it can quiz you if you want. So it's it's super helpful that kind of stuff. \>\> That's really cool. I think we should start I want to start back to front like with the the stuff you're using to read because I think the reading all that reading is sort of the input like one of the inputs to the interviews and then we'll get into the interviews. Um and I'm really excited for both. So, so let's start with with using AI to read and to learn. the um you know so as I was talking about like the one of the main things I think is important is if I'm studying a topic over the course of a few weeks it's um especially if it's a difficult topic it's like new to me it's incredibly important that I've I'm not just casually reading because if you're just casually reading it's like every day you're reread the same key terms the same concepts and you're you start over from scratch. Um, so one of the things I like to do, for example, I was recently interviewing Dylan, right? So if I go to his publication, semi analysis, there's just a ton of lingo and things you have to understand. Um, so the new one was pretty interesting. It's talking about why nobody has built a huge training cluster yet. And then first thing I do is just like what are the key ideas and concepts I really need to understand. So I made myself um a hugging face. You honestly don't need to do anything like this. You can just it's pretty simple to have claude build you hugging face space or if you prefer it what it literally does is like apply this prompt to everything I paste in. So just you can you just copy paste that prompt into claude yourself. But basically it just has I copy pasted some of the things in Andy Matushek's post about how to write good prompts and I just ask cla to make those prompts for me space repetition prompts. So um when I do this hopefully in a few seconds we'll get something back. um initially this will give just give me some ideas of like what are the key ideas here I need to understand so um super useful right I can even zoom in a little bit so it's more helpful um so for for the audience who's listening like it's given me a bunch of question answer pairs that consolidate the key things I need to understand about this post about um you know we can go through the specifics here I'm sure that the actual specifics of AI hardware will bore But um a lot of the things where it's like okay if you don't get this you've like totally missed the boat here. And so you can start with something like this. I add it to my space repetition app. Um or I can just look through this and I'm getting a sense of like oh okay here's what it would take to train a GP4 level model on a 100,000 H100 cluster. What are the three main types of parallelism you need to use to train on a big cluster or whatever. And this is on for a technical post. On other kinds of posts there might be different kinds of cars that come up for history. It might be a different kind of thing. For philosophy, it might be a different kind of thing. So, this gives me a lay of the land. \>\> I love this. This is super interesting. I like I feel like I can go in like a bunch of different directions, but what where I want to start is like um how are you reading and when are you reading? So, is this like are you using this specifically for um uh for reading that you're doing for the show or are you just doing this for any reading that you're doing that you feel like is serious and you really want to learn? \>\> Um both. So, just this weekend, I was reading um I forgot the author's name, but it's a book called Medieval Technology and Social Change, and it's about how different things that were developed through um the last 1,00 to 500 years, technologies, like the steerups, how they affected society, and it's like you can it's entertaining. You can read it. And then one of the things is like, okay, did I really understand what's going on here um with the relationship he's trying to elucidate? So afterwards, in fact, I have some claw chats where I was just going through um while I was reading it, um let's see if this recollects \>\> do it. I I want to know I'm I'm on the edge of my seat cuz I have this book. It's like sitting on the desk in front of me. Um and so I want to know what what you got out of it. \>\> Okay. So um first I was just asked to make space repetition prompts for me. First of all, I was just like I read the chapter. I'm not sure I got it. So just explain to me the chapter about how he says that stirrups created feudalism. Like what exactly was the connection here? So it it's a much more condensed like here's what's going on here. Basically if you understand this it's a useful scaffold so that when you're reading the rest of the chapter you understand where the pieces fit together. \>\> Have you tried like one one of the things that's that I've tried with this is like cuz sometimes it doesn't know especially for a book like that where it's like not that popular. Have you tried like one one of the things I do is create a little claude project and then upload the text if I can find it. Have you tried that? \>\> In fact, let me just cla.ai uh projects. So, if I go to um I literally just like I'm I'm a host of a podcast where I try to ask good questions. My upcoming guest is a geneticist and I just upload the I get the EPUB of the file. I convert the EPUB to a text using an online converter. I upload it to Project Knowledge. Then I I've only just started prepping for this guest, but I'll just have a bunch of chats where I'm like, um, you know, how how does he explain what groups made up modern Europeans? It has all the context in there. That's that ends up being incredibly useful, like you were saying. \>\> Yeah, that's so cool. I I I love that. I love that feature. Okay. Wait, let's go back to let's go back to stirrups and uh and this chat you're having with uh um uh with this book or about the book. \>\> Yeah. So, you know, it explains that the reason stirrups create a feudalism is because you needed um you needed a lot of land basically to support the kinds of people who become heavy cavalry, the knights. The knights need a lot of land in order to um have the income to have, you know, like uh armor and uh lances and other kinds of equipment and to train themselves. Um but you a knight is only possible if you have a stir up against which you can brace yourself as you're attacking with a sword because otherwise you're just like a Mongol who's shooting bows and arrows. So, um, but then then there's a bunch of stuff that's confusing here, like why is it that expensive to have be a knight that you need to like completely confiscate church lands in order to subsidize this night lifestyle? Um, and then on these kinds of questions, the author is dead, but it's just like I'm just like murky about it. I don't know what's going on. So, I can just um these kinds of things I can the book didn't even talk about, right? But I can always just continue the conversation with Claude and have it explain what's going on. Um, and so this is just like a recreational reading that Claude ends up being super helpful with. \>\> I think that's really interesting. What What do you think about um like books like this, like in your, you know, as a as a person who likes history a lot, books that sort of single out like a specific thing like the stirrup and then are like, well, you can trace all this stuff to that like one thing where it like makes so much sense. But then there are things like I don't know like Guns, Germs, and Steel where like Jared Diamond had that whole thesis about I can't remember the the exact thing but it's like people in warmer climates or I can't remember the exact theis but it turned out to be like totally wrong. Yeah. How do you feel about things like that? \>\> Yeah. So my opinion on these kinds of books there's there's one I mean the sort of concise answer is like yeah there's ones that do it poorly but just don't read the ones that do it poorly or something. There is a failure mode for public intellectuals where they initially start off with a discipline and they do some exemplary work there and then they write an initial broad book that's about how this idea explains a lot of the world and it does incredibly well and now they're in like public intellectual mode and now that the next book has to be like here's my theory of everything and it just not that satisfying. So, I do worry about those kinds of things. But, um, presumably the reason I don't know. I'm not I'm not into like reading 500page books about like uh ju just how this tear up physically worked. Like, what's the point of that, right? I do want to understand the implications. And maybe they're wrong, but um I mean, what else are we trying to do here, right? Do we just care about maybe you just intrinsically care about how the stereo physically works there? I I I will point out a couple of examples. So there there's a lot of interesting topics where you really can't get at the heart of the matter without just considering the whole story. And in fact, so a couple of biographies especially stand out in this way where if you look at Ko's biography of LBJ or Codkin's biography of Stalin, it's basically a history of this 20th century or in the case of Codkin even before the 20th century. Um, I think this uh KO books on LBJ start off with the Comanche raids on uh frontier settlers in the mid 19th century or something and it goes through rural life in Texas, why electrification was such a big deal, a whole bunch of other things right now. Um, so it's basically a history of the 20th century, but it has a very specific point of view or a specific locus of character that's moving the story along. And I find those to be incredibly helpful in getting a full picture of what's going on in an era. Um there's a couple other books where they really aren't trying to write a theory of everything. Like I don't think Carol's trying to write about like what is the history of the 20th century, but they just can't help themselves. They feel like you really cannot understand the very specific topic I care about unless I tell you everything about everything. And you know like um Codkin story uh biography of Stalin starts with the like Bismar's career as a military general and how that changed the way that different powers thought about um colonialism and the need to modernize and that's where it starts right and it's a biography of Stalin. So uh yeah I love those kinds of books. I think there's like a very just deep point about the universe being interconnected there, but there's also like a really interesting point for um people who want to make stuff like make writing or make podcasts or whatever cuz like there's this deep fear that everyone has about like being pigeonhold and it's like well if I pick this like really specific topic I won't be able to like bring all of myself to it or I won't I won't be able to be like multifaceted and it's like no no no if you just pick one guy Lyndon Johnson and really get deep into him you have to explain everything else about the world in order to explain him. And I I love that. And like as a creator myself, like that's the thing that I think about when I'm like, "Oh, maybe I'm getting too narrow here." It's like, "No, no, the narrow is actually good. You can find the entire universe in the narrow." \>\> Yes. Yeah. Yeah. Yeah. I I couldn't have said it better. \>\> Yeah. Um Okay. So, so basically what I'm what I'm seeing right now is you're using Claude when you're reading books that you care about, you care about like learning from and you're using it a little bit to like prepare your prepare the mind your mind for like what you're about to read, which I think is a particularly good for like difficult books or for like thinking through a particular argument before you like go through it. You're asking questions. You're asking questions. So, you're kind of like it's a reading companion. You're getting more out of the books you read from that. But then you kind of take take your what you've read and throw it into this um this uh card generator. \>\> Yeah. And so that that's um mostly it's just chatting with Claude. And so let me see if I can find a better example. Um so I mean a lot of topics I just find um I' I've have a vague sense of what's happening but I don't really like get it. And it's super helpful to chat with Claude to make sure I'm on the right track. I one was like um you know Dylan has a couple of posts about how why packing as a technology is super uh necessary for these advanced chips. I'm not trying to make this podcast all about AI hardware. It just happens to be the last podcast I did. So that's what you're getting. But um then I'm I was it's like a confusing it's like a five series post about how advanced packing works and how you know what what the technical specifications are and I'm like wait step back what why why is this necessary? What's going on? Um all kinds of other questions about when there's questions about h I'm worried about I might get too deep in the weeds when I'm just explaining. Yeah. Basically, I'm just like, how how do I think about the broader context of what's happening here? Because I really can't ask good questions unless I have a good mental model of um what they're talking about like I really get where all this is fits together. \>\> That makes sense. And so and and and so cloud is kind of like the first thing you flip to when when you when you want to know that. Are you using it on mobile or using it on desktop? \>\> Desktop. \>\> Okay. Interesting. So, you're doing most of your like reading and research stuff on desktop. \>\> Yeah, that's right. \>\> And what do you think about like uh just Claude being really great right now and like chat like I assume your CHBT usage is lower than it used to be. Yeah, I think these things will keep getting better over time and I um I I you know I I I yeah I think just like getting in the practice of using these tools. I'll talk a little bit about how these tools relate to my post-production process. Initially it was kind of useless but I did spend a few weekends trying to write a few prompts and create a workflow. At the time it was basically useless. Now it's actually ended up being useful and I can use the same you know Jupyter notebooks or whatever to get things done. So um it is worth investing in getting even if they don't work perfectly now to get them part of your workflow so that as they keep getting better you're getting the returns from that. \>\> Yeah that makes sense. So so I want to just go back to the uh the flat the the the ani card generator the the space repetition card generator. So, as part of this, once you once you've done all the sort of like conceptual um uh you know, clearing the ground conceptually for yourself to like kind of understand the the basics of of what a guest is talking about or an idea that you're interested in, then you're kind of um you're adding to your your flash card so that I I guess so that it you retain the information past even when you talk to that guest. Is that right? \>\> Yes, that's right. Um I mean I I think of the larger mission of the podcast is to consult. Why does the podcast get better over time? And it's because basically I'm getting smarter or learning more things. I'm reducing my ignorance around a bunch of topics. And so to if I don't do that, I mean, I think about all the episodes I did before I interviewed Andy and started using space repetition. And I just like really regret it cuz I talked to all these world experts in a ton of different domains. And to be honest, like in many cases, I didn't take that much away. I vaguely remember some things. And now that I use I can walk you through the kinds of cars I make and the space operation tools I use, but it's like totally a gamecher in terms of what I can retain. And in fact, I think it's not even about making sure I remember what I discussed in a previous episode or what I learned previously. It's more about future learning because I'm sure you've heard the saying about um the uh you know learning compounds because you can use what you've learned in the past to um learn future things because they all interconnect. Well, you can't do that if you basically forgotten most things you've learned in the past. So I my learning has for future other things has become much faster because I have cached all these different um concepts and figures and facts. So but future things are just like I I understand how everything fits together much more. It's not even about the past. It's really about future learning. \>\> Can we see your uh I don't know what what you use for for space repetitions. Can we see your your deck? \>\> Yep. I I will point out by the way as a side notes one one use case of claw that ended up actually being pretty useful sometimes you read obscure phil like I was reading Nick Lan's selected writings about AI and his accelerationism and I was like what's going on like I genuinely I'm like what is his argument basically like why does he think that the AI takeover and the whatever thing it creates in the aftermath will be goo because he's a smart guy I'm assume he has an interesting argument so I upload the PDF of his selected writings I just asked Cloud like Okay, so why does he think it's a good thing that AIS take over humans? And he they it offers a summary like initially this isn't necessarily that helpful cuz I kind of did read this in the essay. But what's what's helpful is that when you go through and I'm like I respond like I don't get it. Like what does he think is wrong with human society that you can't uh you have to erase it and then he gives explanation. I'm like I still don't get it. Like what exactly are you talking about here? And then like here's what I do with the podcast, right? have the guest on and I ask them, "What do you mean here? Like, I I I disagree. Here's a contradiction, whatever." And going through their writings with Claude and like, "Have I have I actually found a sort of blind spot in their thinking or is this just me being confused about their ideas?" is super helpful. \>\> That's that is really interesting. It's like um you can you can get you can get down to a deeper level before you talk to them so that you can start there with them as opposed to like starting at the surface. \>\> Exactly. \>\> Which is really cool. I I use that too for like um for for difficult books like not necessarily for like interviewing the author of those books but like for example I interviewed Reed Hoffman like I don't know a month or two ago and I wanted to talk to him about the kind of like intersection between philosophy and AI and he was like um he he like uh almost became a philosophy professor like at Oxford wanted to like was really deep into Vickingstein so like I read a bunch of Vickenstein um which I hadn't read in a while and I I just used Claude for it and it was like so much better. Um because I like I haven't taken a Vickenstein class or maybe I took one in college like a long time ago, but I've read him a lot and it just there are always those those points in those kinds of books where you're like I think I I know what they're saying, but like I'd probably have to go to a a grad graduate school and like get a masters in this to like really know. And Claude is actually like makes me be like oh I don't need that anymore. Like I I any book I want to read like this like I basically know. And it just helped me so much in that in that interview because I could just ask read like really deep Vickenstein related questions and he could answer them. \>\> Yep. Yep. I think that's totally legitimate. I think some people would be like, "Oh, you need to read it in the original blah blah blah." I think if you care about the ideas and you think the ideas are timeless and not the ideas are not about the specific kind of pros that the original author used, but just generally like what is the essence and the gist of what's happening here. If you care about the ideas, and I think this is totally valid, right? I I don't just agree with the people who are like, "No, you need to read like the specific uh syllables that Wickenstein used." \>\> Yeah. I mean, I'm also just saying like I'm I have the book open and then I just take one of his like statements and just throw it in there and then it's like here's here's what what it means or whatever, which which I think is really great. Um, okay. So, you're going to you're going to show us the uh the the space repetition card. So, what what app is this? \>\> This is Mochi. Um, interesting. It's like an I this is the one I use. Um why \>\> uh so that actually I don't have any cards today because I just went through them this morning but let me give you a sense of let me give you a sense of what kinds of things I have right so \>\> I have um if you go through history recently I've been planning on interviewing David Reich who is a geneticist who explores human origins and these are especially cases where just like reading the book I'm like I would have totally forgotten he names all these different ancestral groups and how they combined and in what eras was, you know, when did the Yamina people come through Europe? When did the Anatolian hunter gatherers, you know, wash over uh Eurasia, all these things that was just like you read it in one year, it goes out the other one, unless you make cards for it. And so I made a ton of cards about this kind of stuff. Um, and you know, so there's examples of that here. It's especially useful for hardware and um technical things. So here I feel like if I don't make cards, I'm just constantly relearning the same things because I didn't learn the lingo the in the right way first. It's not just about learning the terminology. It's about understanding the underlying concepts. Let me give you a good example of that. So um maybe I I'll step back and I'll explain like I go through these cards in the morning. If I maybe you can see what it kind of looks like if I do the craards thing. Um I can go through them and right now I'm like I remember this right. I remember it's u this is the first one that came up randomly but it's um multi- query uh attention to not have to use KV huge KV values and then sharing KV values between layers and using local attention and that's the answer. Now, um it seems sort of trivial right now cuz it's just like three things, but like I would have totally forgotten about this if I hadn't made a card for this as soon as I read the blog post. And then it just like I've wasted my time in the future if I'm learning about these technologies in a different context. I just like don't have the connection to what was happening here to connect it to. Right? If I go to a different um category, if I go cram cards, um this is the the white thing. thing. I would have totally forgotten about it if I hadn't made these cards. Um I Yeah, I'm just a big fan right now. I I sort of I've become a space repetition fanboy these days. \>\> How do you think about like the the usefulness of space repetition in a world where like any of these questions is possibly is like pretty much answerable like with claude with like a you know one one search. \>\> Yes. So I think it's about not necessarily remembering this information but when a future thing comes in you understand like the conceptual in fact let me give you a good example of this right so I remember sometimes I actually make cards about facts that I don't even understand in the moment but in the future the as I learn more about the field as a as a sort of territory becomes more clear the things I said in the card make more sense to me so if I um I was reading some of Colin Burn's papers And so I made this card about like why Colin Burns thinks that uh alignment is a tractable problem or understanding what model thinks is a tractable problem. And um at the time I wrote things down about like uh you know features are in a linear space. What the what does that mean? Um or like we can sort of see features in other sorts of categories. And at the time I'm like I have no idea what this means. I'm just going to write it down cuz I read the blog post and there was no point of reading the blog post if I'm not going to make the card. Later on, as I learned more about how the residual stream model of how attention works, you know, how what that is and so forth. This card made much more sense to me in the future. But I would have just like totally memory hold or not even memory hold. I would totally forgotten this content which required future understanding if I hadn't made a card of it. And then when I see the card again in the future, I'm like, "Oh, this is what Colin Burns meant now that I understand how attention works. This is what it means, right?" Um, \>\> yeah, this is this is really interesting to me. So, I want to get into some of the like the ways that you use AI for for interview prep. Um, because I think we we've mostly covered the reading stuff, but before we do that, I just want to like understand like what is driving all of this? like it feels like you are just consuming massive amounts of information and turning that into knowledge in your head. Like you have this in sort of just overdrive of curiosity which I actually resonate with a lot. Like I'm I'm surrounded right now by books. Um and I'm just sort of like um curious for you what what that what do you think that's about? Um I think I um I've uh I I I I really just want to know everything, right? It's I I don't know how to express it. There's a beautiful passage in a Will Durant book as he's turning 90 where he's writing a memoir basically of his main ideas um called Fallen Leaves. And there's a passage on philosophy where he says, you know, as as you get older, maybe with all the philosophy and history I've done, I can I've reached some plateau of higher understanding and clearer insight or at least I've understood that such a thing is possible. And something like that just resonates with me. I don't know. I just like I find that idea really appealing. I'm nowhere close to it, but I just hopefully in the years to come that'll just be a thing that um I also really admire people I've had on the podcast who do have these self-consistent and really deeply interrogated world models. You know, I've interviewed these guests and some of them um people a couple names come to mind, people like Carl Schulman or Tyler Cowan or Burn Hobart. they it feels like they've really read everything and you know everything you know is a subset of what they know and I just um I I I find them to be super compelling as thinkers. Of course there's many things they can still be wrong about. I don't I'm not one of these people who buy like there's like a thing where you just know everything and you can never be wrong, right? you always have blind spots, but the abil their ability to which you can see when you talk to them to connect anything you ask them about and they're like clawed six in the sense of like you start talking about why has a fraction of finance as a percent of GDP. I remember asking Tyler this and he has a right off the cuff just super interesting answer that connects a bunch of different disciplines. Um, you asked Carl about like how fast um, AI hardware could grow and just like done the sort of firmy estimates on how fast algae bloom and how much solar power they consume and um, how many fabs is making it just like I I I find that sort of compression of the input they've ingested over their lives and they can not only do they know that stuff, but they can really connect it in a really interesting and compelling novel way. I I I I find it super compelling. \>\> And and in terms of developing your own worldview, like do you have that anywhere where it's like you're creating like some sort of living document or is it just all in your head like all the stuff that you're learning? Obviously, you have the you have the cards, but that feels like more like um dots in the space rather than like uh the ways that they all connect and and how you think about everything all together as a system. Hm. I think um I've been trying to do more of this recently. Uh and now that I've sort of built up an underlying maybe vocabulary or understanding because of the podcast, it makes sense to do more of this. Something I've been doing recently, if let me pull this up. I've only just started. Hopefully, there'll be more by the time people are looking at this, but um I've started writing, you know, riffs on different books or things I read. And it if I go to um it's basically on my website and um so just like I can read a book and I have questions or I connected with other things I've read. I I remember for example in when I was in Steven Pinker's language instinct he was writing the book before the fox P2 gene that can help explain human uh language was found. And so he has all these observations that are then later explained by the Fox P2 gene. Um, and so I can just sort of the sort of connection that you're talking about I can do by riffing on other people's ideas. I actually am curious. Do you have suggestions on what I should be doing? Maybe I should be writing more blog posts or what do you suggest I should do? \>\> Um, well that's that's a good question. So uh well before we get there like one of the things that this reminds me of I think Claude is so good for reading old science books because it can tell you what's outdated and what's what's not. Um, I do that all the time and I I love that. I love that little thing. But yeah, I mean I think basically like developing a worldview is like you have to just try, you know. Um, and you try over and over and over again. And I I do think like blog posts are uh really good for that, especially like, you know, for me like I have to write every week. Um, and so I'm like forced to take a view on something. And generally, if you're like intellectually honest, you like want one post to like somewhat like agree with the last post and your audience will call you out if you're like just disagreeing with yourself all the time. Um, so you're kind of developing a worldview that way. But for me, like right now, I'm actually like my big thing this um this quarter is like I I just have these like ideas that are simmering that are like sort of the relationship between like um language models and like some deep philosophical questions that we've been like talking about since like Plato, which is like the appearance, reality distinction and like how do we know what's true and what's knowledge and all that kind of stuff. Like I think there's a lot of overlap there and it requires like it's going to be like a 10,000word post or something like that. Um, and so what I'm doing is I just have like a Claude project with like I have all these like little notes and riffs and like and stuff and I'm just like going into Claude and being like, "Hey, like what's what's the thread here? Like what's going on? Can you help me like figure out like there's something in me that I have all these little ideas for, but I can't quite like put it into an argument that all makes sense?" And I think just honestly like sitting with that for like a couple months I will I will know what's in there, but there's something in there. \>\> Um and yeah, it's cool. \>\> Do do you make a clawed project to like here's some the things I'm thinking, how do they connect or like how do you keep track of those things as over those months? \>\> Exactly. I I mean I'll just show it to you. Um uh let's let me just pull it up. So, okay. So, if I go into claude, um, I have a couple different projects. Um, one project is seeing like a language model, which is the title of this big post, whatever it is. Another is Zen in the art motor maintenance. So, this is like a book that I'm reading as prep for this um this piece that I'm writing. Um, I've read it a bunch of times before, but like now I'm like doing a little bit of a deeper read. And so I have like the I have the uh the whole book uploaded and then I can like ask questions. Then I have another one that I love called my psychology which has a bunch of like journal entries uh goals I've set for myself um over the years. And then also like things I've observed about my psychology or things I'm working on like little aspects of myself that I'd like to grow or change. And so when I'm making decisions or thinking something through, I just go in there and it can reference all that stuff so it knows who I am. Uh which is really cool. Um, so in seeing like a language model, let me see if I could pull it up in the projects uh directory. Um, so I have like basically I have this one note in Apple Notes, which is like uh every time I have a little thing come into my head, I'm like I just I just put it in there. Like let me see if I can find it for you. Um um I just throw it in here. And this is like huge and messy and it's like different quotes from different books and like just different ideas that like come to me off the top of my head as I'm like walking around. And I think that there's like a thread here in all of this stuff. Um they're all like I can see how they're all related, but but like I can't quite pull it out. And so like what I've been doing is I just like throw it all throw it all in in here. We have uh we have this like all the all the quotes and all the ideas and fragments. I have a little bit of a draft, like an intro, and then I have a chapter of a book um uh by Richard Rory that I think is is is really good um called Pragmatism as anti- athoritarianism that like kind of sparked this whole thing. Like I read that I read an art I read a chapter of that book and then I was like suddenly like rereading like a bunch of Plato and like Aristotle and and like I was just down this huge rabbit hole. And so um like what I did for example is I put all that stuff in here and I was like hey I have a bunch of notes and some fragments for of text for a long 10,000ish word piece I want to write called seeing like a language model but I need to understand what I actually think and make a bit of an outline before I get started. In order to do that I need to understand the patterns of what I've been thinking and writing down and reading about can you suggest some ways that you can help me do this. I want to get from where I am to an outline. you have access to some fragments, notes, and early unfinished intro. And it just like has a bunch of ideas like thematic analysis or argument mapping or chronological development. And I'm just like sort of going down the rabbit hole with it where it's like um you know, I asked it to do concept clustering. So it's like, you know, one of the concepts that I'm playing with is the philosophical divide, Plato versus Aristotle, which I think is like not quite right. It's actually Plato versus the Sophists, but like it's it's it's close or the evolution of Western thought. It's like how does Plato like um uh uh how does Plato ladder up into the rest of Western thought and and into science and into just the way the western mind works? Um and then how how do language models sort of like differ from that from that um paradigm. Um, so that that's the that's the basic thing that I'm trying for cuz I I I I do have the reason I ask this question is cuz I'm selfishly like I feel like a little bit I haven't done the like big idea thing as much as I really want to cuz I'm I am writing every week. I am sort of like reacting to stuff and so I want to be a little bit more thoughtful. Um, and this is this is my like attempt to like put all of it together into something that like makes sense. \>\> Yeah. you know, as you're going through this, this really actually makes me want to write more because now that you're talking about it, now that you asked the question, I'm like, yeah, I I should be sort of consolidating the things I'm learning in a more comprehensive way. And in a way, that's also more useful and accessible to other people as well, right? I, you know, I spend weeks like learning about some random what, not random, but like the things I care about. I'm about to prepare for Daniel Jorgen, the guy who wrote the prize. this a history of oil or a geneticist um you know AI research or whatever to the extent that I'm getting something out of these research processes I should consolidated in a way that's not evident in the podcast itself. \>\> Yeah. I mean I I selfishly want you to do that cuz I'm curious what you think. \>\> Yeah. I appreciate that. You will send this out through your newsletter, right? Is is that the main \>\> Yeah. \>\> Yeah. Yeah. This this will go through through newsletter. I might do something special for it like um you know maybe maybe I'll make a little mini site for it when it when it launches but that's sort of in the future. I have to actually I have to actually write it first. Um so okay so so so let's I want to move on. I want to I want to talk about the uh how how you use AI to to sort of like do do the interview prep. Um so so let's let's move into that and then we can also um uh we can also um maybe even like prep for an interview together. \>\> Yeah. Yep. Okay. Let's do it. Um I honestly the interview prep is like it requires a lot of work but fundamentally what's happening is not that complicated. Like I can just show you a document I might have made in the past. I'll share my screen. So honestly it literally is just like I'm going through I come up with a bunch of questions and I sort of group them together in uh relevant categories or if I go to um if I was interviewing Dylan Patel sorry this is not the right one. Um just like a bunch of different yeah just like a list of questions basically. It's not that complicated, but the process of coming up up with them is, you know, very research intensive. So, we can go through like if I'm I guess I'm like only barely started preparing for, we can go through the process preparing for them. \>\> Yeah. Can can we can we I just want to stop at those questions like again selfishly because I think it's really interesting like you have these like long lists of questions that are organized by theme. Are you like going down the list or are you sort of jumping around to bed? It's really interesting because um I come up with these list of questions, but it's like it really never ends up being I ask question one and I ask question two and I ask question three. the it I you know I start off with an interesting question and if you listen to the interviews hopefully it comes off more as a almost conversation because I spend so much time preparing that I have these questions basically memorized and so the next one that is appropriate to their response if they say something about um you know me memorization in LMS I'll have a question prepared about that or related to that and I'll I'll just ask it next because that's what fits in together and so you know I'll have a list and this is what I'll send them if they ask for it. But like really just sort of me off the cuff like here's here's a question I remember that was relevant to this in in the actual interview. \>\> That makes sense. So like the the point of the doc is like it's almost like writing the doc is is the prep itself and it's you don't even necessarily need it in the interview. Like maybe you have it just in case. But yeah, that makes a lot of sense. Yeah. \>\> Um and then yeah, we we can even go through let's see um I'm doing a couple of interviews in the future. uh David Reich and David Reich and Daniel Jurgen. So the one the performer former is a geneticist uh with about human origins. The second wrote the prize which is the you know the famous book about the history of oil. Which one sounds more interesting to you? We can do that whichever one. \>\> Uh I want to I want to do the famous geneticists. \>\> So let's go to Claude. In fact I I I do have his book uploaded as a project. So we can just use that. \>\> That's great. And so basically what we're going to do is like we're going to we're going to watch you and I'll I'll do it with you. We're going to prep for an interview uh with this guy. What's his name again? \>\> Um David Reich. \>\> David Reich. Okay, cool. Can we get like a little bit of background on David Reich? Like maybe we can even ask Claude cuz like I'm you know obviously I'm a I'm a newbie to David Reich's work. I don't know. He is a geneticist at Harvard and over the last decade or so their research into how have human populations across the world been formed. Basically like how do the who are the Europeans, what groups make them up, what ancient migrations and genocides and population replacements made them. Same with the Indians or Native Americans or Africans. Um it's completely changed. Uh I mean they've basically sort of like made many academic disciplines irrelevant because they actually have empirical data on like here's actually what historically happened. You guys are completely wrong about what you think your theories of what happened. Um if you're familiar with Nat Freeman's challenge, you know, like you you have these like burnt up squirrels, but with some advanced techniques, you can get some useful information out of them. I feel it's in a similar vein. Obviously, they're not the same kind of project, but like it's a similar vein of like once we develop the advanced mathematics or genetics or whatever to understand what's latent in the genome, um we've like we've just uncovered a ton of insight about what's been going on in human history basically. And sorry, I'm just going getting nerd sniped and just going on riffs here. Like well one of the interesting things is uh you can see when one population replaces another whether it was just like oh we met and like we're like now intermingling in trading and whatever or is it like we're committing genocide against you and you can tell that because if in the case where it's genocide or population replacement it will be that the um the male line of the population that is invading will um overtake the uh male line of the existing population but the female brine will remain. So mitochondrial DNA is only comes up in the female line and you'll see like the female line because they're getting you know like the the new men who are coming in are taking them as wives or something and then the Anyway, so you can just like learn a lot about like what kind of invasion was it? Did they like conquer or was they were they just like mingling or something? Um one of the many things you can see from the DNA \>\> that's really interesting. Wait. And so so this is like basically re-examining DNA evidence of like old settlements and like basically and and he's uncovering new ways of being able to analyze the DNA like what's the what's the what's the new methods that they're using to like draw new conclusions from existing evidence. One of them is just that, right? Like seeing how the Y chromosome and the mitochondrial DNA cuz like you can just learn a lot about a population based on how the female versus male male line is propagated about like what was the social structure like and so forth. Another is you can even tell the level of inequality in a society because if there's a lot so for example in India um one of the things that was super surprising is that the the amount of indogamy which is to say that the um a certain cast in a certain village would just like not there wouldn't be any sort of intermixing with another cast in a neighboring village like it to the extent that's true of nowhere else in the world and they were able to find this in India where the amount ount of um social stratification. You can see that in the genetic catalog over the last thousands of years where for thousands of years these two neighboring casts haven't mixed um with like 99% or something which is like even from sort of infidelity or rape or something you uh you would expect there to be more than what actually ends up being the case. So you can understand modern uh culture in India based on what has happened over the last few thousand years. \>\> That's really interesting. So, I want to like I feel like you're doing like such a good job of summarizing his main ideas. Um, but I kind of wanted I kind of want you to do the same thing with with Claude so we can see how see how you stack up versus Claude cuz obviously you've you've you've you've input his his book into into this project. So, it has it has that as ref as reference material. Can we ask it to just like summarize like a few of his main ideas? \>\> Yeah. Can you summarize \>\> and maybe like the techniques he used to come up with with this \>\> perfect new so what you're writing is can you summarize the main ideas from the book and the techniques you use to come up with new insights \>\> cool and one thing that's like really cool about this is like you've been able to do something like this with JBT for a long time but ch's context window isn't that long and So, it chops it up. Um, and like it's not going to it's not going to really be able to summarize the entire thing because of that. You know, it has to like find the right parts of the parts of the book and the embedding search in it is not very good and all that kind of stuff. And Claude, you can just like throw us throw a ton of stuff in the context window and that just like makes a big difference. Um, okay. So, it looks like it looks like we've got some some uh some answers. \>\> So, it tells us that the ancient DNA is revolutionized understanding of human prehistory. Um and then we we've learned that populations today are the result of multiple waves of migration and mixture. Uh um and then you know just like a bunch of other genetic stuff. Um then it talks about the key techniques about whole genome sequencing and how they've enabled these sorts of new new discoveries they've been making. Um yeah. Yeah. But but any anyways there's a bunch of interesting things uh about uh their research. Well, now I'm interested in like, okay, so the key techniques that it's using are whole genome sequencing of ancient DNA samples. So, is whole genome sequencing like a a a new thing that you can do it on ancient DNA samples? So, it's saying like by improved extraction and sequencing technologies is that that's like \>\> that is an interesting question. So, we can even ask about it because I'm not sure um how uh how exactly do you sequence an ancient um or you know a prehistoric uh genome like can you do like what what is how does that work? Right. Okay. So, they grind the bone and they have then techniques to get the DNA out of that. Now, another thing we can ask is like um one thing I'm curious about. Let's see. Uh I don't really remember the chapter on um Native Americans. I could ask about uh what exactly happened with Native. Here's one thing I'm curious about. like um how would okay so I don't even know if David Reich addresses this himself but like how would David Reich's theories help explain why civilization suddenly um emerges so rapidly and that too um concurrently in the new and the old world after 10,000 BC, aka the end of the last ice age. And then I maybe I'll just like ask Claude why I think it's an interesting question. So like this seems like a really remarkable coincidence given how long humans have been around, you know? \>\> That is interesting. Well, coincidence given that human correct my spelling given that humans um have been around for hundreds of thousands of years. \>\> I didn't realize it that we believe that it emerged like at the same time in diff in geographically disperate places. That's totally new to me. I thought it I thought it was like just in Mesopotamia. \>\> No, it's actually there's a really good book by um Peter Jackson called The Great Divide and it's one of the most interesting books I read. Just as a side note, it's about Yeah, it's comparing the emergence of civilization in the new world versus your old world. So in the old world um uh in the sorry in the new world the um coral is like a civilization in 3000 B.CE And it's based on fishing and um not on like conventional agriculture like memia. And he talks about how that changed the evolution of the culture in the new world versus the old world. But anyways, um \>\> that's really interesting.