Interview with Packy McCormick, writer of the Not Boring newsletter (200,000 subscribers) and founder of Not Boring Capital, on how he uses AI in his research, writing, and investing. Topics include using LLMs to understand dense concepts and refine arguments, his thesis that vertically integrated businesses are the future of tech, using Claude Projects to edit his newsletter and build an interactive graphic tool, his research and writing workflow, his outlook on the next crypto bull run, and a live demo of an AI tool that grades his essays. # Channel Presentation Observations: "How Packy McCormick Finds His Next Big Idea - Ep. 29" ## Guest Profile & Framing (Observable Presentation) - The channel presents **interview-style conversations with notable tech figures**. The host introduces the guest with explicit credentials: > "You are the founder of Not Boring. You write some of the premier essays and analysis of tech. You have about 200,000 email subscribers... you also have a fund, Not Boring Capital." - The host describes himself as a **peer and friend of the guest**: "you've been a good friend in this whole journey," and references a shared Telegram group chat of "internet writers." ## Claimed Scope (Creator Statements in-Video) - The host states the show's focus explicitly when transitioning topics: > "I want to get into your AI use cases... AI as a tool sort of supercharges that whole process, and I just really want to understand how you've integrated it." - The host describes a **recurring show format**: > "one of the things I love doing in these episodes is just doing something together" — here, collaboratively building a Claude "Not Boring grader" project live. - **Channel name and host are stated on-screen**: the closing (AI-generated, self-parodic) outro names "AI and I" and "Dan Shipper as the captain of the spaceship," and includes a like/subscribe call to action. ## Intended Audience (Demonstrated) - Audience is **tech-curious knowledge workers and writers**, evidenced by: - Deep, hands-on walkthroughs of Claude Projects, grading rubrics, and prompt patterns (e.g., "output the reasoning first" to fix grade inflation). - Discussion of writing craft: "how much summary is a part of good writing." - Assume familiarity with figures and outlets like Ben Thompson, Stratechery, The Diff, Byrne Hobart, Fred Wilson, a16z — no basic explanation is given. - Audience interest in **AI-assisted creativity and investing** is demonstrated by long segments on essay grading, interactive graphics generation, and investment-memo critique. ## Presentation Style (Observable Patterns) - **Live screen-sharing / software demonstration**: the host and guest navigate Claude and Substack in real time ("here on the right-hand side is like a bunch of different stuff"). - **Experimental, iterative tone**: extended riffing on the "A-minus attractor state" where Claude consistently grades essays A− regardless of content. - **Monetization via sponsor read**: a mid-roll ad for "creatine gummies from Create" with a discount code ("use every 24"), delivered humorously. - **Humor and self-deprecation**: "We're incredibly mid writers, both of us"; "For me as someone who doesn't ever get anything wrong." ## Self-Description vs. Demonstration Distinction - **Explicit channel self-description**: limited to the outro's tongue-in-cheek claim that the show delivers "pure unadulterated knowledge bombs about Chat GPT" — clearly comedic register, not a serious mission statement. - **Demonstrated but unstated scope**: practical AI-workflow education through expert interviews and live collaborative experimentation; no formal mission statement appears in the transcript. # Delivery Observation: "How Packy McCormick Finds His Next Big Idea - Ep. 29" ## Format Overview This is a **two-person conversational interview/podcast** with a live screen-share segment. The host (Dan) interviews Packy McCormick, and roughly the second half becomes a collaborative, hands-on Claude project-building session. Framed by a host-run ad read and a satirical outro. --- ## Tone & Register - **Casual, profanity-light, jocular**: Both speakers use informal fillers ("like," "you know," "blah blah blah") and playful asides. - Dan jokes mid-intro: *"there's Packy McCormick from Not Boring... I'm going to impersonate you, I apologize."* - Packy's self-deprecating humor: *"Maybe I'm just an A minus writer."* - **Mutual admiration framing**: The host repeatedly compliments the guest; the guest reciprocates. - *"you've just been one of the main voices of this era in tech"* (Dan) - *"I was like I've hit the gold mine of internet writers"* (Packy, on their shared Telegram group chat) --- ## Recurring Phrases & Verbal Habits ### Packy McCormick - **"like" as a dominant filler** — appears constantly throughout his speech. - **Hedging paired with enthusiasm**: *"I think," "I mean," "kind of"* precede nearly every claim. - *"I think Anduril is like by far the best example out there right now"* - **Self-aware asides about his own habits**: - *"just cuz I'm vain"* - *"The grade is like almost a safety blanket for me"* - **Running gag he invents about himself**: *"For me as someone who doesn't ever get anything wrong, it's not particularly valuable"* and *"I just don't know what it's like to have such god-like power."* ### Dan Shipper (host) - **Enthusiasm markers**: *"That's really cool," "I love that," "That is the coolest thing," "This is really cool. I think that's so cool actually."* — repeated many times, his single most frequent reaction phrase. - **Long multi-clause questions**: Questions often stack several rephrasings: - *"What what what characterizes a techno-industrial company? Is it like frontier tech? Like yeah, what's So that I..."* - **Directive interjections during the demo**: *"Just stop you right there," "Can we look at," "I want to see that," "Tell me Tell me when you see it."* --- ## Teaching / Explanation Patterns - **Thesis-then-example structure**: Packy explains a category ("techno-industrials"), then grounds it with named companies (Anduril, SpaceX, Fuse Energy, Earth AI, OnCyber, Blackbird). - **Explicit "why now" reasoning**: Both speakers use the investor framing *"what's the why now"* repeatedly; Packy answers with enumerated causes (*"they're fundable again," "AI is one of the big why nows"*, nuclear sentiment shift). - **Process transparency**: Packy walks through his tooling and workflow step by step — *"the internet... DuckDuckGo browser... Notion... Readwise... Google Docs... Substack... Figma... that's pretty much the whole stack."* - **Live demonstration as teaching device**: The host structures the back half as building a Claude "grader" project in real time, narrating each step (*"So I'm going to make a new project"*) and testing iteratively. --- ## Communication Patterns of Note - **Meta-commentary on AI behavior**: A large share of the conversation is both speakers observing LLM quirks aloud: - Packy: *"the grade starts at an A- minus and then will get to an A the second time I send something"* - Dan: *"one of my pet peeves is like Claude always apologizes even though I didn't say like you did something wrong"* - **Shared humor about the A-minus "attractor state"**: They turn a repeated observation into a running joke — *"We're incredibly mid writers, both of us," "We're doing it for science folks."* - **Turn-taking interruptions during the demo**: Frequent short interjections (*"Oops," "Oh, no," "Wow. 198 out of 200"*) reflecting real-time co-discovery. --- ## Stable Patterns vs. Isolated Moments ### Stable (repeated evidence) - Host's enthusiastic affirmations ("really cool," "I love that") — dozens of instances. - Packy's heavy hedging fillers ("like," "I think," "kind of"). - Thesis → example → company-name pattern in Packy's explanations. - The A-minus grading observation, raised, tested, and re-tested multiple times. ### Isolated (insufficient repetition) - Packy's anecdote about his son rationalizing a made-up story — a single storytelling moment, not a pattern. - The joke spelling dispute over "rubric" (*"I think it's the Swedish spelling"*) — one-off banter. - The satirical outro and ad read (creatine gummies, "two tickets to the gun show") — structural segments, not conversational habits. --- ## Uncertainty Notes - **No curated metadata was provided**, so tone descriptions rest solely on the transcript; vocal delivery (pace, laughter, pauses) cannot be observed. - Speaker attribution in a few overlapping demo moments (e.g., *"Oops"* exchanges around timestamps 2680–2700 and 3590–3610) is ambiguous in the transcript; those quotes are used only where attribution is reasonably clear. # Observation Document: "How Packy McCormick Finds His Next Big Idea - Ep. 29" ## Speakers - **Packy McCormick** — founder of Not Boring (newsletter, ~200,000 email subscribers) and Not Boring Capital (identified from transcript/host intro) - **Dan Shipper** — host of the show ("AI and I"), co-creator of Every (per his own statements) ## Not Boring: Current Focus - Packy says he's come "full circle" to his early interest in **vertically integrated businesses**, now calling them **"techno-industrials"** — a name he calls "cheesy" and says he doesn't love, but needed to distinguish from "deep tech" or "frontier tech." - **Definition he gives**: deep tech includes "science project" companies with scientific risk; techno-industrials are a stage beyond — already-invented technology integrated into companies delivering products with **existing high demand, better, cheaper, at higher margins**, which can reinvest in R&D and growth. - **Examples cited**: Anduril ("by far the best example out there right now"), SpaceX (kicked off the hard-tech revolution and its talent diaspora), Fuse Energy (radiation effects testing/fusion), Earth AI (mining). - **Anduril thesis (Packy's)**: smaller, cheaper, more "tradable" hardware infused with software can compete with the five dominant defense primes operating as a "cabal," taking on risk rather than cost-plus contracts — "it's kind of working now" and he believes it will happen in other industries. - He notes SpaceX's space-launch competitors "kind of sucked" despite SpaceX being "maybe the most impressive company in the world right now." ### "Why now" (Packy's reasoning, varies by category) - These companies are **fundable again**, though many investors still balk. - **AI** as a major why-now. - Nuclear: public sentiment shift + move from **construction projects (gigawatt reactors) to manufacturing processes**, strengthening fuel supply chains. - General: **incumbent sclerosis** ("someone should replace Boeing"). - Mining: rare/critical metals discovery has gotten more expensive; analogy to historical oil/mining cycles where innovation follows "we're going to run out" panic. - Overall trend: **infusing software and hardware**. ## Crypto Positions (Packy) - He is **holding** ("hodling" — noted neither had ever said it aloud; pronunciation unresolved: "hodel's closer to hold") Bitcoin, Ethereum, Solana, and others; he **bought more in the bear market**. Qualified: "obviously not financial advice." - The last mini-bull was, in his view, driven by things that "don't actually matter": the Bitcoin ETF and halving anticipation. People he asked during it said "nothing has actually changed on the product side. This isn't the bull market." - He defers to "people smarter than me" that a real bull, if it happens, would be **2025**. - **Core crypto thesis**: crypto enables things you can't otherwise do; historically this required performance tradeoffs; over time tradeoffs drop while capabilities remain — eventually a "free option" on crypto features inside products. He doesn't know if it flips this cycle or the next. - Examples: **Blackbird** (crypto-adjacent restaurant app, upcoming piece), **On Cyber / oncyber** (portfolio company; founder described a website to a ChatGPT bot that generated its custom scripting language, producing a working 3D world with baked-in stablecoin/NFT payments). - **On the "next breakout consumer app" question**: "If I knew, I would be richer than I am." ### AI × Crypto / verifiable identity - Dan raises the view (possibly Fred Wilson's) that AI-generated untrustworthy content creates a job for crypto-based verification. Packy: it's a **"medium part" of his thesis, bigger for others**; a real narrative with crypto-AI coins often lacking real products. - His unresolved tension: signing only matters if others sign — **he doesn't know where the tipping point comes**. He suspects in ~10 years signing will be default, cites Worldcoin's proof-of-humankind, but says "a lot of stitching work" is needed. ## AI in Packy's Writing Process ### Evolution 1. **GPT-3/ChatGPT era**: fact-checking was unreliable; used it for "do I understand this right?" checks (e.g., fission/fusion for the "Age of Miracles" podcast). 2. **ChatGPT as editor**: "an okay editor, not a great editor." 3. **Claude 3.5 Sonnet + Projects**: current mainstay. ### Observations on LLM grading behavior (a recurring theme) - Packy: grades reliably progress **A− → A → A+** on successive sends, **even with no changes**; seeding a suggested flaw makes it "emphasize that issue" and give a B/B+. - When asked "better or worse" on revisions: **it has never said worse** — "Maybe I just am that good... but I can't imagine that's actually true." - It over-emphasizes **defensiveness and counterarguments** in feedback. - It "always says proofreading" but either invents typos or admits there are none; it "always says it's quite long" (because the pieces are). - **A− as attractor state**: repeated experiments later in the episode, including grading Dan's self-described weaker essay (which initially scored 73/200 with the rubric, but **A− without the rubric**), lead both to conclude A− is a default attractor. Dan: "We're incredibly mid writers, both of us." - **Reasoning-before-score fix**: Dan theorizes the model "thinks by writing" — outputting the score first anchors the evaluation; forcing reasoning first yields more accurate scores. (Early attempt backfired, producing 198/200.) ### Claude Projects workflow - Dumps all research (notes, analyst reports, blog posts, white papers) into a project, mirrors of his Notion research; asks targeted questions while writing ("is there interesting data I haven't used?", "you're an LP — where are you poking holes in my memo?"). - Uses it on white papers (e.g., Blackbird's "flypaper") to ask questions as he reads. - Style transfer: "explain Blackbird's economics in a style that's a crossover between Not Boring and The Diff" — first attempts come out as caricature even when told not to, corrected on second try. He doesn't take the output; uses it for angles. A Diff-style explanation of token economics prompted "yeah, I don't know if I would have explained it like that, but that's actually really good." - Separate **editor project** with persistent persona instructions ("world-class editor... heyday of the New Yorker... Stratechery... Pirate Wires") so he no longer re-types the prompt. Dan objects jokingly that Every isn't in the list; Packy says Every is "a different approach... less optimism," though he loves the writing. - The persona prompt includes the mission: "make the world more optimistic" with a "fact-based look at the most promising companies and trends." - Uses **Hacker News commenter** persona ("what is wrong with how I just summarized this?") — with a stated **danger**: a couple of pieces got "more watered down than I would have wanted" because of this always-present critic; it's a balance between avoiding obvious errors and pulling back arguments. ### Dan's contributions on writing - **Summary is a huge, underrated part of good writing**; AI collapses summarizing time "particularly for complex ideas that you already understand." - Dan shares his own impostor-syndrome use: "pretend you're a PhD computer scientist — what are the holes?" gives him confidence; previously only available to people with big editing teams. - On novelty checks: truly new ideas are "ungoogleable," but LLMs can "move laterally through the entire space of human knowledge." - Dan contrasts Google's "filter bubble" results with Claude surfacing counterarguments to a question that presumes a worldview. Packy jokes: "For me as someone who doesn't ever get anything wrong, it's not particularly valuable." - Packy's check for prior art sometimes returns **made-up blog posts** that sound exactly like the piece he wanted to write — so he treats results cautiously. - On writer types: Packy places Ben Thompson and Byrne Hobart as having "more structured brains" with frameworks; his own brain treats every idea as new ("like a sitcom... every episode is new"). Dan uses custom instructions to keep key ideas present and "hearken back." ## Interactive Artifacts - **"The American Millennium" piece**: asked Claude to code a vector visualization of government + entrepreneurship producing "progress"; deployed via Replit as a clickable interactive element. He disclaims: "not going to hold up to peer review by any stretch," but "I never in a million years would have made this." - **Risk-appetite piece (ChatGPT)**: had it score America's risk tolerance 1–100 across historical periods and graph it. Disclaimers noted heavily ("this is not accurate. It is just guessing") — but "I don't know how I would have come up with those numbers otherwise" and manual estimation would be "equally imprecise" but take hours. - **Empire values experiment**: asked for entrepreneurship/government scores of historical empires without influencing it; it matched his expectation (America strongest on entrepreneurship). This led him to "confidently say America was the only capitalist empire," which drew pushback ("What about the Dutch? What about the British?"). His response: "Fair, but I still think the government was more powerful than the capitalist system there." He flags the risk: **confirmation — it "might give me a little more confidence than I probably deserve."** - **Nuclear company piece (upcoming)**: pulled nuclear reactor design code the founder used, had Claude walk him through it and explain parameter changes; hopes to ship an interactive "play with reactor parameters" element — "not a nuclear engineer by any stretch." ## The Grader Rubric Experiment (live build) - **Process**: Dan builds a "Not Boring Grader" Claude project using exemplar essays — *Excel Never Dies* (co-written; Packy notes this grades "what I can do with someone else"), *The Great Online Game*, *Fuse Energy* — plus a bad example, *Praise Elon*, which Packy volunteered as "not great": too "glib and tongue-in-cheek," written in-the-moment on Twitter, "not representative of what I want to be writing." - Claude's critique of *Praise Elon* ("narrative feels forced," "premise... seems like a stretch," shallower, reactive) matched Packy's own assessment. - **Issues encountered**: hallucinated example attributions (Fuse hook placed under *Excel Never Dies*); asking for examples dropped the point structure; requesting refinements **added** points rather than redistributing (200 total instead of 100); repeated regenerations to map the score distribution (roughly 180–184). - **Outcome**: Packy's previously A− essay scored 182/200 (≈91, still A−); when asked to "be as objective as possible," it **dropped to 165/200** — evidence the A− default persists even under explicit objectivity instructions, though rubric-based grading produced more variance (Dan's weak essay at 73/200). - **Conclusions (both)**: A− is an attractor; a rubric based only on one's own writing keeps you in that state; **wide diversity of examples** is the likely fix. Dan's alternative proposal: bucket essays against explicit A/B/C/D exemplars rather than math over rubric parts. - Packy's homework: grade against a curated list of favorite older essays ("this is the bar — grade me against these"), and possibly test whether an outside writer scores differently. - Packy's final assessment: the **grade is "almost a safety blanket"** (a C would mean "I can't send this"), but the rubric's specific tips genuinely change how he thinks about writing. ## On AI Intelligence and Future - Packy is **"definitely not a doomer."** His reasoning: current systems are "incredibly inefficient"; orders-of-magnitude gains in training and inference compute are coming, plus architectures enabling **post-training learning** (vs. prompt tuning as the only way to add information today). - He demos "pressing replay" to regenerate multiple gradings, mapping the score space (~180–184), and argues **creativity is "doing this a thousand times in half a second"**; with fast regeneration and live updating, talking to AI will feel "very similar to talking to an actual human." - On children analogy: his not-yet-four-year-old rationalized a made-up conclusion with an invented story — "we really all, including I guess Claude, do this" (reason used to justify intuition). Dan extends it: people who deny AI will get smarter should note "this is how children reason," and children get better and better — a basis for his confidence these systems will get "even smarter." ## Tool Stack (Packy) Internet via **DuckDuckGo browser**, **Notion** (dumps), **Readwise** (highlights → Notion), **Google Docs** (writing), **Substack** (sending), **Figma** (graphics) — Claude/ChatGPT are "the first new addition to that stack in a while," and a habitual go-to when stuck. ## Metadata & Other Notes - Packy credits the origin of Not Boring partly to a Telegram group chat with Dan and other internet writers: "I don't know if there'd be Not Boring without that." - During the episode he published a "fairly moderate take" on Democrats intended to "piss off both sides" — Democrat readers offended he didn't call Trump "the worst person in the history of the world," Republican readers upset he treated Democrats as not redeemable. - Contact: **@packym** on Twitter; **notboring.co** ("I have not sprung for the dot com yet"). - Transcript includes mid-roll ad copy (Create creatine gummies) and a satirical outro — both Dan's production elements, not Packy's positions. # Speaker & Provenance Observation Record **Video:** *How Packy McCormick Finds His Next Big Idea - Ep. 29* (ID: `01a0f15b-0a12-7eb8-9a11-a66975539c20`) ## Speakers & Roles - **Dan Shipper** — **Host / creator**. Identified as "Dan" by the guest; closing promo names him as the show's captain. Writes for "Every" (self-identified while grading his own essay). - **Packy McCormick** — **Guest**. Founder of **Not Boring** (~200,000 email subscribers per host intro) and **Not Boring Capital** (a fund). Contact points given by guest: **@packym on Twitter**, **notboring.co**. ## AI Tools Referenced (by speakers) - **Claude 3.5 Sonnet / Claude Projects / artifacts** — used by both speakers for editing, grading, code generation, summaries. - **ChatGPT (GPT-3 era onward)** — editing, graphs, code explanation. - **Replit** — used by Packy to host an interactive essay graphic. - **DuckDuckGo, Notion, Readwise, Google Docs, Substack, Figma** — Packy's stated creative stack. ## ⚠️ Promotional Segments (Flagged) - **Mid-roll advertisement: Create creatine gummies** — host reads ad, promotes 30% off with code/link ("every 24"). - **Outro promo (apparently AI-generated voiceover)** — urges viewers to like/subscribe to "AI and I," includes a parody declaration of love for Dan Shipper; clearly a scripted promotional bit, not guest content. ## Referenced Third-Party People, Companies & Sources Claims about these are speaker attributions, not verified facts: - **Companies discussed:** Anduril, SpaceX, Boeing, Fuse Energy, Earth AI, Blackbird, OnCyber ("On Cyber," a Not Boring Capital portfolio company per Packy), Worldcoin. - **People referenced:** Fred Wilson (crypto/AI thesis), Marc Andreessen, Peter Thiel, Ben Thompson (Stratechery), Byrne (Hobart), Jay Drain (a16z), Julia (co-host of "Age of Miracles" podcast), Matt Shurmer ("make it better" tip). - **Publications referenced:** The Diff, Stratechery, New Yorker, The Atlantic, Harper's, The Economist, Pirate Wires, Every, Hacker News (as critic persona), *The Sovereign Individual*. - **Packy's cited essays:** "The American Millennium," "Excel Never Dies," "The Great Online Game," "Praise Elon" (self-labeled weak), "The Unbearable Heaviness of Being Positioned," a crypto/risk-appetite piece. ## Third-Party Claims of Note - Crypto/verifiable-identity thesis attributed to **Fred Wilson** (per Dan). - "2025 bull market" prediction attributed to unnamed "people smarter than me" (Packy). - Market observations: Bitcoin ETF and halving as drivers — Packy's own view; he disclaims "not financial advice." ## Availability Limits - **Comments availability:** not stated in transcript or metadata. - **Curated metadata:** none supplied beyond title and transcript. - Uncertainty: speaker attribution relies on conversational cues; transcript contains no timestamps, so segment boundaries are approximate. I feel like we could make a Claude project for you that has a really rigorous set of rubrics for what essays are best. Hell yeah, let's do it. I'm going to impersonate you, I apologize. Um, there's Packy McCormick from Not Boring. I want to create a detailed rubric that explains what goes into my best writing. Do you have any pieces that you've written that you think are bad? Huh, no. Now, the thing I want to do, I want to add this to our knowledge base and I'm going to say, "Here's an essay draft, please grade it." Are you looking to get the most out of ChatGPT? Everyone talks about prompt engineering, but what they don't tell you is the best way to get ChatGPT to follow instructions is two tickets to the gun show. 1,001. 1,002. And if you want to maximize your gains, both with your body and with ChatGPT, I highly recommend you try creatine gummies from Create. I actually eat these every single day and they help me maximize my lifts and give me more energy. They also taste pretty great. If you use the link below, you'll get 30% off. Just use every 24. Are you getting this? Packy, welcome to the show. Great to be here, Dan. Excited for this. Really good to have you. So, for people who don't know, you are the founder of Not Boring. You write the some of the premier essays and analysis of tech. You have about 200,000 email subscribers. And you've just I think you've just been one of the main voices of this era in tech. And in addition to your writing at Not Boring, you also have a fund, Not Boring Capital. And you're just you've been a good friend in this whole in this whole journey. And so it's really fun to have you on the show. It's I mean, thank you for that for the intro. It's great to be here. I like still remember I don't think there would be Not Boring if it weren't for that group chat that we had on on Telegram with all of the right I the first day that I walked in and like saw you in there and saw a few other people in there. I was like I can't I'm like I've hit the gold mine of internet writers. Like this is amazing. And I really I I don't know if there'd be Not Boring without that. So, fun to bring it full circle here. Yeah, I love it. And I want to get into we'll get into some of your like your AI use cases. You have some interesting ones that I really want to talk about, but I think before we do that like I just want the update like just almost as a friend and like an admirer of your work. Like what's what's the latest? Like what's going on with Not Boring? Where where are you right now? What are you thinking about? Ooh, um I'm kind of like kind of have come to reuse the phrase full circle full circle again. One of the first things that I ever wrote before there was Not Boring just like when I started writing was this piece on like natively integrated companies like internet / vertically integrated businesses. And I've really just like gotten obsessed again with with vertically integrated businesses calling them kind of techno industrials. I think we've talked about kind of AI and how it applies to analyzing some of these cuz they're just like these big complex beasts, but I really like writing about complex things that if they work turn into really good business models and businesses that make an impact. And so, more and more on both the writing and investing side I'm trying to converge a little bit on really just diving deep into some of those companies which means that you know, like I I will still I'm writing about a crypto company next week and like that was a complex one that just like you know, nerd sniped me and continues to nerd snipe me. Um but more and more looking at you know, like I've written about Anduril, a company Fuse Energy that's doing radiation effects testing and and fusion energy, a mining company Earth AI. And like I just love this excuse to dive into these industries that I should know more about and don't when I start the process. And so, trying to orient as much as I can around you know, the investing in writing in those types of companies. That's interesting. What what what characterizes a techno-industrial company? Is it like frontier tech? Like yeah, what's So that I I have like a cheesy I I don't love the name techno-industrial, but I needed something that's different than deep tech or frontier tech cuz I think there's a lot of deep tech that is incredibly cool kind of science project type companies where like they're trying to make something that has never happened before happen and there's scientific risk there and it may work, it may not work. And then there's like kind of a stage beyond that where some of that stuff has already been invented and then you integrate it into a company that can deliver a product that this is kind of like the the thing that I look for. Deliver a product that there's a ton of demand for already, better, cheaper, and at higher margins, which then you can reinvest back into R&D and you can reinvest back into growth and all of those things. I think to use like the cliche one, I think Anduril is like by far the best example out there right now. Like SpaceX I think kind of kicked off the the hard tech revolution both in terms of as an example and the talent diaspora from that company. But like the the space launch competitors kind of sucked and so like obviously zero knock against against me. It's like the most impressive company in the world right now maybe, but I think that to me the interesting unlock about Anduril was that they said like we have this different approach to defense and we think we can actually take on these like, you know, huge 100 billion plus dollar defense primes that kind of just operate in this cabal, these five companies that dominate everything and we think that if we make, you know, smaller, cheaper, more tradable hardware, but we infuse it with software, then we can deliver a better product to the government at better prices and cheaper margins and take on some of that risk ourselves as opposed to doing it cost plus. And it's like kind of working now and I think that kind of thing is going to happen in a lot of other industries. And so that's that's the thesis. Interesting. And then what is the like what is the why now of that? What's what's making those companies shapes like like uh um potentially important or impactful right now? Yeah, I mean I think one is like they're fundable again and so like these are some they're still like a bunch of them that we look at. I think still investors are like I don't know that seems like a lot and a lot has to go right for this to to work, but they are fundable now. I think AI is one of the big why nows. I think you know if you look at something like nuclear for example, there's public sentiment shift. There's uh there is this shift from kind of construction like this belief that every nuclear project should be a gigawatt reactor that is a construction thing to a manufacturing process and like starting to see enough companies do that that the fuel supply chain is strengthening a little bit. Like there's just a bunch of things kind of coming together. The the why now I think It's hard to do like a general why now on these and like one of the things I like about it is that there are specific why nows. I think one of like the big why nows is that you just feel like in a bunch of different categories, there is sclerosis among the incumbents and there's the opportunity for a company to come in and and do something better. I mean like someone should replace Boeing as one good example. That mining company that we looked at, the interesting why now is that it's just gotten a lot more expensive and harder to discover new rare metals and new critical metals. And so you need kind of like this happens in the history of oil development, the history of mining where like you kind of get everything that you can at one technological level and you hit a wall and people are like oh we're going to run out of this stuff. We're going to hit peak oil. We're going to run out of critical metals or China's going to get all of them. And then someone comes in and and innovates and then you can kind of like get to the next level of something that used to be more expensive that now you can make economical. And so it's different per category, but I think infusing software and hardware is probably the big kind of overall trend. That's really interesting and then and just selfishly like what should I think about my crypto portfolio right now? I I'll say like I'm I'm holding. I've got got all of the Bitcoin and the Ethereum, but obviously like there was a huge bull cycle I guess in like 2022-ish and then it seemed like there was it was like almost coming back like 6 months ago or 4 months ago and then now it's sort of like back off the menu at least like in in the spheres that I'm traveling in which is like only crypto-adjacent. Like what's your current crypto take? I'm also hoddling Bitcoin and Ethereum and and Sol and you know, a few other a few other things in our portfolio or the Is it hoddle or hodel? I don't hoddle? Hodel I guess. Hodel's closer to hold, but I've only ever read it. Yeah, me too. I've never said it out loud and I understand why people don't say it out loud cuz it's kind of tough. Um But I mean obviously not financial advice and blah blah blah, but like I'm I'm have held on. I've bought more in the bear market. I think like I I was certainly excited when I got to see the prices of the things in my portfolio going up in that kind of like last mini little bull, but I think so much of that was exaggeratedly driven and and driven by the the kind of Bitcoin ETF and the anticipation of the having and things that like don't actually matter. A lot of the people even then that I talked to I was like, "Oh, this is awesome. Like is this the bull market? Is it happening?" And they're like, "No, like nothing has actually changed on the product side. This isn't the bull market." a lot of people smarter than me have said, you know, 2025 is if when it happens, it'll probably happen in 2025. Um but you know, I would think we're still waiting to see what those breakout things are going to be. This company that I'm writing about uh for for next week, Blackbird, I think it's a really really interesting product that is kind of crypto and and more just kind of a restaurant app. Uh this company that I wrote about last week called On Cyber, this is one of our portfolio companies that makes it easy to build 3D worlds in in web browser. It's another interesting one where they wrote their own kind of scripting language to build worlds on top of the game engine they had created to build this NFT gallery. But now, you know, the founder, I told him on a call what website to make, and he like kind of described it, and it wrote something in their scripting language in a chat GPT kind of in a chat GPT bot, and then he plugged it in, and then he just had this kind of like game/world that got made. And so, I think that's going to be really, really interesting, and they have crypto kind of payments just baked in to to the site, so you can turn on, you know, stablecoin payments, you can turn on NFT minting, a bunch of easy stuff. So, I think hopefully we see a bunch of things where crypto is infused, but it's not the whole product in this cycle. Do you buy the argument that like we're just starting to get to the place with like L2s and and other crypto infrastructure that like we can really start to see like actual breakout consumer apps in this next cycle? What's What do you think the next breakout comes from? If I knew, I would be richer than I am. So, I don't know where the next breakout comes from, but I do genuinely believe that. Like, I in the middle of the bear market, I like talked to a bunch of people who kind of like re-inspired me on on on crypto generally and wrote this piece that essentially says like crypto gives you these things that you can't otherwise do. Now, like up until now, you've had to make some like real performance tradeoffs in order to use those things. And so, if you need those things, like if you're launching a meme coin or if you need to own an NFT that you can't own other like there are specific things where that tradeoff in performance is really, really worth it. But over time, the performance tradeoffs drop, and the capabilities you have either remain or get stronger. And so, at some point you almost get like a free option on all those other things that crypto enables. I don't know if it's this cycle or the next one when the that like kind of flips, but I think just over time as performance gets better, as things get cheaper, you just get stuff for free with crypto that that will be useful to include in in different products. And what are your thoughts on the um um I think there's a sort of like galaxy brain take. I think it might be Fred Wilson who's like one of the main people behind this, but uh just generally there's a there's a thought that as, you know, AI proliferates enables the proliferation of like lots and lots of content that may or may not be trustworthy, like it creates more more of a job to be done for for crypto to to, you know, verifiable identity to, you know, verify who's who's saying what. Uh is that any like on your radar at all? Is that part of your thesis? Like what's what's um It's like a it's a medium part of my thesis, and I think it's one where it's a big part of a lot of people's thesis. I think Fred has a very nuanced take on it. I think there's a general kind of crypto AI thesis that is like, "Oh my god, like crypto and AI like of course it's going to happen and crypto, you know, the crypto AI coins have taken off like whether or not there's an actual kind of real product behind them and and all of that. So, it is like a real narrative in the meta. Um But the thing that I'm still trying to figure out is like there is a tipping point where at some point like to sign to have to sign something. If you're like the only person who's signing something and proving that it's real, it doesn't really matter. Like if no one is signing their transactions uh cryptographically, then there's no expectation that other people will. So, I don't know where that tipping point comes. I do wonder if like an ex you know, integrated at some point or if platforms start to integrate. Maybe. I do think like we wake up in a world in 10 years, and that's probably something that just that just happens for people to prove it. Obviously, Worldcoin doing the proof of humanity thing and others doing kind of proof of humanity or decentralized ID. I think all of that is interesting and will be valuable. I just think there's like a lot of stitching work that needs to happen in the middle to get to a point where it's just like kind of default that if you're if you're sending something as yourself, you're signing that thing. That makes sense. So, I want to start getting into the AI your your uses of AI. And the way I want to do that is like just sort of taking a step back. You as a person, you have this sort of like incredible amount of curiosity. You love thinking about like really really complex companies and spaces and and and writing long-form essays about like how they all how it all sort of fits together. And so, your job is almost to like be really curious about the world and about companies, do like a ton of research, write about it, and use that to kind of like crystallize a worldview that then you go and invest on. And I really want to understand I just feel like AI as a tool it like sort of supercharges that whole process, and I just really want to understand how it has how you've integrated it to help you do that that core that core thing that you do that's sort of being curious, doing a lot of research, writing, and then using using all that writing to create a thesis that then you use to invest. Yeah, so I think it's it's evolved a little bit. So, it would with GPT-3 and ChatGPT, it started out just as I was writing something, you know, like I wanted it to give me like facts and all that and it didn't do that, you know, predictably well enough that that I could use it. But if I were looking at, you know, writing about fusion or doing this this podcast that we did Age of Miracles with with Julia and I and I where we looked at nuclear fission and fusion, there'd be a lot of things where I'd be writing a script for that or if I was writing a piece where I'd be like, "Am I getting X, Y, and Z about fission right? Or like explain what I'm getting wrong here? Or is there a simpler way to say what I'm trying to say here?" So, it was a lot of going back and forth and doing kind of like "Do I understand this right?" Or like here are the different types of kind of fusion fuels. Am I missing any? Or like different things like that as as I was exploring and I I still do that for sure as I'm as I'm using, you know, the chat tools. Um it evolved into I started using chat GPT as my editor and I'd say it's like an okay editor, not a great editor. It's like not going, you know, not going through and doing copy edits or line by line. It's not like really tightening my prose. Um what I've started using recently though I've I've started using Claude 3.5 Sonnet and now projects. And so Sonnet I just think is at least like it sounds nicer as an editor and like it makes me believe that it's giving me better feedback than than chat GPT. It does I ask for feedback and a grade just cuz I'm vain and and every time pretty much without fail the grade starts at an A- minus and then will get to an A the second time I send something and then we'll get to an A plus the third time I send like I I could like also like not change something and it'll still probably go through that same progression. If I say if I say when I'm like asking for feedback send it the same exact thing and I'm like, all right, give me a grade on this one. Somebody else that I sent it to said that like this was one of the issues with it. Almost invariably it'll like really emphasize that issue and then give me like a B. Um a B or a B plus if I like, you know, so it's not it's not the most uh reliable editor but it will say like this section is too long and it drags and I'll go back and read it and that section is too long and it drags or I do think it's too defensive or like wants you to like really look at all like examine all of the other sides and counter arguments to what you're saying which I think is a valuable thing from a valuable exercise for me to do as I'm writing and if there's something that like really does kind of uh it poke a hole in in my argument like then I'll go back and kind of try to incorporate that but like it really I think over emphasizes the defensiveness in in writing which is okay. Um but I do think it's useful and I think it's just become like almost a habit now where if I'm stuck for a second I'll just throw it in into Claude as like a thing to do to do something while I'm feeling stuck. Projects I've started using for the past couple of weeks and they've been a a revelation and that's both on the writing side and the investing side where take a piece, the a piece that I'm writing on on Blackbird like dumped all of my notes uh with the company in there, dumped the materials that they sent. I was studying, you know, like when I write one of these pieces, I'm trying to understand the industry that they're operating in. So, try to understand the restaurant industry, put uh analyst reports in there, put blog posts that people have written in there. Like just dumped as much content as I could. Everything that I normally put into a Notion as I'm going to research, I put in the Notion now, but then I also just dumped the text into into Claude. And then I'll ask it questions as I'm writing. I'll be like, "Cool. Now, here's the section that I'm writing. Here's what I wrote. Like is there any like interesting data anywhere that I've that I should be using that I haven't thought about using? Or are there quotes from X, Y, and Z investor that I talked to that might be useful here?" And that's been really cool to be able to do. Or like, "Here's my full investment memo on this company. Am I missing something like really important? Or if you're if you're an LP who's looking at this, like where are you poking holes in my thinking?" So, that giving it that context and then asking it to analyze the work given that context, I think has been really, really valuable. That's really cool. I want to see that. Can we Can we look at your project for for Blackbird? Ooh, I don't know if there's anything secret in there, but all right. So, here on the right-hand side is like a bunch of different stuff that I was reading about Blackbird. And so, that could be Fred Wilson's original blog post, a couple of those. Jay Drain at A16Z wrote a blog post. It could be their press release. It could be uh blog posts that the company's written. An interesting one that they did recently, they uh just dropped their uh their white paper, the the fly paper. And so, that one's really interesting to say like, all right, like I'm going to read this and there's actually a little bit more approachable cuz it is more of like a consumer restaurant facing product. But for a typical crypto white paper to be able to have something where I can just ask it questions as I'm going through and ask it different things is super super valuable. Um and so like one thing that I did here was ask you know, please explain Blackbird's economics in a style that's a crossover between Not Boring and The Diff. Or like you know, I was I was I played with doing The Diff recently. Um And and I always have to tell it to uh to not do it like a character and then it'll do it like a character and then I'll go back and be like, you did it like a character and then it'll write something kind of like good in my my style and I don't take that, but I'm like just looking for just inspiration for different angles that I might not have thought of and I feel like putting The Diff in there like in this one in particular, they had a couple of explanations that I was like, yeah, I don't know if I would have explained it like that, but that's actually a really good explanation. Um and so just you know, use this as a way to go back and forth. Um so you like, okay, this is still a bit too character and over the top. And then use it to go back and forth uh kind of almost describing the thing that I'm reading back to me in my own voice in the own way in my own way that I would write about it and it's not again perfect, but it's like close enough that it does make it sink in more than just kind of looking at a regular white paper would. I just want to stop you there. Just stop you right there. Like I think it's so um important and misunderstood how much summary is a part of good writing. Um and in particular like how much summary is uh important for writers to like even know what they're talking about and then for writers to give to readers to like set up the point that they want to make. Um like that's it's It's huge huge huge part of writing and for something like that, okay, if you if you scroll up like a summary of um tokenomics, for example, it like it might take you like a day or whatever to like really deeply do that. Even if you Even if you generally get it. Like even if you read all the stuff and you have it in your head, like to actually put it into like a crisp, clean format could take a day or two at least. And one of the beauties of Cloud projects but like just generally this this generation of AI is like particularly for complex ideas that you already understand, it just saves you that summarizing time in your writing and in your thinking so that you can get to the more interesting stuff. And yeah, like you're probably not going to just copy paste this exactly, but it's it's surprising how much just having it in that form where it's like basically in the context that you need it, just like speeds you up to like just get through that part of it so that you can do the actual interesting thinking afterwards. A a thousand a thousand percent. And and like if if I do summarize, being able to say like cuz I'm always debating, should I do more and I probably do often do more than than less, but like should I do more here? Like what am I missing here? Did I get anything wrong or like put your a common one is is, you know, you're like a Hacker News commenter, like what is wrong with how I just summarized this thing? And I I I do think there's a danger to that and like same with the way that they give feedback when I ask for feedback in a grade, which is like I think there've been a couple pieces probably that got a little like more watered down than I would have wanted them to because I have this critic there that otherwise wouldn't be wouldn't be kind of involved in in the writing process. And so I think it's a balance between just like making sure that I avoid really obvious errors uh and then like kind of watering down or like pulling back my argument too much because I have a Hacker News commenter kind of all of a sudden in my in my ear. And so that is like an interesting balance to to try to play with. I do that all the time. I mean, like anytime I'm writing out something that's technical, I just like have this voice in my ear that's like, "You're not really a great programmer." "Do you really understand this?" You know? Um like you didn't You don't have a PhD. Um and uh and I love Claude for that because it just gives me enough confidence because I can just put what I'm what I'm saying in there and just be like, "Okay, pretend you're like a PhD computer scientist. Like, what are the holes?" And it might not get everything, but it gets enough that I just feel comfortable that like it's I'm not saying something completely stupid. And I I feel like that's so important for writers to like be able to like have that resource. And previously, it was only available to people who had like big editing teams or a lot of resources or whatever. And it's just like it's the coolest thing. Totally. Um but there's there's one So I mean So this is I wrote a piece uh a few weeks ago called The American Millennium. And I had this uh I had this idea that I wanted to play with that was one of the interesting things about uh America is that like the system works so well and like the entrepreneurial drive works so well. And all these things that like kind of no matter who no matter who's in the White House as long as rule of law and the Constitution are maintained, like we might not suffer the fate of the Romans because people can just build things and and uh you know, prevent the decline. And so I wanted to show that at First of all, play with the idea, but then show that. And so I asked it to code me up a little thing where like I could show what happened to the the vector sum of kind of like government and entrepreneurship Woah. on progress. And it just coded that up for me. And I went over to And it's like, you know, very very simple thing, but I like put it in the I put it in the essay. Um and then I went over to Replit and just like dumped the code in there. And I had a little website that you could like click on in the essay and and play with it yourself. And so it's like fun. Like this is not going to you know, this is not going to hold up to peer review by any stretch of the imagination, but it's just like an another like interesting thing where I never in a million years would have would have made this. Maybe I would have tried to draw a shitty version of this, but to like have this little interactive thing that I could put in there because of because of Claude, like that was I thought a pretty fun thing to be able to to do. is so cool. Wait, we got we have to see how how you made this. So press continue chat. Like I want to just go up to the top. Like I want to know how you like where you started this cuz I think this is like just such an underappreciated thing where you're someone with with so many ideas in your head and suddenly you can just like make something that's this new form or new representation of something that's been in your head that like maybe previously like you could have done, but it would take a a lot of work or it would have you would have had to pay someone and now you can just like get something out of your head in this totally new way that's not writing, but is like it's a visual representation or it's a it's an interactive demo and share with your audience. Like I just think that is the coolest thing. It's it's really fun and I've done this a couple of times. I this is like a slightly different one, but I used I used ChatGPT for this one when I wrote about kind of America's tolerance for risk or or risk appetite. I had it judge through a bunch of different periods like what America's score between 1 and 100 was and just like asked it to make me a graph on that and you have to disclaim the hell out of the fact that like this is not accurate. It is just guessing like all of that, but it does give I think a pretty good kind of like rough guide and it's a quick way to make a visual where I don't know how I would have have come up with those numbers otherwise and so just to be able to like quickly be like, here's a dumb idea. Can you give me this these numbers and then turn them into a chart? It's something that I probably wouldn't have done, but if I had it have taken a few hours and would have been equally kind of imprecise. And so it's like a fun little thing that I I've done a a couple of times now. So this one actually started with here's a thesis I'm playing with that I'd love your help thinking through. Since technology compounds and government doesn't, uh technology should overtake government in importance at some point. And so it like gives me some ideas here. What are the Can we read through some of the ideas? Like I'm sort of I'm sort of curious. Yeah. So you're right that technology tends to advance exponentially. Each new innovation builds on previous ones. Uh government evolution, while governments do evolve, they generally do evolve at a slower pace. Relative importance, the idea that technology could overtake government in importance raise some questions. What do we mean by importance, political power, impact, economic influence? Is it a zero-sum game or can they both increase in importance simultaneously? Uh what are some scenarios if that happens? What are some Again, always, what are some counterarguments to this point? Um and then historical perspective. And then This is really cool. I think that's so cool actually. Um and I know like I totally get your point that like it's sort of annoying when it you're like just trying to like get like figure out how to make this essay better or whatever and then it's like here are like 15 counterarguments or like What What one of my pet peeves is like Claude always apologizes even though I didn't say like you did something wrong. I'm like, "Okay, make this better." And it's like, "Sorry, like you're totally right." And I'm like, "You don't have to say sorry, like it's fine, you know?" Um but I also think it's so cool that like it's even presenting some of this stuff because um let's say it's not you and it's someone else and like and they're asking a question like that which like the question presumes a particular worldview. Um and there's a lot of assumptions and it doesn't just like say here's the answer. Um it like says, "Here's like let's assume what you're saying is right, but here's like a bunch of ways that it might be wrong or some things you need to think about." Which is like completely different I think from the like sort of filter bubble world that like we come from with Google where it's just like showing you like Mhm. the latest bright parts screed when you search for something that like sort of indicates that you're like you want that, you know? Yep. And I I love that. I think that that's really cool. It's it might be for you. For me as someone who doesn't ever get anything wrong, it's not particularly valuable, but uh I love it. I love it. Yeah, I mean, I I just don't know what it's like to have such god-like power, um but yeah, that's good. It's normally me correcting the the LLM, but but I mean like and then then you can go in and like the other thing I don't want to do is spend all this time like I'd be like, "Oh my god, I have this really cool idea about technology and government." And then like 75 people have written that exact thing before, so I'll ask it. Um and you know, sometimes uh it's it gives me things that are real. Sometimes I'm like, "Oh my god, that sounds like the exact blog post that I want to write." And it's a completely made-up thing and it doesn't it doesn't make any sense. And so I'm like, "All right, cool." Like So there's there's that. Did any of these help you? Like like let's let's read through them a bit. Like the sovereign individual like are any of these like actually you kind of like get it from or like it it it helped kind of shape the argument for you? None of these actually Yeah, none of these none of these did. Yeah, that's interesting cuz I do think that I do think that is a sort of underrated thing for Claude, especially for writers or anyone who's trying to do something new is like if you're truly writing something new, there isn't a pre-existing website that like talks about this idea in terms that you're talking about it. Um and that's that makes the question effectively ungoogleable. It's like, "Who else has thought about this?" Like you just can't Google that. Um you can like try a couple things, but like it's just unclear whether or not you're going to find it. And because Claude or ChatGPT or any of these AI tools like kind of get the underlying concepts, they can like move laterally through like the entire space of like human knowledge to like zero in on people that might have talked about similar things but in different terms than you. And that is like the most valuable thing for people like us. I just love it. I agree. Uh yeah, and these these ones I hadn't read everything, but I like, you know, familiar enough with the ideas from Sovereign Individual. I've probably read most of the things that that Marc Andreessen and Peter Thiel have read. And so like I had a lot of it to like jog me, but there was nothing in there that was like, "Oh, that is a totally different way of thinking about this thing that I'm that I'm trying to think about." Um yeah, but yeah, there's been plenty of times where I'll be like like, "Oh my god, I have this novel idea." And I'll be like, "Philosophers have been talking about this for 17,000 years." And then I'm like, "All right, cool. You you saved me. You saved me a lot of time. Thank you for and embarrassment. Thank you for letting me know." Um and it's it it is also helpful cuz like I do think there are a couple of types of writers like broad like I'll put like Ben Thompson and Byrne in one category where like they just have bigger like more structured brains probably. And like anything that comes out, they're like, "Oh, let me hang it on like this piece of my framework over here next to all of this other relevant information." And my brain is like, "That's an interesting new idea." even if I'd like thought about it yesterday cuz I just have like no memory and no whatever. And so having something like this where I can just check those things and maybe in another brain just kind of exist, I think it's really helpful. Yeah, I agree. I feel the same way about my writing. Like that's something I've been trying to change is like I I call it like it's sort of like sort of like a sitcom. It's like every day is new, you know? Every episode is new. Whereas like yeah, people like Byrne or like Ben Thompson, like they're much better at like having like a plot arc to the whole season, you know? Um and I I do agree like having this tool as like a throwback. Like I I I often will put in custom instructions like things about like what I'm thinking about or what are the what are my key ideas right now and trying to have it like hearken back to those things or keep keep me on track is like really helpful. Oh, that's really interesting. Yeah, and then we actually get right into the government and entrepreneurship vector graph. Yeah, so out of there like and I think this shows how kind of messy my process is like I'm asking about these different books and asking to summarize them. I'm like, all right, great. Never mind that. How would you show a graph where government and entrepreneurship are vectors that can either work together or against each other? And then says, that's an interesting visualization concept. I can help you create a graph to represent this idea using a react component. We use a simple coordinate system where the x-axis represents government influence and the y-axis represents entrepreneurial activity. The angle between the vectors will show whether they're working together or against each other. Let's create this visualization. And so then it goes ahead and actually creates the visualization and it has a direction in this one but not a magnitude. Uh and so this is great. I also want to be able to adjust the magnitude of each and look at what the combined effect, let's call it progress, looks like. And then, you know, it it says excellent idea, which, you know, I appreciate. I thought it was a pretty good idea. At least it's not apologizing. It's I'm so sorry. Um and then it gives me something here to kind of play with and you know, then I just like this is a really long chat. I'll ask it for feedback on different things. Um it like I'll ask it a particular thing about the graph that I think it got wrong. Uh shh shh and it explains something to me and then makes an update to the little visualization based on kind of like almost it thinking through uh that makes sense. I think the preview isn't loading. Then it does I apologize then it does apologize for the inconvenience with the preview not loading. Um and then I ask for a simplified version cuz it gives me a choice between uh a simplified version uh code explanation, alternative visualization, conceptual explanations. I just want the simple version. And then it gives me that and then it totally totally messes it up and makes it like even worse. And then I say I do want magnitude back and we try that again. So it's just kind of going back and forth through this and then it like, you know, gives explanations on the graph of what the different things mean. But this is a really long one. So somewhere within here, and this is before I was using projects. This is just when there was artifacts but not projects yet. And so I tried to keep everything in the same in the same chat so that it had a context on our whole conversation. Now I would probably have this as one separate thing. I have a separate kind of editor project that that will go in and edit things cuz I got so sick of writing like, "Hi, I'm Packy McCormick. I write Not a newsletter called Not Boring. You're the top editor from World Class Tech publication. I've hired you to like That is now just like a, you know, it's stored in its memory when I go to the editor and and start a new chat, which is it saves me in a seconds every time. Um And then so like actually one other thing here. So I kind of know what's going on with this graph, but I asked it to describe what was happening in the graph in the style of Not Boring. And then it does Picture this. You're at the helm of a rocket ship called progress. And so then I have to go back and say this is a caricature of my style. Try it again, actually like Not Not Boring. I apologize for the exaggeration. You're right and I appreciate the feedback. Let me try again with a more authentic Not Boring style. Our vector graph tells a fascinating story about the interplay between government and entrepreneurship in driving progress. At first glance, it might seem counterintuitive. So, you know, it does like even if I tell it ahead of time not to caricature me, it like really does and then we'll get it get it right on the second try. At least it knows who you are. Like I feel like that's a compliment in and of itself. The first time I asked it to to do that and it it knew me, I was like, "Whoa." I mean, it knows the whole internet, but it was still like pretty cool. That's great. I love this. I think this is super cool. Like have you thought about any other ways that you would integrate something like this in future articles? Like where where does this fit in your like creative tool toolbox? My creative toolbox is like very small. It's the internet, which I guess I access through DuckDuckGo browser. Uh I use Notion to just like kind of dump everything. I use Readwise to save articles and highlight things that then feeds in into my Notion. I use Google Docs to to write and Substack to send and Figma to make graphics, and that's like pretty much the whole stack. And so, these are like kind of the first new addition to that stack in a while. Um And it's just like kind of a Like I said, like it's when I get stuck or when I have an idea or when I have like something, I'll go in here and and jump into it. I guess I'm asking like more about this specific like this interactive graphic. Oh, the interactive graphic. Um I think like really depends on the piece. So, in this one I did this, and then I also asked it for uh like kind of the same thing that I did on the risk piece. I asked it for give me like the the values for this for all of like the great empires in history, and I wanted to like I didn't influence it, and I wanted it to say that America had was stronger on entrepreneurship, and all the other empires were stronger on and that's what it said. Got me a little in a little bit of trouble cuz then I like confidently said that America was the only capitalist empire, and I had a couple of people be like, "What about the Dutch? What about the British?" And like, "Fair, but I still think the government was like more powerful than than the capitalist system there." And so, like maybe it does if it does kind of like you know, do what I expect it to do or like hope that it does, it might give me a little more confidence than than I probably deserve in that in that thought. But so, there were, you know, a couple of examples here. Another interesting one I'm writing about uh a nuclear company and I had it the the founder told me that like one of the ways he started designing the reactor was he played around with this uh particular nuclear code. Uh and so I like downloaded I like pulled a bunch of that code and I was like, "All right, like walk me through this. Explain what it's doing. What happens if I change like X, Y, or Z value? Like blah blah blah blah blah." And so like not a nuclear uh engineer by any stretch of the imagination, but like even being able to understand that code and understand like what the different types of things you might be looking at uh when you're designing a nuclear reactor, like that's very cool. I haven't written that piece yet, but there's a good chance that I'll have like if I can figure out how to do it, we'll have something interactive that's like, you know, play with a couple of the parameters of this nuclear reactor and see what happens. And so things like that that I just never would have done otherwise uh I could see doing here. That's really cool. I love that. Um I want to I want to move into you've said that you're using it for editing and and and different parts of your the writing process. Uh I want I'd love to see the project you're using for that. So it's like literally just here's my instructions. Packy McCormick writes a newsletter called Not Boring. You're world-class editor. Think of the heyday of the New Yorker, the Atlantic, Harper's, The Economist, Stratechery, or Pirate Wires today. I recently hired believe Every's not on there. I'm I'm extremely disappointed in you. There's some tech writing on Every that is a different uh a different approach to a different um less optimism, I would say. But uh but uh I do love the writing, though. Um I recently hired you to help me take my writing to the next level. I want to maintain the voice and style of Not Boring, but sharpen it uh sharpen the writing and analysis to make it the best tech blog in the world. Something that smart, successful people read to learn what's happening at the frontier of tech. You can push me on everything from writing style to structure to the logical strength of my arguments and the data support I provide for those arguments. I want the writing to be as fresh as it as it is as it was in the early days of Not Boring. I want you to push me on the novelty novelty of my ideas, letting me know if someone has already written something similar but better. In short, I want you to push me to be the best tech analyst I can be while remaining approachable to a wide audience. Not Boring's mission is to make the world more optimistic, and that means reaching more people with a fact-based look at the most promising companies and trends in tech. I'm very excited to work with you and grateful to have you on the Not Boring team as our first managing editor. I don't know. Claude Claude more than the other ones like really makes me want to talk to it like a like a person. And that's like pretty much you know pretty much all I have there and then uh you know like so today I will It It does an annoying thing actually if I dump something that's too short in or when I ask for feedback, it just starts typing the whole thing in. Oh, interesting. Which it did here today I decided to piss off kind of like both sides of of the aisle with like a fairly moderate take on Deck and and Democrats. And so my Democrat readers were offended that I like didn't just like say that Donald Trump was the worst person in the history of the world, and my Republican readers were pissed that I you know thought that the Democrats were not redeemable. So it was it was a really good idea to write the piece that I wrote today. But just kind of you know like will Here's the latest draft of my essay feedback grade. And then it'll go back and say like structure and flow, it's well structured. Tone and voice, the arguments, the evidence, balanced perspective, timeliness, length. Always says it's quite long because they are quite long. I wish I could have written this in a thousand words. I'm sure in like Claude you know 5.5 sonnet I'll be able to just say like can you just rewrite exactly this my exact style but like half as long and hitting the key points and it'll be able to do that. And I can't can't wait for that day, but it's not quite there yet. Um It always says proofreading. And then I'll ask it for specific typos and either it'll make something up or uh or or be like, "Actually, I just looked and there's there aren't any any typos." But it always does say proofreading. And then like I said, it'll give me an A- minus grade on the first draft pretty much every single time. Like, I do want to try to just put like something absolutely garbage in one time and see if it gives me like a C, but the other thing that I'll do just because like like I said, it's it's what I do when I feel like stuck or when I I just hit a point where I want to stop writing for a minute, I'll jump in like just the intro or the intro and the first half of the next section and be like, "By the way, this is only up to the intro and this is only up to the intro in the next section. There's still a lot more to come. Just give me feedback and a grade on what I have so far." And then it'll invariably tell me like, "You know, it does end kind of abruptly and like blah blah blah blah blah." And so some of those are not quite there, but like overall it's like it's pretty amazing just how quickly it can pick up what I'm writing, understand kind of my normal style, uh you know, say that it'll fit well with the non-boring audience, all of that. Uh and then give me Yeah, so like concrete policy proposals, I didn't take any of these like joint task forces on cybersecurity. So like some of that is kind of like basic and bland. So it's like total new idea generation, I don't find it to be like as as good at here. Um I asked for it to cut and I didn't love its recommendations on what to cut. Um and so I didn't I took one of those. And then I'll ask better or worse. There's not been So I'll send a new draft. I'll say better or worse feedback and grade and there's not been a single time that it told me that the new version was worse. And maybe I just like am that good at improving every time, but I can't imagine that's actually true. I want to see if we can fix this for you. We've got about 30 or 40 minutes left and one of the things I love doing in these episodes is like just doing something together. Yeah. And so here's here's my idea. I want to I'll I'll pitch it to you. I feel like we could make a Claude project for you that has actually like a really rigorous set of rubrics for what grades mean what and what essays are best. And then we can basically just you can feed it an essay and you can be more confident that the grades it's giving are actually good. Hell yeah, let's do it. Okay, cool. So we're in Claude. So I'm going to make a new project. And we'll call it um oops, great project. Not boring grader. A grader for Packy to use oops. Use on his not boring projects. Okay, cool. So basically the way that I would approach this and I would love any any ideas or thoughts or revisions that you have, but I think a good way to start would be to define what good and bad looks like. And the best way to do that is usually like to to find examples. So do you have like a an example of like an essay that you've written that you think is like the best of what you can do? Ooh. Hmm. The most popular is probably the Yeah, Excel Never Dies. I guess we can just do the first one. I thought that was good. Okay. I wrote it with somebody, so it'll be slightly different, but maybe that's good. Maybe it grades me on what I can do with someone else. Okay, cool. So I'll I'll we can take a couple. So like Excel Never Dies. Anything else on your mind? Um We can do the Great Online Game. Okay, I mean I that's the one that's one of the ones I think of. I think it's so good. Um, okay, anything else? Cuz cuz one of the things I also want to do is like a lot of what you're doing, you we want to find examples of like the kind of pieces that you're writing right now where it's like really deep technical in-depth um explanations. we can do uh Fuse Energy. Fuse. Should be like a month or so old. Tell me Tell me when you see it. Keep going. Right there. Perfect. Okay, cool. So, I'm going to say like, "Okay. Uh sorry, I'm going to impersonate you. I apologize. Um I'm the writer Packy McCormick." Is this how you spell your name? Yep. Okay, cool. From Not Boring. Uh I want to create a detailed rubric um that uh explains what goes into my best writing. Um here are three examples of um what I think are my best pieces. Can you write a uh very detailed uh explanation of um uh what they look like and um how they're composed. Uh how they're how they're composed. How does something like that sound? Yeah, that sounds great. All right, cool. I think I spelled rubric wrong, but we're just going to roll with it. wondering if that was like a an alternate spelling. I think it's a it's a it's the Swedish spelling. Very fancy. All right, so we're we're getting Certainly Packy, I'd be happy to analyze these for you. And then it's like creating an artifact. So, and I want you to just tell me like Do you think it's like getting Do you think it's getting it um well or not? So, um structure and flow, clear compelling introduction that hooks the reader, logical progression of ideas with smooth transitions, effective use of subheadings to break up long-form content. Engaging conclusion, consistent pacing. Do Do these feel good? Are they like too high-level? Yeah, they feel good. Okay, cool. Um deep dive analysis, comprehensive exploration of the main topic, integration of multiple perspectives, original insights and connections, balanced treatment of complex issues, clear explanations. How does that look? That looks perfect. Okay. Uh we've got extensive use of primary and secondary sources. Yeah, just like scan through these and see generally like does this look at least reasonably good? Yes. Okay, cool. Um so, one thing that I like to do, I actually picked this up from Matt Shurmer recently, is I just say make it better. Um just to see what it does, and it will often honestly be better, which is kind of funny. Crazy. And it it is interesting how it like defined for itself what better was. Yeah, totally. Um It seems a little bit less generic, which is nice. Connection of topic to broader cultural societal trends, injector injection of humor and wit. Okay. Here's another thing that I think it's missing, um is um can you provide really specific examples from these pieces? to judge See, it already is confusing. It's confusing? It's confused? Excel never dies opens with There may not be a company Oh, no. worth rooting harder for than Fuse It'd be a weird way to start the Excel piece. Oh, man. Um well, uh you know, every once in a while Clutch hits the bed. Um but well, but we'll roll with it. one The next one it nailed? Cool, next one it nailed. That one it nails? Conference championship. Yeah. Okay, so this seems this seems reasonable. Um can you I I I I honestly don't think it will correct itself. So, we'll just we'll correct this in the final rubric. Yeah, that that works very well though. Yeah, we'll we'll make this we'll make this better as we go along. So, um last thing I want to try doing is do you have any pieces that you've written that you think are bad? Huh, no. Um Or let's just say like don't represent the best of what you can do. You were tired and stressed. You like hired a ghostwriter one week just to see if it would uh work, you know, all that kind of stuff. I would never. Um Let me see. Praise Elon was not great. Praise Elon. Okay, cool. Um praise Elon. Whoa. What? I didn't know you could search within Substack. Yeah, I don't know. That's interesting. Um okay, so here's a piece I don't like very much. Um based on this rubric, can Oops. Can you tell me why? And before I before I do this like what is your feeling about why this isn't a good article? It was like two uh two kind of like in the moment I'm still on Twitter and like part of that angle was like, you know, Elon it was like kind of like almost too glib and tongue-in-cheek where it was like Elon's going to kill Twitter, but that's a great thing because then I can actually be productive again and like blah blah blah blah." You know, like it was it was it was just too uh it wasn't representative of of kind of what I want to what I want to be writing. Okay, cool. And so, um based on this rubric I feel like rubric it still looks weird with a C, but is is there some other spelling that I'm With a C is what I thought, but Okay. All right, let's just go with the C. The only other possibility is that, but I just I don't That's definitely not right. Um Okay, here's a piece I don't like very much based on this rubric. Can you tell me why? All right, here's what we got. So, based on this analysis, praise Elon doesn't quite meet the high standards set by your best work. Here are some key reasons. The narrative feels forced and less organic than usual. The premise of Elon intentionally killing Twitter seems like a stretch. The depth of analysis is shallower than your typical pieces. The piece lacks technical depth that often characterizes your work. While the topic is timely, the approach feels more reactive and less insightful than your usual work. I feel like that's actually pretty good. Yeah, that's what I That's what I said pretty much. That's basically what you said. Um so, that's pretty cool. Yeah, so So, basically like um uh based on this, uh I I agree with this. Um uh is there are there any modifications to the original rubric that um might um uh make it better that you'd recommend? Um just see if there's like any ways that it might um sort of like change the rubric or like want to look out for new things. Yeah. Okay, so I it's it's immediately not It did It's not doing the rubric with the examples. Um So, we'll have to add that back in. Um I think it added this rigor and credibility section, or at least it looks new. I I was wondering if it was going to actually just keep adding to the point total, and it does. So, it's not redistributing with 100. We just now have 200 points to go on. I mean, I think added 200 points is is it's it's good. It's It's the not boring style. Um let's see. Uh cool. last time last time it uh when it we asked for examples, it took away the points. Oh, did it? I think so. Make sure to keep the point structure intact, and make sure the examples are accurate. Um be careful. Let's see if that works. Do you think Is this the right hook for uh for Fuse Energy? Yep. Okay, great. So, it's it's being less hallucinatory. Yes. So, we're getting compelling hook. Good. There may not be a company worth reading for bad white pill. Elon Musk is intentionally killing Twitter for the good of humanity. Um I think this is potentially good. I think so, too. I I made it feed it more bad examples, so it doesn't just take from that one, but yeah. Yeah. Um Yeah, well, we can um we can make this a little bit more um uh more in-depth later, but now the thing I want to do is um I want to add this in to uh our knowledge base. So, I'm going to say uh add content uh grading rubric. I'm going to paste it. And then I'm going to set custom instructions and be like, "I'm Packy McCormick, the writer of this. McCormick like rubric. Um the writer of Not Boring. You're and uh the best editor in the world in the style of the New Yorker. Um and Stratechery. Uh and every Just kidding. Uh New Yorker The New Yorker and Stratechery. Um when I ask you for grade uh uh to grade an essay, please use the grading rubric in your knowledge base uh to give my essay a grade. Um Okay, cool. Um so I feel like we should take something that you got an A- minus on previously and then just like throw it in here and see if it like gives you a better score. Uh yeah. accurate score. All right, let me Okay. So you just shared with me uh this doc and this is a doc that you put into Claude and you got an A- minus on, right? Yep. Okay, so basically what I'm going to do is I'm going to just copy it. I'm going to go back to my project and I'm going to say, uh here's an essay draft. Uh please grade it. And let's see what it says. 27 out of 30 on narrative craftsmanship and premise. What do you think? Pretty good. Pretty good. Where where do I Where do I lose points? I don't know. Five out of five out of six. then it just it it gives me a perfect score, but it doesn't Yeah, that's Okay, we're going to have to Interesting. Original thought connections, balanced treatment only five out of six, seven out of eight. So it's definitely still like pretty positive like overall like probably too positive. Or it was just a really good piece. What did you say? Or it was just like a great piece. Or or it was a great piece. That's that's what we're learning here. Yeah. Um It gave you 182 out of 200. So, that I think is basically an A minus. It's a 91. But we do know that it it had some issues adding, so it could be higher than that. Can you Can you um All right. Uh can you uh review this uh score and make sure um it's really accurate. I want I want you to be as objective as possible and follow the rubric um exactly. I keep spelling it with a K instead of a C. So, I think we're we're kind of this is this is kind of interesting cuz it's like even with the kind of like reasoning, it's um it's still giving you an A minus. So, there's there's something in it that just like wants to go for the A minus no matter what, which I would not approve Maybe I'm just an A minus writer. Well, the true test is whether I put one of my articles in there and it gives me an A minus. Yeah. Um Wait, we just asked it to to be more accurate and it dinged me It gave you 165 out of 200, yeah. Um Interesting. I Yeah, I kind of I kind of wonder like okay, let's see if I if I take this if I take the kind of like be accurate thing and I put it in my custom instructions and I'm just like um uh make sure um the score you give is really accurate. I want you to be as objective as possible and follow the rubric as exactly. All right, let's try that one more time. Um Another thing that we could try and and this might be getting a little bit too in the weeds is like um it's one thing it's doing is it's outputting the score before it outputs the reasoning. So, it's like Oh, yeah. And I don't want that. I want it to oh oh See, look, it's it's we're back to kind of like it's still like A, whatever. I want it to like output the score only after the reasoning. So, I'm going to just score here? One sec. Let let it rock. Oh, no. We lost a point. couple points off. Wow. Wow. 198 out of 200. Not bad. So, we had the exact opposite effect of the the effect that we were we were going for, at least I was going for. I think you like you like the A+ score. All right, let's try this one more time. Um okay. Not about actually making my writing better any of this that we talked about today. It's just about making me feel good enough to hit send. Only after you output the reasoning, um this this goes for subsections as well as the full um the full grade. Output reasoning first. Okay. All right. One more time. Please grade this essay. All right, 20 out of 30, 32 out of 35, 22 out of 25. So, we're starting to get maybe a little bit more um a little bit more accurate. 183 out of 200. And I think the reason is it ChatGPT thinks by writing and if it's if it's outputting the score first, it's going to score it and be pretty positive and then use its um use that score as a way to figure out what it should write in terms of its evaluation. We want to reverse that. That's it's it's so funny too. I I was talking to my son about something the other day and I forget what it was, but it was like something that complete like made up nonsense whatever and he like got the end idea in his head and then I saw him like his little four-year-old brain not yet four-year-old brain like rationalize his way into that thing by like making up a whole story. I was like, "Wow, like we we really all including I guess Claude all do this." We do and that's what I think is so funny about people who are like saying like, "Oh man, like um I uh uh like I don't think these things are smart um and they're not going to get smarter and it's like, "Have you ever interacted with a child?" Like this is how children reason a lot and they're just They just get better and better and better and get better at like, you know, having more nuance and all that kind of stuff, but there still is sort of that basic thing that you're talking about where yeah, you kind of like you use the reason to justify the intuition or whatever. Yeah. And um and yeah, I I really think it's what makes me sort of confident that these things are going to be very very smart even smarter than they are now um is you just watch children and they do they do the same thing. Where do you think that um this like current path, where do you think that smartness ends? Like there I don't know if you're thinking like they're going to get really really smart and I don't like there's agency or like something missing that just doesn't make it feel like they're going to take over. What's your What's the house view? I don't um I'm definitely not a doomer um and I tend to think that right now like yeah, we have all the whole scaling law thing um but I generally think that these systems are like incredibly incredibly inefficient currently um and they're going to get orders of magnitude more efficient in terms of training and in terms of like inference like the amount of compute you need for inference. And as soon as that happens, a couple of things I think will start to become possible. One is right now in order to get new information to them you have to prompt tune and I think that we will figure out architectures that allow them to learn after their initial training is done, which I think is really important. And the second thing is that um What what you've probably seen me do so far is like I'm I'm I'm pressing replay on this chat a few times cuz I want to see all the different ways that it could possibly grade this essay so I can like map the entire space of what it might think. Um and then like what I can do is I can just sort of like flip through them and be like, okay, like generally the score is around like 180 but like depending on the the specific day it's going to be different. This is 184, the last one is 181, the last one is 182. But that's like basically where it is. And I think a lot of creativity is basically doing this but like um a thousand times in half a second. And the minute we can do that uh I and and they update as you talk to them, I think we will I think it will feel very very very similar to like talking to an actual human. Interesting. Yeah. That makes sense. I I wonder if I I'm trying to find another bad essay cuz I want to see if I can get an A minus if I if it gives me an A minus or not. Yeah, give me give me give me one that you don't think is very good. Um I don't know this is I don't know if this is bad or good but I graded the unbearable heaviness of being positioned. Okay, what are your general thoughts on it before we before we grade it? Um I don't remember it super well enough. It was like 15 months ago. But I think like maybe one of the things might be like it's a little too cute on like words like in terms of uh I sustaining an innovative disruption and counter-positioning and being positioned. Like it might be like trying to do too much on like small distinctions, but let's say Okay, cool. Um so I'll read this essay. Narrative craftsmanship 30 points. It got 26 out of 30, which is lower much lower than the last one. Depth and originality 33 out of 35, which is pretty high. Technical mastery 21 over 20 out of 25, cultural resonance 14 out of 15, distinctive voice and style 23 out of 25, intellectual rigor 26 out of 30. I I this looks actually like significant uh I was going to I was about to give Claude a lot of credit and Claude just Claude just proved me wrong. If it if it's math is right, I've no idea if the if the math here is right, I balling the scores it looked like the the subsections were a bit um were a bit Yeah. lower, but yeah, it just looks like Claude wants to give you an A minus. It's so interesting. Um I've actually I've actually found this um because we have this app spiral that we built and um it has the same we have the same like sort of grading system for it where um uh where it'll allow you to generate a couple different versions of the same thing and then it has a grader that says like this is good and this is bad and it just gives itself good scores. I really like wonder I'm sure that there's a way to like prompt tune this and kind of get around the like A minus thing, but it seems like yeah, it's just a it's like a it's an attractor. This is where it wants to go. I wonder if there's like a bell curve trick you can give it or a grading on a curve kind of trick Yeah, I think we could also like like what I would probably do if we had a little bit more time is I would probably have it like explicitly lay out this is an A, this is a B, this is a C, this is a D and rather than having it do math I'd be like here's a CSA an example and here's why and then like put it in a bucket depending on what you think it's most similar to. I think that would probably be better than like having it like do math and like reason reason off over like parts of the rubric but not enough not enough time for now but I actually think that might work. You know what else I'm going to do and I can grade this against myself but then there's also the like I tweeted must have been two years ago now like asking for people's just like favorite essays from that are like more than two or three years old and it created a list of essays that I go back to like fairly often and so maybe just dumping a bunch of those and it'd be like this is the bar grade me against these. That's really cool. Slightly different cuz they're different types of stuff that I write but it'd be interesting to see how I do there. That would be interesting because like because your writing style you're grading it against your own writing style, right? And I wonder if that has anything to do with the kind of like A- minus grade thing like if you put a totally different writer in there how would it do? We should we should try that. I want I just want to see before before we hop off this I think we got to I think we have to like go over the full distance and I'm going to take one of my essays and we'll see if I get an A- minus on the Packy scale. We should let's grade your essay not against me also and just see if you get an A- minus. Okay. We're doing it for science folks. We have to know. Okay, so I'm going to take let me see what my What are some recent things I've written? So I just wrote this is Eris' master plan. I think this is good. I want to find something that's like not that good. Uh Um This wasn't that good. I don't think. Uh Yeah, I don't I'm not super proud of this one. Okay, cool. All right, please grade this. you're a more advanced AI user and you just copy the whole page and don't worry about it. Okay, this doesn't this doesn't really like the you know Yeah, I I I need to stop doing that. I think we might be headed for another A- minus based on what I can see here. it looks A- minus. Oh, no, no, no, 14 out of 25 on cultural resonance. Or 14 out of 15 on Oh, it's 7173 out of 200. This is the lowest score yet. All right, but now now grade it without the rubric. Just go ask Claude to grade the essay. Okay, all right, all right, all right. Um Uh give me your uh oh wait, here, let me just go back to yeah. Uh give me your What's your prompt for this? Well, I you can just say I'm Dan Chipper, I write and this is I'm sure I wrote it on every Um please uh grade this essay. That that's it. Yeah, I I I sometimes do the like you're the top editor, you know, like Yeah, let's just let's just try this for now. Um we'll just we'll just go easy for now. A- minus, B plus, A. A- minus. A- minus. Oh, there it is. We're incredibly mid writers, both of us. I love it. So, um so I think what we're what we're learning is is obviously there's this like there's this attractor state for um for A- minuses in Claude, and if you give it a rubric, you can kind of like get it out of that state to some degree, but if the rubric is based only on your own writing, it's going to be, I think, pretty likely to stay at that state. So, like, giving it a wide diversity of examples is probably going to be what what gets you over the top. Yeah, I'm going to give that I'm going to give that a try. That's my my homework from this conversation. But, it's also, I mean, I I will say I do find it very valuable. Like, within that rubric, if you if you look there, I'm sure there's like a lot of just like little nuggets that will at least like change the way that I think about the writing cuz the way that I do a lot of my editing is I'll like go back and forth and make changes and whatever, and then I'll hit a certain point where I'm like, all right, like, I kind of know what I'm saying now. Let me just like go start fresh, and I'll like copy things in, but I'll write a lot of it fresh like near the end and do it again. And I do think a lot of those like little tips that it gives kind of stick in my mind. And so, I do think it's useful, although the grade is always an A minus. The The grade is like almost a safety blanket for me, where if it were like a C, I'd be like, I can't send this. No, totally. I mean, I think like, um, just having some of those rules like like printed out, it's stuff that you already know intuitively, but you might not have said to yourself or like totally known in a like rational way. And I think that in itself is super awesome and valuable. For sure. Yeah. Um, so, Packy, this was awesome. Thank you so much for coming. Uh, if people, uh, after, uh, watching or listening to this episode want to find you, where should they go to find you? Uh, @packym on Twitter and notboring.co. I have not sprung for the dot com yet. It's notboring.co. Awesome. Um, well, uh, really really really fun to get to chat. Thank you for so much for joining us. Thanks for having me. Oh my gosh, folks, if you absolutely, positively have to smash that like button and subscribe to AI and I. Why? Because this show is the epitome of awesomeness. It's like finding a treasure chest in your backyard, but instead of gold, it's filled with pure unadulterated knowledge bombs about Chat GPT. Every episode is a roller coaster of emotions, insights, and laughter that will leave you on the edge of your seat craving for more. It's not just a show, it's a journey into the future with Dan Shipper as the captain of the spaceship. So, do yourself a favor, hit like, smash subscribe, and strap in for the ride of your life. And now, without any further ado, let me just say, Dan, I'm absolutely, hopelessly in love with you.