Episode 33 of Every's podcast features lead writer Evan Armstrong and host Dan Shipper in a workshop on how professional writers use AI tools—ChatGPT, Claude, the AI word processor Lex, and Every's prompt builder Spiral—to improve their writing. Topics include using Claude and ChatGPT to articulate and explore personal taste in writing and art, converting research notes into a thesis with Claude Projects, publishing two pieces weekly, overcoming writer's block with Lex, catching mistakes like passive voice, crafting metaphors with Claude, and building an audience. Timestamps and links to resources are included in the video description. # Channel Presentation Observations — "Supercharge Your Writing With AI – Ep. 33 with Evan Armstrong" ## Intended Audience - **Writers and content creators interested in AI-assisted workflows.** The conversation is framed explicitly around "talking about writing... particularly in the context of AI like how are we using in each part of the writing process how are we each using it." - **Existing channel followers familiar with the guests and team.** References like "for people who don't know you" coexist with deep-cut asides ("for the every heads... beyond our like deep cut fans"), suggesting an established subscriber base. - **People considering a paid course.** The episode closes with a pitch: "you should follow Evan on Twitter... and obviously subscribe to every... we'll put the link down in the show notes" for the course "How to Write with AI." ## Claimed Scope - **AI usage, demonstrated through professional writing practice.** The episode is structured into "four sort of distinct areas... taste... topic... craft... and audience," mirroring the course structure. - **Practical tooling focus.** Tools demonstrated live include Claude, ChatGPT, Lex, Spiral, and Consensus — the channel presents itself as hands-on rather than theoretical. - **Series format.** The title labels this "Ep. 33," indicating an episodic show. ## Explicit Self-Description - Host Dan Shipper introduces himself implicitly as running the channel: the outro (apparently AI-generated comedy) calls it "a journey into the future with Dan shipper as the captain of the spaceship" — explicitly naming the host. - The show is named in the outro: "smash that like button and subscribe to Ai and I" — i.e., the channel is **"AI and I."** - Guest identity is stated directly: "you are the lead writer for every... you write twice a week for every" and Evan teaches "a course on this... called how to write with AI." ## Demonstrated Presentation Patterns (Observable, Not Claimed) - **Conversational, collaborative format** rather than pure interview: "a little bit less like me just interviewing you and more like us together talking about writing." - **Live software demos** on screen (Claude projects, Spiral tweet generation, Lex editing), showing the channel demonstrates tools rather than only discussing them. - **Humor and banter** ("this is where the every beef of 2024 starts"; "I'm costing myself money") as a regular tonal feature. - **Affiliated media ecosystem:** the channel cross-promotes a newsletter ("every"), a SaaS tool ("Spiral"), and an educational course, indicating a creator operating a broader media business. - **Audience-scale claims by creator:** "every's audience of... 78,000" — a creator-stated figure, not independently verified in the material. ## Notable Unclassifiable Content - The final outro paragraph is a hyperbolic, apparently AI-written comedic sign-off ("I'm absolutely hopelessly in love with you") — consistent with the channel's AI-experimentation theme but presented without explicit labeling. # Delivery Observation: Supercharge Your Writing With AI – Ep. 33 with Evan Armstrong ## Overall Delivery Format - **Conversational two-host dialogue**: This is not a monologue lecture. Dan Shipper and Evan Armstrong alternate frequently, riffing off each other, interrupting playfully, and doing live demos of AI tools (Claude, ChatGPT, Lex, Spiral, Consensus). - **Structured by a pre-announced framework**: The episode is explicitly organized into four segments, stated up front and repeated: **taste, topic, craft, and audience** — matching Evan's course structure. > "we've split up the segments... into four sort of distinct areas one is like taste... two is topic... three is craft... and then four is audience" ## Tone - **Casual, jokey, self-deprecating**. Both hosts use humor constantly, including fake antagonism ("this is where the every beef of 2024 starts") and running jokes. - **Recurring joke about Annie Dillard**: Dan's tendency to reference her is a running gag. > "the running joke at every is that everything I relate everything back to Annie Dillard" > "the Annie Dillard will continue until morale improves" - **Bleeped profanity and edgy humor** appear occasionally ("holy [ __ ]", "it's just the [ __ ] sandwich you have to eat"). ## Vocabulary and Recurring Phrases - **"Vibes" as a working term** — used repeatedly for describing taste: > "can you tell me the Vibes of these writers in detail" > "language models tend to do well with Vibes" - **"Make it better"** — Dan's stated core prompting habit: > "I'm just basically saying make it better make it better make it better" - **"Reflect, don't rewrite"** — Dan's task-splitting prompting pattern, explained and demonstrated multiple times. - **"Rote work" / "rot labor"** — Evan's repeated framing of what AI should automate: > "the accompanying tools that you can use to automate away the rot work" - **Filler-heavy, speech-like style**: constant "like," "um," "you know," "sort of," "whatever" — consistent with an unedited conversational podcast transcript. ## Teaching Habits - **Live demonstrations instead of descriptions**: Both hosts screen-share AI workflows in real time ("we're doing it live folks"), including a live retry of Dan's taste exercise and Evan's Consensus demo. - **Explicit meta-commentary on prompting technique**: Dan narrates his reasoning while prompting: > "I want to split up the task into two... understanding that there are multiple tasks involved... helps" - **Naming specific tools and authors**: Concrete references throughout — Claude, ChatGPT, Lex, Spiral, Whisper, Consensus; writers like Sapolsky, Pirsig, Le Guin, Mary Oliver, Annie Dillard. - **Contrast as a teaching device**: The hosts repeatedly highlight their opposing workflows (sauna ideation vs. voice-memo + AI synthesis; "clear the runway" vs. "thought partner"). > "it's the exact opposite of how I think about my writing" ## Communication Patterns - **Question handoffs**: Both hosts end long turns by redirecting ("I'm curious Dan for you like how do you articulate your taste"). - **Friendly adversarial fact-checking**: A mid-episode spat over whether Dan used Claude or ChatGPT ("don't come at me unless you've got receipts") models playful peer accountability. - **Ethical pause in an otherwise tactical episode**: Dan raises the plagiarism/attribution question directly, and both acknowledge unresolved uncertainty ("we don't have it figured out"). - **Outro pattern**: Ends with course promotion ("how to write with AI... starts September 17th of 2024"), a follow plug, and an exaggerated comedic AI-generated outro ("you absolutely positively have to smash that like button"). ## Uncertainty Notes - **Host attribution in the cold open**: The first ~60 transcript seconds appear to be a pre-roll excerpt; speaker labels are not marked in the transcript, so attributing individual lines to Dan vs. Evan rests on contextual cues (e.g., "Evan welcome to the show" implies Dan is the greeter). - **Delivery pace/gesture/timing observations are unavailable** — this analysis is limited to the text transcript; no visual or vocal evidence is present. # Position Record: "Supercharge Your Writing With AI – Ep. 33 with Evan Armstrong" **Speakers:** Dan Shipper (host of *AI and I*, co-founder of Every) and Evan Armstrong (lead writer at Every). Note: transcript attribution is inferred from conversational context (Dan hosts, Evan is the guest teaching "How to Write with AI"). --- ## 1. Framework: Four Areas of Writing with AI Evan structures the conversation (mirroring his course) into four areas: - **Taste** — how do you know what good is - **Topic** — how do you pick what to write about - **Craft** — outlining, writing, editing - **Audience** — how do you reach people --- ## 2. Taste ### Evan's definition > "Taste is not whatever people in Brooklyn are doing... taste is the ability to articulate why something is good." - Calling something "awesome, loved it" isn't taste; describing *why* you liked it is a discernible skill. - Evan says he couldn't articulate his own taste until he started using AI more. - His personal bar: **entertaining reads about boring topics** — "the more boring the topic and the more entertaining it is, the more skill that's presented." He writes about accounting; Dan about tokens. - He contrasts "capitalist taste" (taste aligned to product jobs-to-be-done, citing Lenny's Newsletter: "make me smarter, make me money, entertain me") with his own approach: he only writes things he'd enjoy reading, and deviating from that fails for both audience and himself. ### Dan's taste discovery exercise - Dan describes his piece **"What I Do When I Can't Sleep"** (June 23, 2023), written during an Every identity crisis, using ChatGPT and Claude. - His articulated tastes: intellectually stimulating/analytical/philosophical writing that is also emotionally resonant, poetic and lyrical (Annie Dillard), accessible on hard topics (Robert Sapolsky), practical, interdisciplinary looks at the human experience, humans and technology, creativity, philosophy, business. - He states he could see this pattern across his life but **could never say it until Claude and ChatGPT told him**; once articulated, it becomes something to aim at. - **The exercise:** keep a running Notion list of writers you like (Sapolsky, Robert Pirsig, Ursula K. Le Guin, Mary Oliver, Bill Simmons, etc.), paste into Claude: "tell me the vibes of these writers in detail," press retry to explore the latent space, then ask it to synthesize into a five-sentence taste summary. - Dan on the output: > "When I first did it, it was like looking in the mirror for the first time... this is what I look like and I like it." ### Evan's observation / disagreement-adjacent point - Evan notes Dan's writing was lyrical *before* the exercise; the change afterward was a **new emotional plane** — comfort writing the way he wants to write. Dan agrees, tying it to his piece "Admitting What Is Obvious" and the fear of admitting identity (cutting off other avenues, fear of ridicule). ### Evan's extension: multimedia taste - Evan's thesis: **taste is "a blob of emotional permission"** not constrained to one medium; being a great writer doesn't mean only reading books. - He consults his wife Morgan (Humanities PhD) and ChatGPT to explore related works across media. He worries writers who "only read" get in a rut. - Live demo: ChatGPT given Dan's favorite authors (Dillard, Pirsig, H.D.F. Kitto, Ian McGilchrist) recommended Tree of Life, My Dinner with Andre, The Seventh Seal, 2001, Wings of Desire. Dan reports he **hated Tree of Life**; Evan diagnoses the LLM failure mode: "they'll either go way too deep or way too surface level." - Refined prompt ("passing knowledge in cinema, after 1985, more accessible") yielded Truman Show, Walter Mitty, Dead Poets Society, A Beautiful Mind, Into the Wild — better received. - Evan: the hard next step requires **emotional activation energy** — actually consuming the works. - Dan adds taste also includes exploring chains of influence; LLMs are excellent for traversing who influenced whom. **Minor factual dispute (preserved):** Evan teases Dan that the original exercise used ChatGPT, not Claude; Dan insists he did both ("the key to internet success is nitpicking needless details" — Evan). --- ## 3. Topic ### Evan: sauna method (AI-adjacent, minimal AI) - Publishes twice weekly plus a chunk of the Sunday digest; no time for elaborate ideation. - After lifting, sits in the sauna 15–20 min on Mon/Wed/Fri; "I just sit in the sauna until something appears in my brain... that's literally it." Ideas are never the hard part; **picking the idea** is. The first subconscious idea is usually the best. ### Dan: voice memos, advanced voice mode, thesis distillation - Walks and records voice memos, transcribes with Whisper, feeds to Claude/ChatGPT to extract interesting threads; or brain-dumps to ChatGPT advanced voice mode and asks it to reflect back. - Stores headline-level handles in Things (e.g., "Generalists Own the Future"). - For a long in-progress piece ("Seeing Like a Language Model" — LM architecture vs. ancient appearance/reality debates), he maintains a months-long note file, puts it in a **Claude Project**, and asks Claude daily to write a thesis statement from his notes. - Prompting techniques he advocates: - Repeatedly say **"make it better."** - Ask it to **critique first, then rewrite** — "just reflect, don't rewrite" — splitting tasks improves output. - Treat each response as a **kaleidoscope**: stochastic variation lets him see his notes from new angles; he ultimately writes the thesis himself. - Evan's response: this is "the exact opposite" of how he works — no note-taking, everything in his head; he means this descriptively, not judgmentally. ### Evan: Consensus for rigor - Uses **Consensus** ("LLM mixed with Google Scholar") to fertilize intellectual soil on fundamentals (e.g., open-source models and monopoly dynamics). - Claim: > "If you read like three papers you've gotten to about 95% of the depth of most experts" — the pre-LLM problem was knowing *which* papers; citations were a flawed metric. ### Shared product wish - Dan wants a personal "consensus data bank" of all read/adjacent books and papers. Prefers **bigger context windows over RAG** in general, but acknowledges whole books add extraneous context that distracts the model — **deselecting is as important as selecting**. Evan suspects the right answer is "basically RAG." --- ## 4. Craft ### Evan's tools - **Conclusions:** his weakness; pastes drafts into Claude asking for 10 subheads/thesis options — "almost always all 10 of those are wrong, but by being able to articulate what is wrong... I'm able to say what is right." - **Lex custom prompt** ("What Would Evan Say"): system prompt containing past articles for tone/voice, automated first message; generates 10 ending ideas instantly. - **Lex checks:** e.g., passive voice (which editor Kate flags); cleaner drafts to his editor yield better edits. - Strong claim: you're "maybe one... Claude model away from being able to eviscerate like 20% of the editing department at the Atlantic." - He's shifting AI labor out of chatbots into in-line tools because chatbots are "distracting and clunky." ### Dan's tools - Writes "Seeing Like a Language Model" in **Lex**; uses AI-written generic passages (e.g., Plato's theory of forms) as placeholders to keep momentum, intending to rewrite them in his own voice later. - Uses **@Lex comments** ("turn this into something interesting") to expand sections and generate examples in context. - **Metaphor-building collaboration:** iterated with Claude on a Socratic "sea of words" metaphor adapted to pragmatism — first outputs "not that great," but a bad suggestion pushed his brain toward a better one; he then fed in relevant numbered notes from his project, asked Claude to weave them in, reflect, and revise. The final water/drop-of-water metaphor he calls "beautiful and amazing... one of the central metaphors of the piece" and says it "totally would not be possible... without Claude." The whole exchange took ~10 minutes. ### Stated difference in stance (preserved as tension) - Evan: so much usage difference stems from **publishing deadlines**; he wants AI to "clear the runway" — "I got the juice, you fix my emotions, give me the next step." - Dan: prefers a **collaborative thought-partner** process with note-taking. Evan adds note-taking is a psychographic — fine if your brain doesn't work that way. --- ## 5. Audience ### Spiral (Every's tool) - Described by Dan's analogy (via Evan): a "Mario pipe" transforming one text into another format. - Dan's insight: writers constantly **translate core creative work into other formats** (headlines, tweets, show notes) for distribution — skilled but repetitive work; Claude with the right prompt gets ~80% of the way. Built as an MVP during Every's "think week"; team and EIR Brandon productized it; approaching 5,000 users. - Evan uses it mainly for **essay → tweet** ("social media is the bane of my existence"). - Dan demo: converted a LessWrong summary of the OpenAI "Strawberry" reporting into tweets via an internal spiral, edited ~5 minutes in bed, got 30,000 views/157 likes — versus 30–40 minutes of writing wholesale. Result: he tweets more and engagement is way up. ### Ethical dispute over transformed content (unresolved tension) - Evan raises the "moral horror" case: taking someone else's content, transforming with AI, monetizing on top. - **Dan's position:** it's plagiarism if wholesale lifted without attribution; it's fine if **summarized in a new way for your audience with attribution** — he cited and linked both The Information and the source. He acknowledges blurry lines: we need (1) tools detecting whether a sentence *comes from somewhere* (not merely whether it's AI-generated) and (2) a new ethics, since technology changes ethics; he expects norms within 5–10 years. He distinguishes training on public text to build an intelligence layer vs. outputting wholesale copyrighted material without attribution. - **Evan's counter-position (contradiction he admits):** when others thread his articles with a shout-out, "I listen to your logic, you're right... but when it happens to you... I don't like this, I spit on you." He acknowledges even an AI-forward org like Every hasn't figured it out. - Evan also loved receiving Substack refutations pre-AI; he wonders whether at "GPT-6" fully automated effort-free transformation becomes not okay. - **Dan's response:** models replicate pre-seen patterns and are **bad at finding new formats that work when things change**; he doubts current architectures learn this alone, so he's "not particularly worried." We've lived in a sea of garbage for a long time (Twitter, Facebook, scientific literature); LLMs are the first tool to effectively filter it, getting writers to things worth engaging with faster. - Evan wonders if society builds "social antibodies" to AI content as it partly has to social media; Dan agrees — Gen Z uses social media differently; humans and technology "co-evolve." ### Evan's final point: AI in distribution - Most online content is already **algorithmically selected**; writers serve the algorithm as much as the audience — a spiral that works for tweets won't work for LinkedIn/Facebook. Dan agrees: "it's the shit sandwich you have to eat if you want to write online." --- ## 6. Course Promotion - Evan's course **"How to Write with AI"**: lecture format covering taste/topic/craft/audience plus tools (Claude, ChatGPT, Lex, Spiral); student writing groups with trained Every editors; final essays shared with Every's audience (~78,000 subscribers at recording). Starts September 17, 2024. - Dan's framing: the goal is sharing the hard lessons learned over years so students avoid the same suffering. # Observation Record — Speaker Attribution & Provenance ## Video Identification - **Title:** Supercharge Your Writing With AI - Ep. 33 with Evan Armstrong - **Video ID:** 01a0f15b-0854-7ae9-8459-db9039f65c67 - **No curated metadata was supplied**; all identifications below derive from the transcript only. ## Speakers & Roles ### Dan Shipper — **Host / Creator** - Identified in-transcript as host; runs "AI and I" podcast. - Lead at **Every** (media company); writes weekly; Evan's colleague/manager. - Introduces guest, structures the episode, delivers outro. ### Evan Armstrong — **Guest** - **Lead writer for Every**, publishes twice weekly (Tuesdays/Thursdays); ~3 years working with Dan, 2 full-time. - Background noted by Dan: former "professional marketer SaaS investor" turned writer. - Teaches a course, **"How to Write with AI," starting September 17, 2024**. ### Referenced Third Parties (non-speaking) - **Morgan** — Evan's wife, Humanities PhD, taste advisor. - **Nathan Basches ("Nathan bashes" in transcript)** — Every co-founder, runs Lex. - **Kate** — Every editor-in-chief (mentioned re: passive voice editing). - **Brandon** — entrepreneur-in-residence at Every; co-built Spiral. - **Lenny** — friend, writes "Lenny's Newsletter" (jobs-to-be-done framework). - Voice-over outro speaker (unidentified) praises the show and host. ## Episode Structure (per host) Four segments, matching Evan's course structure: 1. **Taste** 2. **Topic** 3. **Craft** 4. **Audience** ## Referenced Sources & Tools - **AI tools:** Claude (incl. Claude Projects, Sonnet 3.5), ChatGPT (incl. Advanced Voice Mode, custom prompts), Whisper (transcription), Lex (AI writing editor), Consensus (LLM + Google Scholar search), Spiral (Every-built content transformation app). - **Books/authors cited in taste exercises:** Annie Dillard, Robert Sapolsky, Robert Pirsig, Ursula K. Le Guin, Mary Oliver, William James, Bill Simmons, H.D.F. Kitto, Ian McGilchrist. - **Films referenced:** The Tree of Life, My Dinner with Andre, The Seventh Seal, 2001: A Space Odyssey, Wings of Desire, The Truman Show, The Secret Life of Walter Mitty, Dead Poets Society, A Beautiful Mind, Into the Wild. - **Dan's articles referenced:** "What I Do When I Can't Sleep" (June 23, 2023), "Admitting What Is Obvious"; in-progress piece "Seeing Like a Language Model." - **Book cited:** *The Cave and the Light: Plato versus Aristotle*. - **News source referenced:** The Information (OpenAI "Strawberry" reporting); LessWrong forum. ## Third-Party Claims - Consensus "just raised like 10 million bucks" — per Evan, unsourced in transcript. - Every audience: "78,000" subscribers (per host/guest exchange). - Spiral: "going to pass 5,000 users in the next couple weeks" — per Dan. ## Promotional Segments ⚠️ - **Closing outro:** explicit like/subscribe promo for "AI and I," praising Dan Shipper as "captain of the spaceship." - **Course promotion:** Evan's "How to Write with AI" course (starts Sept 17, 2024) promoted twice; link promised in show notes. - **Follow prompts:** Evan on X/Twitter at "its your boy Evan"; subscribe to Every. - **Spiral** discussed extensively — a product built by Every; discussion includes usage stats and availability framing (promotional in character, presented as editorial content). - Opening lines of transcript are a **cold-open excerpt** repeated later in the episode (top-of-file fragment precedes the actual welcome). ## Provenance / Ethics Discussion (recorded, not evaluated) - Discussion of summarizing third-party articles into tweets with attribution; both speakers state the ethics are unresolved. - Evan reports readers ("Armstrong Warriors") flagging unattributed reuse of his posts. - Dan articulates a distinction between training on public text vs. outputting copyrighted material wholesale. ## Comment Availability - Not stated in transcript or metadata; **unknown**. we've split up the segments or the the things we're going to talk about into four sort of distinct areas one is like taste so like how do you know what good is two is topic like how do you pick what you're going to write about three is craft so that's actually how do you do the writing it's everything from outlining to writing to editing and then four is audience how do you reach people so why don't we start with taste my line about this is that taste is not whatever people in Brooklyn are doing no I think taste is the ability to articulate why something is good so what I did was I just like copied this into Claude And I was like Hey here are a list of writers I like can you tell me the Vibes of these writers in detail for me right now like because I've seen this before it's not like a mind blow moment but when I first did it it was like looking in the mirror for the first time and I was like holy \[ \_\_ \] this is what I look like and I like it Evan welcome to the show thanks for having me long time coming yeah I'm excited to have you for people who don't know you are the lead writer for every um so you write twice a week for every you've been you we've been working together for about three years two years full-time um and in all of the writers that we've ever worked with you are you're the one that survived the gauntlet and actually became a real writer um and I'm just psyched to have you on both because I just I love hanging out with you and getting to work with you every day and I think you're just you have that sort of like rare combination of you're really smart you know a ton about business you're funny as hell and you actually want to be a writer um and it's just been like such a pleasure to get to watch you go from being a I guess professional marketer SAS investor you had a bunch of different things that you were doing um and now being a pro writer so uh welcome well thank you I'm really excited to do this mostly because I'm going to chop up what you just said and just like for my performance review at the end of year just play you back to you that was the only reason this is just to make sure that I hit my bonus for the year that's the only reason I'm here today I'm costing myself money yeah exactly this is a very expensive podcast um great so I think what what we wanted to do is like uh do a little bit of a non-traditional episode that's a that's a little bit less like me just interviewing you and more like us together talking about writing because I we're both huge writing nerds we love to write we're both professional writers um and talking about writing us particularly in the context of AI like how are we using in each part of the writing process how are we each using it um and to what effect where is it good where is it not good all that kind of stuff um and you're actually teaching a course on this um called how to write with AI so it's a good time for us to kind of explore together and my hope is like we both just come out of this I mean nerding out about writing which is like probably both of our favorite things to do but also like learning stuff from each other that we can apply to our process yeah I think when people picture every I think they Vision it more editorially cohesive than it is where like we're all you like it's I would say it's more contentious than people would think like we're debating the stuff a lot we're arguing over sentence structure and I'm going to guess that today we're going to find out we use AI very very differently in our writing process that would let's hope I think that' make a more interesting episode it would it would make it more interesting I I think we're going to find where we use it pretty differently okay cool well basically like we've split up the segments or the the things we're going to talk about into four sort of distinct areas um one is like taste so like how do you know what good is um two is topic like how do you pick what you're going to write about what do you write about all that kind of stuff three is craft so that's actually how do you do the writing it's everything from outlining to writing to editing and then four is audience um how do you reach people um and we did it that way because that's that's how your course is structured um and that sort of allows us to get the the whole breadth of all the things you might use AI for in in writing as a as a creative intellectual Pursuit um so why don't we start with taste can you like teed up like talk about why taste why is it important um and yeah we'll start from there yeah I think taste taste is a buzzy word and it's also a word that means nothing and everything and that like taste is uh not uh you know my line about this is that taste is not whatever people in Brooklyn are doing um it I'm in Brooklyn I don't mean that is a an attack against Dan but more against the Brooklyn industrial complex um they made our coffee too expensive and um it's all their anyways no I think taste is the ability to articulate something is good like you know you may say that you loved Dune 2 or you loved you know whatever latest article either Dan or I wrote but being able to accurately describe why you liked a thing besides awesome loved it you know like that's actually really hard it's a discernable skill and I couldn't really do it for myself until I started using AI more and so I think it's an exercise that everyone who wants to write something good has to be able to say what good is and and what does that mean to you like what is good to you how do you articulate it for yourself This is complicated so I think when you when we're talking about taste you have to be taste in what context so like in the capitalist context of taste you're like is my taste overlining with the problems that my product is solving um so Lenny who's a friend of ours he writes Lenny's newsletter does a great job he has like these four jobs to be done of and you got to help me here if I'm missing some of them but it's like you know make me smarter make me money entertain me it describes these jobs and then there will be taste that goes next to those jobs I have found that I am very bad as a writer of like I got to make a product I'm just not good at it I get bored the writing is crappy so instead what I have found that like what good taste is is basically things that I enjoy so I only write things that I would have a good time reading and that usually ends up anytime I deviate from that the product doesn't you know the audience doesn't like it I don't like it no one enjoys it so good taste is things that I would I like smile while reading and what do you smile about I think the the peak of writing is the more boring the topic and the more entertaining it is the more skill that's presented um so you and I Dan we you know we write about on one level very boring things you know you mostly do like tokens I'm talking about the next token right and I spend a lot of time like on accounting like here's how Finance works like no one cares no one likes that no one enjoys that it's not fun at all but uh being able to crack jokes to be able to make it accessible um and have a an energy to it it's really hard it's really really hard to be accurate and enjoyable and so for me that's what I shoot for in my own taste I'm like is it something boring that I know I should know but I don't and I have a good time while reading about it very hard bar but that's what I typically go for entertaining reads about boring topics is how I think about it I'm curious Dan for you like how do you articulate your taste where do you find uh your taste being fulfilled that's a really good question and and I will say also for me like this was one of my my big um unlock moments for AI is I wrote um this this piece called what I do when I can't sleep which is about using AI to discover my taste um and it sort of came at this um particular time in 's history where we were kind of going through a little bit of like a identity crisis like what are we going to be what are we going to do and I think I had to go back and think to myself like what what do what do I want to do like who am I and um both chat and Cloud were like incredibly good for identifying that and I think the the things that came out of it for me um you know going through the exercises using those things to to think about who I am and what I like I really like um writing that is like really like it's intellectually stimulating it's analytical it's philosophical um but I really also like it when it's like emotionally resonant it's like psychological or it's um it it pulls on your emotions in a in a certain way I like I also like writing that's very um very like Poetic and lyrical um so like an Annie Dillard type type person with the running joke at every is that everything I relate everything back to Annie Dillard I'm laughing because like literally I think for most your pieces I have to edit I have to like hold you back like you do not need to mention an Dillard nothing to do with you need to cut the section I'm a broken record on an Dillard but um the Annie Dillard will continue until morale improves um so I like that I really like um writing that is like really accessible even if it's dealing with a hard topic so like Robert spolski is like a really good example of someone who I think does that incredibly well um I also really really love writing that is just like practical it's like you can actually like apply this or like you know how relates to you um even if it's like somewhat esoteric um and I think generally the things that like I'm drawn to are um very kind of like interdisciplinary looks at The Human Experience um the relationship between humans and Technology um the relationships between technology and creativity and psychology like um and then sort of like philosophy like all bundled into that and like maybe and and business all bundled into that are like the the kinds of stuff that like really really get me going and it's kind of interesting cuz it's um it's one of those things that I if I look back on my life I can totally see that as a pattern and stuff I've Loved for a long time but I was never able to like say it until um Claude and Chachi told me like hey this is what's this is what's going on for you and like you said like saying it articulating it it's so powerful because um once it's articulated it becomes um something that you can aim at um you can aim yourself at you can aim other people at um and you can you can start to refine uh how you write and what you're doing based on that and I think that's like sort of just this key underlying component to getting better I think it's interesting because for both of our answers there like if I had the stopwatch I bet we both went on for like 2 minutes of like this is what I like and it's kind of just an Amorphis BL Bob of things and uh emotions and so what I think about like taste particularly when I saw you cuz I was thinking about when you wrote that piece that was June 23rd of 2023 um after you wrote that it wasn't that you could suddenly be like I like Annie Dillard and like because she's lyrical and so my writing is going to be more lyrical like you were before that your writing was lyrical it wasn't like there was some huge shift in your writing necessarily it improved of course but the thing that noticed is after you publish that piece was like uh you hit like a new emotional plane where you were like ah like I am comfortable writing the way I want to write I do you do you think that's a fair characterization um of like that change after you publish that piece I love that I think that's so true um yeah I think part of it it it sort of relates to that piece I wrote um I don't know maybe three or four months ago called admitting what is obvious which is like admitting that I wanted to write as like a core thing um and I think you're I think you're totally right like um articulating it gives you something to aim at and also allows you to incorporate it as part of your identity which requires like admitting who you are which is like a it's actually like very scary to do um because it feels like it's um cutting off different other avenues that you can take you know like I like things that are not any of the things I mentioned you know I I've I like you know dumb funny movies or whatever but that's not in my taste um and so um that uh that's scary to do and it's also scary to feel like um like maybe you'll be ridiculed like people won't like you if you say that you like this thing that like no one else really like I don't know anyone that likes Andy Dillard except for me they're they're out there but like I don't associate with them the dehe heads unite and once you say it and you realize like how basically no one cares and the people who do care are like oh that's kind of cool like it's fun watch someone just like something like something in public then you're like much more comfortable just like owning it and being like this is this is what I want to do and that I think you're totally right is like such an important part of doing any kind of good creative work um I'm curious maybe we should talk about like what you actually did in the article um for those who hav't for the every heads uh beyond our like our deep cut fans like what was the AI exercise that you did to like develop your taste I'm I'm Cur like can we do it live this is the AI Andi show we'll do it live so basically the way this worked and I did this like a long time ago so we'll see how we'll see how how well it does um you know today I'm sure it'll be good actually but it'll be it'll be interesting to see how how it updates basically like I just had this like note in my notion doc um and um I was just like thinking for a little while like who do I actually just like as a as a writer so I started adding names and this was like not just a onetime thing it's like a it was a continual process because there's all these different contexts in where you're like oh I really like that person even though you forgot so for a while I was kind of doing just updating this and I have like Robert spolski Robert perig um spolski obviously does the like uh really accessible like deep science stuff pig is like really accessible philosophy blended with fiction Ursula cawin is like really interesting like psychological fiction um we've got Mary Oliver like that that resonant like pros um Bill Simmons who's like a very bloggy funny like clear simple kind of writer um so I just had all these people right and I have words for these people that I that I um I can say all the words right now but like I I could never say that before um before this exercise so what I did was I just like copied this into Claude And I was like Hey here are a list of writers I like can you tell me the Vibes of these writers in detail and then I just pasted my list and I went for it and I kind of like the like asking for vibes from a language model VI like language models tend to do well with Vibes and it sort of gives me this like really big list of things like Roberts pulski scientific engaging um accessible see that's a word that I used um p philosophical introspective leguin imaginative thought-provoking feminist Mary Oliver nature Focus contemplative William James philosophical psych psychological pragmatic um and it sort of goes on and and one of the really interesting things here is like you can even start to now like pick out things that words that resonate with you like I don't know if you you see any words here that you're like ah like that is actually something I hope to be I mean uh I I have the highest standard for myself like I should be all of these all at once I don't know if you ever get that where I'm like I should just be the best of every best writer and do it all in my 1500w blog post um I kind of the most um I I'm curious what one thing we should do is you actually did not do this in Claude last time um you did this in chat GPT I did it in both oh you did in both I it was both Claude And chbt so listeners you should know that Dan is a liar because in his post that I was reading this morning he says chat GPT um no it says it says Claude and chat GPT you didn't read the post uh carefully no oh yeah oops oh no okay here's the thing okay no this is different don't come at me unless you've got receipts you're changing the truth you use Claude to do the notes part of the exercise you didn't use Claude for the writer part of the exercise or maybe you did both and you just didn't include those I did both but I just used the one from CH one from CLA the key to internet success is nitpicking needless details and starting a beef over it so this is what I'm trying to do here today this is where it starts this is where the every beef of 2024 starts okay so let's let's keep going with this so basically um so we've got this big list and you can start to pick out things that you think are interesting but like it's also to me it's like overwhelming it's like wow like um how am I going to try to be all those things it's impossible so one of the things you can do which is really cool um well first before I even get to the things you can do I would press retry a few times just to like see how it does it in different in different ways like it will you'll kind of explore the like latent space of possibilities here and like it may come up with different ways of describing things that might be better or worse like I don't think that one was like particularly better um I think this is like slightly better um because it's it's not necessarily citing their like most uh important work which I think is kind of irrelevant to this exercise so I'm going to go with this one and I'll say something like um can you synthesize The Vibes down into uh something more compact I want a summary that can help me express my taste do it in five sentences um and we'll see what it does what's really interesting about this is Chachi BT when it does summaries like this um like the sort of like tell me the Vibes and it gives you a big long list at the end it usually has a summary graph that just like tells you what it just said and that graph is usually like really good CLA doesn't do that so it might be interesting to try this in chat gbt after this but okay it says your literary taste gravitates towards thinkers who blend scientific rigor with philosophical depth often exploring the intricity of human nature and Consciousness you appreciate writers who can make complex ideas accessible whether delving into Neuroscience psychology or the cosmos there's a strong current of introspection and mindfulness and your preferences balanced by dash of humor and pop culture savvy so bid aside from the fact that it's like really complimenting me and gassing me up like this is actually like really good and for me right now like because I've seen this before it's not like a mind blow moment but um but when I first did it it was like looking in the mirror for the first time and I was like holy \[ \_\_ \] this is what I look like um and I like it you orgas successfully yeah and so um so so that's the that's like the basic gist of the exercise is like find people you like throw it into jbt and have it synthesize something when you're so you have this list and you've had you've sat on it for a little over a year now like when you're editing a piece or writing a piece do you ever find yourself like mentally going through this checklist of attributes or is it like I'm curious how much this actually comes into play during your day-to-day process it's not a checklist of attributes but um when I when someone gives me a piece and they're like what do you think of this or should we publish this in every like I am kind of like explicitly being like if if I don't like it I get a vibe that I don't like it and then I can be like well it's just not uh it it doesn't have uh it's not accessible enough or it um it doesn't have like that sense of like a little bit of like Curious optimism or it doesn't have the the depth or the thoughtfulness or whatever um so in that sense I I totally do and then another way that this works is like when I'm editing myself I do have some of those words in mind and I'm often either thinking about those words or I'm going back and being like I'm I feel dry like I don't have the vibe anymore and like here's I know that Robert spolsky's got the vibe I'm going for I'm just gonna like reread him um yeah so I'm curious for you I know that I know that you've done these exercises too like how are you how are you doing taste like how are you thinking about it um and how are you identifying it with AI so I think I I did because you read this article or you wrot you wrote this article last year and I was like o I should do that so like all credit to you for this exercise for myself like I didn't come up with this idea I just copied you um I the place that I took it differently is I think I'm more multi media than you are when it comes to taste making like I love Cinema like I I love exploring different forms of artwork and um I find that informs what I write just as much as anything else um and so a lot of times I will find the taste notes of what I'm looking for by talking uh well talking first with Morgan my wife who's a Humanities PhD and so she has a much better articulation of all these things than either of us um but if she's busy uh by talking to chat GPT about it and getting a better sense of like if uh if I liked a couple of movies like why did I like these movies or if I liked a couple of posts what artwork is related to these posts because I find that it's able to draw things that I haven't heard of or I haven't interested in and it makes me more well-rounded I worry when writers are like I only read because I think you can get in a little bit of of a rut a little I personally I get into a little bit of a rut um and so I think it's important to be multimedia with your taste making and so chap G helps me do that I'd be curious like how you how you do that so read out to me like five of the writers that you love right now and make sure they're ones I can spell okay cool I'll give you I'll give you a little bit of I'll give you a little bit of a list um and actually before we do that can you just introduce like the exercise that you're going to do like tell us what you're going to show me um basically my goal is those taste elements that you pulled out in your exercise where it was you know philosophical or um lyrical um I I think it's really interesting when you say I like a lyrical Pros how does that apply in other mediums because not necess like lyrical is obvious in say a poem or in a song but does it is there lyrical paintings is that a thing um and so my big thesis when it comes to taste is that it's a blob of emotional permission to like what you want to like and it's not constricted to certain types of medium so it's not just writing being a great writer and having great taste as a writer does not mean you only read the best books it means you partake in the best movies the best music whatever it may be um okay so what I want to do is take the list of writers that you have and then try to convince you to watch a movie because I I've I've I've known you for years I've given you like 20 movie recommendations I think you've watched zero so today we're gonna fix that we're gonna fix it Dan if chat gbt tells you you'll do it if I tell you you ignore it so we're gonna have chat gbt do it for me I love that I also would like to do that with you too just to like see what we get because I I really want to explore your taste too so but like let's start let's start with um let's start with what you want to do so um yes let's pull chat gbt and we can uh we can see what it says okay so uh Dan who should I put in just give me like five okay so I mean we've already talked about any dealer do I have to have her on any list um I would say Robert perig um a new one like a more recent one is this guy hdf kiddo he's like a he's like a classicist he writes about Greece he's amazing uh K T EO tto tto T I like kiddo K DDO but that's his nickname kiddo um also um Ian mcgilchrist e sorry his name is uh i a i n he's got an i in the middle oh man and then MC g i l c h r i s t so uh what I'm going to do is I took those lists of say here's a list of my friends favorite authors please pull out the Vibes of each of these authors and then recommend five movies that have similar Vibes be specific and why they are similar um I do like uh so the response from chat gbt is kind of funny because they put Vibes and quotation it's like it's not a real word which they may be right about um and this kind oh so and it listed out the five Vibes for each of them it kind of gave three for each of the five authors and they gave Five movie recommendations I'm curious in the five movie recommendations for the Tree of Life My Dinner with Andre the seventh seal uh 2001 Space Odyssey and wings of Desire have you seen or heard of any of these so I've seen the tree of life and I hated it I did not understand it at all um good we're doing good but like I know why it's recommending it and I have been recommended that before by other people and it could be a could be like one of those things where I just it just wasn't like contextualized for me appropriately like the description of it sounds amazing I want to watch it but like the actual like reality of it I was like this sucks um um My Dinner with Andre um another one that I've that I've heard of that I've never watched it but I I know that it uh I probably would like it so that's a good that's a good recommendation the seventh seal ingar Bergman I I've definitely seen inar Bergman I think I maybe watched that one but it was a long time ago basically I went through like uh um I went through a phase where where I really liked Woody on movies which I really obviously don't like want to say uh their art is different than the artist you don't have like if you're going to reject film based off of like the moral actions you're just going to have to reject the genre okay well I will say like when I was in college I like really liked an Hall in Manhattan and um ingar bugman's like one of his big influences and so I started watching ingar B Brigman films um I can't say that I like immediately like loved him and like watch him all the time but like I respect him as an artist and and I like his work um 2001 of Space Odyssey I must have seen that I don't like specifically remember but uh it's if You' seen 2001 of Space Odyssey you'd remember you you would is that good I mean I remember like the you know Dave thing or whatever um but I don't I don't can't tell you like where I was in my life when I watched it okay um and then I've never seen wings of Desire um let me see so this it says wing wings of Desire this film Echoes a the mystical and existential quality both Dillard and Miguel Chris's work it tells a story of angels observing human life catcher capturing a contemplative spiritual mood that aligns with their philosophical in inquiries that's interesting um so I would say like generally it's it's on point it's sort of steering toward like um more like introspective philosophical movies which I'm like I'm down for um but it's probably missing some things about movies that I love like there are movies I love that are not part of this um that I don't know I don't know how what where you typically typically go go from here but um could be yeah I think this is actually a really good illustration of the problem with this exercise is you are a professional writer like you your living comes from writing words and so of course you're going to have a really fine-tuned indepth taste of words while in comparison like movies like you you just like I know you just don't watch that many it's not where you've really dived in deep and so giving you the Deep cuts um I don't know if two 2001 is not a deep cut per se but it is very different than most modern films you're gonna you're going to have this problem so if you go my experience with llms is they'll either go way too deep or they'll go way to surface level so you know you might say I like paintings who should I like like have you ever heard of Van go you know like um so I think with this one with these five movies I'm going to prompt it with my friend has a passing knowledge in cinema can you recommend anything after 1985 that is slightly more accessible now I'm curious uh we have the five shows that it has is The Truman Show The Secret Life of Walter midi Dead Poet Society A Beautiful Mind and into the wild have you seen any of these definitely seen The Truman Show great great movie I've not seen The Secret Life of Walter midi that sounds interesting um I've definitely seen Dead Poet Society I've seen a beautiful it was actually filmed in my hometown um and I've read into the wild but I don't think I saw the movie okay um funny because I was just in the town where The Truman Show was shot like three weeks ago that's where we did our baby moon so small world um you would love the secret life of Walter midi it's so good um it's very accessible it's about the collapse of Time Magazine and then Ben Stiller's character is the back room photo specialist goes on this journey of self-discovery to Iceland and goes outside um so I really think you would love this movie like I really think you would dig the secret life cool I want to watch it I want to watch it and so I think with the exercise like the next step is the hard step the one that requires the emo the most emotional activation energy which is where now you go and you have to go consume this stuff you know you're like okay now I actually have to go do it um which I think Cinema is a hard version of this but art is a really easy one so sometimes what I'll do is like I'm reading something like I really like this and I'll go say give me paintings like this and it'll help me out as well yeah well I think like um so one of the reasons I I really love this as an extension of of the original exercise is like um the original exercise that I did is like a sort of looking backwards type thing as if I found a lot of the stuff and I just need to name it but there's a whole part of t which is like exploring new things you haven't heard of that are like like the things that you like um because often um there are like things I mean always things exist in context and they exist as part of like a chain of other works and so if you like one thing there's usually like a whole related chain sometimes it's like um it's in different mediums and sometimes it's just it's still a book or it's still a movie but it's like the five other directors that influence this one director and So like um part of I think part of like getting is traveling those like roads of who influences who and who thinks about what um and I think Chad gbt and CLA are like also excellent for that I think that this is that's what this exercise is like starting to do is like um you can explore that those chains of influences yeah and you can also just I like it because you can bounce so easily from surface to surface um in my own writing more and more I've been feeling like I've been doing like philosophy where I'm skipping along um from Fuko to Playdoh whatever and chat gbt is excellent at helping me get the surface level stuff and get enough understanding um or at least know where to dig deeper um I think the idea that you brought up of like there's more change to discover I I'm just so passionate about like content and about like consuming good things the world is just full of good stuff and I just want people to know how to get into it and know how and so that's why I love these tools and discovering your taste this way because you can just so much there's so much good movies there's so many good books and like your entire life should just be filled with greatness like every day you should get to consume something that blows your mind there's enough out there that you'll never run out and that's just such a gift and it's overwhelming to find but this makes it a lot easier totally I love that those the you're talk about Good Vibes uh talk about uh I don't I don't know exactly how that fits into my my my vibes list but I'm picking up energy and and and I love that energy um so I feel like we've kind of um I feel like that puts a really nice bow on the on the sort of taste aspect of what we're talking about here be great to to um go into topic I would love to hear um yeah what you think of topic and then yeah how are how are you using AI to to help you like pick topics and find topics to write about yeah I actually think this is um the least maybe one of the least aiie a i AI is AI adjacent what's the right I don't know you're the AI and I guy aifi part of my process so um I publish twice a week every Tuesday and Thursday and then I write a decent chunk of our Sunday dig or it's now called context window and so I don't have the luxury of a ton of time to think through all of my ideas of like hu yeah so I had to find a way to really go into the zone and pick the right thing and I found this is I apologize this is so Austin Tech bro of me um but i' I go every morning when I after I do my lift I go and I sit in the sauna for like 15 or 20 minutes and if it's a Monday Wednesday or Friday I think about what ideas are good and if it's a um and what I'm going to write about and Tuesday or Thursday like yeah so that I just sit in the sauna like isn't that a dumb answer like I just sit in the sauna until something appears in my brain I'm like hm that's a good idea um and that's it that's literally it isn't that dumb that's such I it's a dumb answer but it's it's mostly how I do it many incredible thinkers uh have have gone before you uh having ideas in the sauna um so I I don't think it's dumb at all if it works for you like I think that's the thing that people people miss about creative stuff is like you got to just find what works and different things work for different people and if like sitting in the sauna until like your your brain melts out of your ears is like the way for you to like have good ideas like power to you I think it's you know like it's like the Matrix like I just spend all day like jacked into the internet you know um through Twitter and emails and talking with people I just spend all day jacked into technology and I'm just every day I'll have dozens of ideas about what to write about for me as a writer ideas are never the hard part it's picking the idea and like knowing which idea will be right and I find that if I try to sit down and like write them all out I just get overwhelmed but if I listen to my subconsciousness and just let it Bubble Up naturally where I'm not thinking about anything usually the first idea that comes into my head is the best one um and so I just sit and wait um and it doesn't take long because I'm a wuss and I can only last like 15 minutes or whatever but I sit there take a cold shower come home right down the essay that makes sense as you as you might guess like I have a little bit more of an AI process for this yeah tell me about it so um what I do a lot is um I I feel like I think really well if I'm walking and talking um and and so what I'll often do is um I'll either uh just get up take a walk and record a voice memo um and then I'll go transcribe the voice memo with whisper and then I'll it into Claud or chbt and like have it basically pull out okay what are the interesting things or what I'll do is I will um uh I will actually like have a conversation with chat gbt advanced voice mode and I'll be like okay I'm just going to brain dump and then I want you to um I want you to like reflect back to me what you hear and then we'll go down a rabbit hole on a particular thing that I'm interested in and I think it's like really good at helping you find like okay I have this like morass of things like swirling around in my head like what's an interesting thing to like start with or where do where where do I what's a topic that I want to like kind of dive down deeper into and whenever I find one of those I like just put it in my I have a things I use things as my to-do list and I just like have a little thing in my to-do list with a little headline like usually if I if I have a piece I want to write like I I want to write a piece right now called generalists own the future I just like know that's the headline and I just put it in things and I basically like that's like the handle for like all the ideas um and when I sit down to write I put it at the top and just like kind of go for it um I also find that there are other um and and I I actually can show you a demo for this but like there are other pieces like I'm writing this piece right now where um it's not on the on my weekly Cadence because I I publish once a week it's like a much longer piece that requires a lot of research and like um basically what I have is this like I'll show you um so basically what I have so I'm I'm writing this like longer piece and um it's taken me a month or two to write I'll probably hopefully I'll finish it this week um or at least a draft and it's about like um what what is it even about I I can't even say what it's about that's how long and difficult and complicated it is but it's it's oh I I'm grim missing because I have to edit this so I'm like oh no um it's it's basically about like um the sort of underlying way architecture of language models and how that relates to some ancient debates in philosophy about appearance versus reality um which which I can sort of get into but like more or less it's like uh some of the philosophical implications of language models um and I basically have this note in in um in my notes that has been I've just been adding to for like um months at this point right oh my gosh and um and it's highlights its ideas like you know I WR I read this book The Cave and the light Plato versus Aristotle and I'm like taking a highlight like figures as archetypes not figures for profit he's supposed to have said which is something about Pythagoras and you know I have all these quotes in here and one of the things that's like really interesting about this kind of a uh kind of a project is I have an intuition about what I'm trying to say um and I'm I'm running into things all around the world that like reflect that intuition but I'm having a hard time saying it so it's it's a little bit like the um language model uh sorry it's a little bit like the taste thing from earlier where it's like I have taste already I just don't know how to say it and being able to say it is like a really important thing to actually being able to do it and I find that language models are really good for like synthesizing down like a morass of things like this into something like much more compact so if I go into Claud I can probably find like historical chats where I'm like asking it to pull out basically what I do is what I've been doing or what I was doing previously is I was like every day going into Claud and having it write a thesis statement based on all the notes that I was collecting and then I was trying to like rewrite it and like make it better and I was just like every day I was writing a new thesis statement until I like refined something that's like this is the idea this is what I'm going to go with uh and I found it was really really helpful for that um let me see if I how do I search for my oh here we go so I so I have this project in Cloud called seeing like a language model U and I basically take that note file and I put it in as the as the knowledge for that uh for the project so it has access to all this to this huge long note I've been collecting and I'll start a chat and I'll be like given all of my attempts and all of my notes write out what you think my thesis for this piece is um and so it'll say like based on your notes it appears your thesis for seeing like a language model is um language models offer us a new lens through which to view intelligence knowledge and our relationship with the world this perspective challenges the 25 2500 year old church of reason that has dominated Western thoughts since PL and Socrates by shifting our Focus from Essences to sequences from definitions to usage and from abstract rationality to contextual understanding this Paradigm Shift not only resolves long-standing debates about ai's capabilities but also promises to transform fields from science to creativity so um I think that that's actually pretty good and it's like something that I couldn't quite say um and it's like sort of distilling everything down into something that like kind of gets me there but it's not not quite there um because there's all this stuff where it's like what does it mean to shift our Focus from Essences to sequences from definitions to usage like that's just philosophical like mumo jumbo basically um and so I'll say something like make it better um and it will do it again um I think that's a really good like claw trick is just always ask it to make it better and it just will be better sometimes you can also ask it like is this any good like what do you think of this please critique this and then based on the critique once it once it gives the critique then say make it better from the critique um you know so it gives another one I'm just basically saying make it better make it better make it better um and um and I'm saying make it better we don't want to Define intelligence we want to dissolve the question and I think this is me of like saying I want you to make it better in this particular way um and and sort of seeing what it does um and I'm honestly just going um going down the list like that um now I'm saying okay please reflect on this thesis and all my notes that led up to it how do you think it could be improved remember I want it to be a concise accurate interesting thesis statement including a few bullet points or paragraphs of elaboration to impack it just reflect don't rewrite it so I want to I want to split up the task into two and often like like in a in a language model context like understanding that there are multiple tasks involved in what you're trying to do and splitting it up like rewrite and reflect instead of just like doing it both together helps it so that's what just to clarify that's the the just reflect don't rewrite yet is like I don't want you to rewrite the thesis I just want you to tell me how I can improve it and then I'm going to assume in your next prompt do you tell it toite it with the reflection yeah exactly um and if you don't do that sometimes it will just like try to rewrite it um and and you want it to be very explicit about its thinking process and use its response to only think through what could be better and and then do the do the rewrite after um so it says you know the thesis effectively captures the paradig shift from essentialist thinking to a more fluid context dependent worldview blah blah so it's giving all the strengths and then it says areas for improvement it could be more concise it could be have more clarity it could have a personal angle it could tell talk more about practical implication and create more tens or there's a lot of it could do better and I'm like rewrite it and rewrites it um and um I think the the interesting thing from all of this is like I'm not then taking the thesis and like um uh and like just being like okay this is my thesis or whatever like it's not going to give me the thesis but what it is doing is it's reflecting back to me patterns that it sees in what I've been thinking about and Distilling it down in a way that like every time I ask it like I'll do this like literally every day until I have something I'm satisfied with like every time I ask it it's like a little bit of like a kaleidoscope where I'm like I get to look at all my notes from a different perspective because it's sort of like St stochastic and it it helps me be like okay there are these phrases that it's using that are resonating or phrases that aren't and then I'll go and write it myself until I have like this over a period of days or weeks I have like a really concise thing that I'm trying to say um and once I have that then I can start writing is the stochastic element because comes back a little bit different every time because of that and that's why that's important yeah exactly uh what's interesting to me about this process what one the like how you do it is interesting but also it's the exact opposite of how I think about my writing um I don't mean that that's neither good nor bad it's just very very different um typically for me there there's no note taking maybe like it's very rare for me to take a note um just it's all in my head I can just draw out my head when the time comes and so the The Taste element helps me reach a level of emotional Clarity and permission to do it and then there will be some initial spark uh so some news items some headline some discussion I have with somebody that leads it off and then once I have that spark I want to go deeper on some fundamental thing that that spark indicates so um have you ever used consensus before do you know what consensus is like the blockchain thing no Dan the blockchain thing this isn't scam and I um that was a big blockchain company wasn't it yes I'm being mean about the blockchain I I I shouldn't be mean about the blockchain there's some use cases I believe in but it's too easy to dunk on okay well I'm about to blow your mind let me show you this this is consensus I I think they just raised like 10 million bucks or so in the last month or two and think of it is an llm mixed with Google Scholar oh I have seen this this is really cool I love it yes yeah so it's helps you answer like fundamental questions and so uh a lot of my work think about you know Monopoly Dynamics power dynamics within Industries and so if I'm trying to get more scientific and more rigorous in my thinking I'll come to consensus to start pulling out um studies um and just to just kind of like fertilize the intellectual soil if that makes sense of as I'm thinking about the topic there might be some spark I don't know what was something um what what was a news item that caught my interest lately um like oh the the open source models for meta like that's a really big deal I want to think about it more correctly like so what I haven't done this before so this may fail spectacularly but what does we're doing it live folks we're doing it live um I find consensus is better with science questions but we're going to try this out but what does open source do on Monopoly Dynamics in software um so basically what it does there's these synthesize and these co-pilot questions where um the it pulls out the various pieces and then does the key insights if you ever read a bunch of papers like most of the writing is pointless and overly verbose and so I love consensus because it helps me get right down to the middle bit so co-pilot summary will tell you um this like okay who I like duh it says these studies suggest open source software changes Monopoly Dynamics by increasing competition altering Market structures and influencing software quality pricing Innovation which is like fine yeah um that's not like a necessarily great answer but it's useful because it says the impact of Open Source on Monopoly Dynamics it pulls out six papers and I can start going a little bit more in depth um it's funny but as a writer you eventually learn that if you read like three papers you've gotten to about 95% of the depth of most experts you can get there quicker than you think as long as you're reading the right papers and the issue online before llms was that you couldn't it was really hard to know what the right paper was outside of just citations which is a really flawed metric for reasons we can get into if you're interested but um so can I use consensus so there'll be some spark for me of like oh that's a good topic but like I need to better understand the fundamentals and it'll be combination of read consensus having questions about from the papers pulling it into chat GPT explain a term and then eventually I'm like okay I have the idea it's time for craft yeah I'm I'm curi like I I I really think that that that consensus thing it makes it makes total sense like and the the place it makes sense I think most for me is um as a writer in order to write anything interesting you have to understand the current context like um what is the consensus on this topic already um that's why it's such a well- named product um and like normally we know that but you know sometimes you want to go outside of your normal beat where like I can tell you the the current consensus on like something AI related like pretty easily but if I'm writing something that's like not about that um just getting up to speed really quick I think a tool like this is so so so so helpful because otherwise it's like hours and hours or weeks or months or whatever to like really get there and um uh like like it limits what you can even write and so this sort of expands the the the number of things that you can write confidently which I think is really cool yeah eventually what I want is a product where I can drop in all of the books that I have read all the books that I know are adjacent to what I have read all the papers into one place and build out like my own consensus Data Bank U we're not there yet but we're pretty close like we're remarkably if someone could build that for me I would make I I would introduce you to investors we could get you funding it's a really good idea I mean Claud projects is sort of like this um I will do that fairly often as I'll like Drop books or parts of books into CLA projects and and and you know and use that as like a jumping off point for like stilling down a an idea or a thesis I think one of the problems currently is if you drop an entire book into projects it basically works but um having that much context can like confuse the model a little bit because it doesn't know as much of what's important and I think what's really interesting is sort of doing the dynamic selection of like based on what I'm writing like what are the books and what are the like sections of books or papers or whatever that like would be useful here and what wouldn't be um like deselecting is just as important as selecting in in in some way so I I'm really curious to see how we evolve that over time because I do think yeah that's like the dream that's like the nerd dream is like throw all my books in here and like uh help me get ideas out of it when I when I want to understand something or I'm I'm looking for I'm looking to like distill something like how we do that do you think it's a question of context window or is it like oh you got to fine-tune your own model do you think it's like oh I have to use a technique like rag it's just rag basically you think you think it should be rag it shouldn't just be like a 10 billion word context window or whatever I think context window is great um and uh and in general like I would you prefer to use like just a bigger context window over rag because like Yeah the more context you have the better but um if you're talking multiple different books um and some of the books are like 400 Pages like there's just a lot of extraneous stuff and the more extraneous stuff you have in context the more likely you are to like get get off track basically so the extraneous stuff becomes distracting and you can if there if there was like an easier way to select the parts that should be in the uh in context versus not um and basically like give the attention mechanism in the model like just an easier time of uh knowing what to attend to like I think that would be that would be better um yeah well if anyone has that product you should email us uh we'd buy it um so okay yeah uh D DM's open for sure DM's open that's right um okay so I think that's that's sort of the that's the id8 phase be really curious um to go into craft with you so how are how are you using it to um you know write and edit your pieces um yeah let's I I think the big thing when you're talking about Ai and craft is your it's mostly a tools question right um how are you allowing the llm to interact with what you're creating uh and is it within a chat bot is it a co-pilot within an existing application in which you do your creating is it something entirely different and so that's the big question um for the chat Bots this is I think level one of when you're trying to get better the most common thing that I'll do uh as a writer I suck at conclusions I suck it's just like I I say what I want to say and that just like okay I said it like you know and then I need to find a way to land it I always struggle and so it's very simple but I'll just copy and paste it drop into into Claud um and say help me finish this give me 10 different uh subheads and the thesis that we could do and you know almost always all 10 of those are wrong but by being able to articulate what is wrong uh it's able to uh I'm able to say what is right um is that similar to how you you that you use the chat Bots or that is similar so like there is the the kind of like summarizing aspect or continue on when I'm stuck there's a lot of different places that I will I will use it so right now I'm writing this seeing like a language model draft and I'm writing it in Lex and Lex is a is a um it's sort of like Google Docs but with AI baked in um every uh incubated it it's now its own separate company run by every co-founder Nathan bashes um and I use it because it's like it's sort of just like um having things having access to AI in context is just like it removes a little bit of friction and that's really nice and you can see if you um if you if I show changes actually let me there's a way to do this uh AI view okay so what what you can see is um how much like what text is AI written right um which is really cool so the text in blue is is written by Ai and um I I'll say like I probably won't be using this actual text what I'm trying to do with this draft it's like 5,000 6,000 words 7,000 words already is I'm just trying to get it out um and there's a lot of times where um I'm summarizing an idea that I already understand but I just like getting it into words it's such a drag and I just don't want to do it so in this case like I need to talk about Plato's theory of forms um and I just basically have Lex like write the theory of forms and that it's Claw on the back end um and then where I would have gotten stuck and been like oh I need to go read Wikipedia and read like the Stanford encyclopedia philosophy and whatever I just get those like three or four sentences that are super generic and like it just explains exactly the idea and then I can move on and like later on in my process I'll probably go back and like make these sentences my own and like make it give it like the flavor that I want it to have but like this is enough for me to keep going and I think that's like a really really really valuable thing um oops another um shoot another cool thing that I like to do is um uh Lex has this feature where you can um ask it uh uh like ask it to complete things in comments so I'll like highlight something like this so um these are some notes that I have about a part of the article that I'm writing um it's it's basically about like why science has been stuck in certain Fields like psychology for a long time um and I want it to like expand that part of the uh of the argument and give me examples of what I'm talking about and rather than having to go into Claude and be like here's what I'm writing about here's all the context blah blah blah I can just make a comment and say at Lex um can you turn this into something interesting um and it will give me like um uh like a bunch of thoughts on like examples I can use or um ways I could write a particular par paragh or section and that's just like a really really easy easy way to like get the specifics in my head or get the examples I need or whatever so that I can like I can keep going so it's it's it's really really good for that um those are my le things I have more stuff to show you in Cloud but I'll I'll pause there in case I'm curious like what this brings up for you yeah it's interesting seeing because these are uh I also will use Lex and this is very different than how I use it so it's kind of fun to see um the tooling here I I found that over time I'm trying to shift more and more of my AI labor out of like the claw chatbot and the chat gbt chatbot because it's distracting and I don't know it's clunky and I want to work in in line so I can show you um do you do any of the custom prompting I don't okay like you want to show I built one yesterday yeah I want to see that okay so like I mentioned uh one of the things I really struggle with is a conclusion and I do it so often where I want to write a conclusion that I don't really know like it's just I don't want to keep doing it over and over again copying pasting match I just don't want to do the prompting anymore so what you can do um is you can go to prompt Builders and this is one I call what would Evans say um and you could see that I name it here I pick the model so I'm using three and a half Sonet here and uh I have a draft so or a system prompt so where I tell it hey I've got a draft I'm in the middle of below is going to be a big brain dump of things I've written in the past use that to create a list of things I might want to say next and below that I have I think one or two articles that I've written because I want when it gives me the conclusion I don't want it just to do the ideas I want it to do the tone and the voice and I I just want it to have the whole thing so that's the system prompt the next is um uh it says what's up here's some ideas um we'll bleep it just say the whole thing yeah we we'll bleep it um so it says what's up here's some ideas and it says what's up just say it no um and so I also automated the first message back um so think of this when you're doing the chat GPT or CLA experience this is the first message that the AI will give you and these are the instructions and this is the system prompt is the thing to make the instru the output good um so what I'll do is this is my draft that I published I think last Thursday or Tuesday I can't remember when I last published it's been a week um and so I'll just go to ask Claude and then I say what would Evan say um and it just gives me 10 ideas on how to do the on how to do this finish welcome to the content Thunderdome that's like such an Evan thing to say oh yeah yeah it had a I was hoping you would do it again but yes uh last night when I was playing with this it says uh copyright is like a condom it works but it's more fun when you're when you don't have it around um which is something which is something I would say and then you would make me cut that's really great but I you can make these custom prompts for anything and then what's also useful is if you do the checks do you use the checks at all I do sometimes yeah so checks are basically um what like I really struggle with passive voice this is something that Kate our editor and chief who is wonderful is constantly getting me to try to be better at which is passive voice so all I do is say check for the passive voice for me um and just run the checks um and good news uh this is an already edited piece so we don't have it uh really in here there's not that's not too much passive voice it'd be interesting to do it if we did with a a new draft the the one that I'm working on today but you can go through and do these edits and the goal isn't necessarily to uh the goal isn't necessarily to get rid of your editor but it's more the better and cleaner the draft is that you turn over to your trusted thought partner your writing partner the better the feedback they can give you and so if they're wasting time with like um you can't say that cliche or like the the better the draft is the better the end quality will be and a lot of editing is wrote where like you're just one you know maybe GP 5 or whatever CLA neck model away from like being able to eviscerate like 20% of the editing department at the Atlantic like they could just go away like their job or their jobs could be something different here because the language models can do a good enough job um so I find all you know come up with the spark sauna right edit and Lex and then I turn it back over to my editorial team yeah I mean I think like um for us like obviously we have editors um which is great uh but some people don't have editor a lot of people don't have editors um peasants not many people don't have editors and also sometimes editors are asleep or on vacation or whatever and so having that available all the time helps and it also just helps like to give Kate a draft for example that's like just better um it helps her um you get better edits because of that because she's not thinking about things that are like something else can catch which is really cool another thing I use cloud for that's sort of in the in the crafty realm is finding ways of doing metaphors and analogies and similes nice I do this too and so like I have this particular uh analogy in um in the piece I'm writing that's about Socrates and Socrates like search for truth and I'm um I'm talking about him like uh sort of splitting the Sea of words into like words that Express the truth and words that Express opinion and I want to I want it to like um revise that metaphor for a uh a different philosophical Outlook called pragmatism and and I think the specifics don't really matter but I'm just like saying to Claude like I'm writing this piece I talk about the Socratic method using metaphor of you know dividing up the Sea of words how do I modify it um to show the pragmatic method by contrast and it like gives me something that I think is like not that great um and then I'm just like I'm pushing it a little bit I'm like hm what about something like in a pragmatic Viewpoint you just find currents that are going to take you where you want to go so so basically what's What's Happening Here is like it suggested something that I didn't like but that pushed my brain to be like okay but like here's a metaphor that I actually would like or is sort of like partially expressing what I want and I'm just like going um going back and forth with it on um on uh on sort of building that metaphor and it's not doing the best job um and so what I have it do is again this is in my cloud project so I'm like what are some quotes from my notes that might help me write this section on on pragmatism a little bit better and what's really interesting about this is it like it makes the the stuff that is relevant to pragmatism um which is the sort of school philosophy that I'm introducing in this part of the piece it makes it more um relevant to the model because it's more it's like just right there in the chat history and once I do that it gives me a bunch of quotes which is really useful just to like see like what am I thinking about in terms of pragmatism and then I pick like a few of the quotes that like really express the idea that I'm trying to express as this metaphor and I say like okay weave number eight so number eight is like uh each each of these numbers is like a number of a of a note that I've taken so we' notes number 8 four and six into this metaphor and then it rewrites the metaphor um in to something that um that incorporates some of those some of those ideas um and and sort of I I just keep going with that I ask it to reflect like we've talked about reflec on what you wrote How can you make it better um and then revise and like the thing it came up with is like actually really good it's like um uh okay in the socratic view we dive into the sea of language hoping to separate the murky Waters of opinion from the clear streams of truth but when you look closely even the clearest drop we find no indivisible essence of water only space molecules and relationships this is the pragmatist Revelation meaning isn't a substance we extract but a property that emerges through use just as water becomes refreshment when we're thirsty cleansing when we're dirty or danger when we're drowning words shift their meaning based on context and purpose um and like this is good I like I want to make this better but uh it's create it's like it's this it's this duel collaboration like the some of the stuff that it's coming up with like I I put in there like um you know I said like you know when you divide a drop of water you never find the pure substance like there it's it's weaving things that I put in there it's weaving in notes and it's weaving in its own like sense of what what good is and what's relevant to create this metaphor that I probably wouldn't have come up with on my own um and and I think it's going to be one of the central metaphors of the piece and it's like beautiful and amazing and I like I love it um and totally would not be possible in the way without without Claud it's really powerful for this how long did this exercise take you I was doing it in like like the 10 minutes before this show because like I was actually just doing it for myself like I actually just wanted needed this so say like 10 minutes to come up with a metaphor so like interesting I it's interesting seeing how much of our relationship with these models comes from our publishing deadlines because every no I'm serious like I I don't mean that in a derogatory or like a a moral judgment way but but more just so much of your usage is like I'd really like to do that I'm like I don't have time to do that um which is my own fault CU at the start of this year you and I sat down I was like I need to publish twice a week I need to get to that speed I don't I don't know man you you published you definitely publish more than me for sure but if you want to talk about who's busier I I I might give you a run for your money oh I I listen I'm not trying to compare it all oh the podcast I have to talk like no come on um I I do have a anyways we don't need to talk about the podcast um it's very funny that like the Marquee post of your of your year was like uh admitting what is obvious I want to be a writer and then the big thing you've done this year is do a podcast is kind of funny um I mean that's that is one of one of the big things I've done this year like let's let's be real here but yes the the podcast uh the podcast is one of the big things and um and the writing uh it's it is always a continual struggle for me to like figure out how to prioritize both and like wanting to prioritize the writing and and all that kind of stuff and I'm I'm constantly finding that balance no yeah no I think I think it's less of like who is more busy uh because who knows like I'm not going to compare that but it's more about the attitudes that we have or like what we want to pull out of the models like I'm not quite as interested in a thought partner um where I'm just like I I got the juice I just need you to clear the runway for me you know I just need you to let anytime I get blocked fix my emotions give me the next step and I'll just take it from there and while you is it's a much more collaborative process so it's really really different um but uh valuable I want to tr I want to try the maybe I need to take a note and then once I start taking notes I'll put them into uh clot projects yeah no I think that I think that is I think that that is very interesting um and I think generally like it reflects like how we work in general like I think like I just like a more collaborative like work process and I think you like a more like I'm going to just clear the runway I got the juice you know um yeah so I think that's really interesting and I think um yeah I think the not taking thing is it's just like a um it's a psychographic like it's a thing that some people do um and some people don't and uh I think some there are people who are like oh I should take more notes and I'm just like no no no if you want to take notes great but like sometimes that's just not how your brain works and that's totally fine you know um so um yeah so I think this is a really good good summation of like some of the ways that we use use Claude for the kind of Craft part of the writing process um let's let's talk about the last one so audience tell tell us about audience and how you use it for for audience see I actually think you are much better than me uh at using just an audience in general I think this is actually one of your big strengths as a writer U one of my big weaknesses it's why we're a good team um but the like I'll do the typical things so we have spiral have you talked about spiral on this podcast I talked about it a little bit um but we should introduce it for for anyone new okay so spiral is an app that Dan came up with the idea for and then our internal team of Engineers and designers in partnership with our entrepreneur and residence Brandon uh built together um you can think of it well I don't know how you describe it Dan so let me try to describe it and you tell me how close I get uh I kind of think of it like a Mario pipe um where if you've ever played Mario like sometimes he'll go into the pipe and then he comes out in like a different shape or he comes out in a different place and the uh spiral it makes is a pipe designer and so you can take one body of text and stick it in the pipe and it transforms it into something else so pragmatically it means like you write an essay it can make that essay into a good tweet um or you write a good tweet and it can turn that into a good YouTube description or whatever it may be what am I close did I yeah that's Bas that's more or less right I mean basically like the Insight is um as a writer you're constantly like I feel like I'm constantly like I do the core creative work and then I'm constantly translating that work from one format to another so I'm taking an essay and I'm like I need to make a headline from it or and that is a new format of the essay it's like a compression of that essay um or or I'm taking an essay and I need to tweet it or taking a podcast transcript and I need to tweet it or making LinkedIn post or whatever or I have a podcast and I want to make show notes like there's so many things where it's you're transforming it from one uh one form to another as a way to get distribution as a way to reach people where they are in the channel that they are for the amount of attention that they have in the format that they expect and um that is a really skilled task it like it requires a lot of knowledge and skill to like do it well um and it's also like really repetitive and kind of sucks like no one wants to do it mostly um and I realized that like Claude is actually good enough um if you do the right prompt for it to like automate a lot of that where it's doesn't do everything for you but it's like it gets you 80% of the way there yeah and um and so I was I made a prompt for myself for like a couple of these things like for um you know podcast transcripts to tweets or whatever and I was using it but it was like hard for me to type and I just felt like it would also just be hard for I felt like it could be really valuable for every but I felt like it would be hard to get people to use the prompt because it's like big and hard to create and so we have this thing called think week at every um where we don't do meetings and we just sort of like reflect and think about what we want to do next and also just spend a lot of time just like letting our creativity run and I just like built an app to do it called spiral um did I did it in a couple days and you can basically make a spiral you give it a bunch of examples of the tasks you wanted to do so like podcast transcript to tweet you give it a bunch of podcast transcripts and tweets you've done and then it just gives you a little text box where you can paste in a new transcript and it'll make tweets for you um really simple but it works really well yeah um and uh and yeah Brandon and and the team kind of like took that mvp app and just built it into like this beautiful thing that uh that we launched a couple a couple months ago and I mean it's doing really well I think I use it a ton internal I use it a ton I think you use it a ton weuse everyone internally uses it I think it's going to pass like 5,000 users in the next like couple weeks which is pretty cool oh wow cool so um yeah so that's that's what spiral is so all you spiral mostly um social media is like the ban of my existance I do not enjoy it I am not good at it however uh we do not make any money if people do not find our essays and so social media is a really key component and so I'll use spiral to uh take an essay and transform it into a tweet is my most common usage um I I I I assume it's the same for you like I'm curious for for your spiral usage if you move Beyond um just tweets is is there other places you're using it um yeah and I'll I'll show you an example um so yeah I mean I using it a lot for tweets um and Linkedin posts and all that kind of stuff so um and it's it works super well like it's kind of crazy how well it works like um I'll show you here we go so basically um so on the on the right over here like we have a tweet right it's got 157 likes which is not the most viral twet I've ever done but it has 30,000 views um and it's about this model that just came out or not came out but like that open eye has been working on that the information reported on and um uh and I want to tweet about it because like I think part of my job is like when something new comes out like I want to tell people about it um but also composing that tweet even though it's like it's like pretty wrote like it doesn't require a lot of thinking it's like it's not a new idea I'm not like that interested in it and but I want to get a tweet out so so that people see it um and people know about it because I think people rely on me for that kind of thing and so what I did was we have this spiral that is an internal spiral that converts articles into insightful conversational tweets and there was someone who on um uh on less wrong summarized like all the news about um about this less wrong is like a forum basically for rationalists and uh summarized all the news about this uh uh about this new model um so I read it um understood it and then I was like okay I want to turn this into like a something I can tweet and I just threw it into uh into spiral I pasted it in here and I just pressed generate multiple and then it generated a bunch of tweets so open AI strawberry is about to change the game this AI can solve complex problems on the first try without hallucinations open ey strawberry set to revolutionize AI here's what we know and it gives a bunch of stuff and um these are not things I want to tweet just wholesale but like a couple of these things would have been hard for me to come up with like it solves complex problems on the first try without hallucinations it generates high quality training data for Orion it may be integrated into catb as soon as this fall like obviously I could write that but it would take me a little while to like figure out the bullet point structure and what I want to say and having this thing like oh why does it matter right and so what I was able to do is I just took that I past it into Twitter I revised the headline revised the top because I didn't like the like set to revolutionize AI thing because it just felt like kind of cheesy um I you know I edited a couple things I took out some of the Emojis whatever and I tweeted it and it has 30,000 views and that's like a really simple thing where like I would have done this ordinarily but it would have taken me like 30 minutes or 40 minutes or something like that and it would have been a lot of brain work and for this I'm just editing which is like much easier than writing wholesale and it took me five minutes I was in bed like it was really really easy um and I do that a lot for news articles news stuff I do it for obviously all of our articles for our podcasts and it means that I tweet more I have more interesting stuff to say and um and like all my engagement and stuff is is way up because I'm able to put out more stuff um which is really cool I'm curious like as a writer I know that some people are going to watch this and like have like moral horor right that you're like oh you took someone else's content you transformed it with an AI and now you're going to monetize on top of that like that's I I think that's a case where some people uh some writers a real apprehension and like this is like the worst case scenario do you think about that at all does it bother you or do do you have a have you worked your way through those emotions I mean obviously I think that's like a really um important question and it does bother me if I think it's like uh I if I think there's a case of like it's stealing or plagiarizing or whatever like all that stuff is really bad and I will say also like it's much more common for me to be doing this with my own stuff than someone else's stuff but I so but I think this is like a really interesting case that like is important to like reason through my basic thing is um so for in this case like I cited the information in the tweet and linked to both linked to the information and linked to the article uh that it originally came from and I think like there's a very very wellestablished practice of like reading stuff from another news site and then summarizing it uh for your audience um and and that in general I think is like not a problem at all um I think there's a there's a like a further component which is like and uh you're using AI to do this and I think that there are like um I think that there are cases in which that's okay and cases where where that's not okay um the the case where it is not okay is um you are lifting wholesale without attribution like sentences or ideas that come from someone else um where it is okay is you are summarizing it in a new way uh for the audience that you have and I think that that's totally fine obviously like there are blurry lines there and one of the problems with AI is it's like hard to um it's hard to tell always like where the output is coming from and I think what we what we need are um both new tools to like detect like okay is this was this does this sentence come from somewhere or not um not was it AI generated but does it come from somewhere or not um and then uh two is like a new ethics about like what is okay and what is not okay because like when you have new technology it changes ethics um and we just haven't CH updated our ethics to account for this like new thing but I think we will like I don't think that this is going to be like a like a um we never figure that out I think in the next 5 to 10 years like we will shift like what is okay and what's not okay um and my my general belief is that using um like for example like training these tools on publicly available text to like create this like um intelligence layer is very different from training these tools creating the intelligence later and then having the intelligence later out output wholesale copyrighted stuff without um without attribution those are different things um and yeah I think I think we'll come up with ethics to differentiate them yeah it's interesting I um cuz I'll have people do this to my writing I don't know if you get people that do this but they'll like grab one of my posts they'll make a thread of all my ideas and then they'll and it'll be if not word for word copy it's the same thing like they they did a thread of my article or whatever and then um sometimes they'll give me attribution like they'll at the very end they'll have like a tweet a shout out to EV Armstrong for doing this or for writing about this or they'll get called out in the comments by one of my readers uh thank you readers for being vigilant uh Armstrong Warriors um but like they'll say hey like this sounds like my uh a post that I had recently written and I listen to your logic you're right I like it makes sense to me like transformation feels is totally fine but when it happens to you you know I'm like I don't like this like I spit on you you know like I I I don't like it at all but I then then go do and I'll use spiral to um I haven't done it the case where I'm pulling like other news articles or whatever but but like you said you know you gave attribution to the people who have the pay wall um and they did the original reporting but there there is no like I think it's really important to acknowledge uh even for us which is a very AI forward organization like we don't we don't have it figured out like I don't know what's right or wrong like I I you know and I don't think like anyone does and that's the hard part I think I think that's totally right I actually I have a very different response to that like um obviously someone like talking about an idea I had that they got for me without citing me like I don't like but um I do get people all the time like summarizing articles or podcasts and and being like this is from Dan chipper Dan chipper had this cool take or whatever and like I feel honored like I like I think um in en those kinds of things indicate that like people are um value value your content and are consuming it enough to like do something with it um and I think as a writer as an internet writer like that attention is like really really really important um and it it always sort of like lead bleed bleeds back into like subscriptions for every or like people reading more more of my stuff or whatever so I I actually like it a lot yeah I think it's um I if you think about like the bar of intellectual effort that's required to engage with the content uh when we first when you and I first started writing online and AI wasn't a thing the responses I would get and the ones I liked the most were the criticisms I loved when somebody would take my post think it was the dumbest thing they've ever read and write a substack about it like I loved that because even though I obviously disagree uh but I like that they took it seriously enough to try to refute it and you could think that each successive layer of model so two three to four to four and a half whatever like the intellectual activation energy is decreased because you can do more of the rot labor by the models um and so I wonder if there's a point eventually where we're like at gbt 6 um where we say okay I don't like this is no longer okay because you're just doing the whole thing um without any effort on your own it's completely a completely automated process um maybe maybe it is okay but uh like right now we're in this really fuzzy Middle Ground where it does require engagement it does require like enjoyment but a lot of the work can be outsourced to an AI you know yeah I think my my general feeling about that is um what the what these models are good at right now is um replicating patterns that you've that have been pre that they have seen previously um and uh like there are certain formats like for example this like you know straw tweet or whatever it follows a particular type of format for a kind of tweet that currently works that changes a lot um and the models are actually very very bad at like when things change and um uh need to be like a new thing that works needs to be found they're actually like not very good at that and and I think it's like unlikely that the language model architecture is going like on its own is going to learn to do that um which means that even if even at the gbt 6 or seven place um until the until the models um get much better at reasoning and learn from experience they're not going to just not going to do that um and like I guess who knows who knows what's going to happen but I'm actually like not particularly worried about um about that like it will happen like you know there's going to be a lot more AI generated content that's shitty I think we will develop tools and sensibilities to differentiate between them it's not going to be perfect um this always happens with new technology there's always trade-offs there's always bad \[ \_\_ \] and there's always good \[ \_\_ \] um and I think generally um we've actually been living in a sea of garbage for a long time um both in like on the Twitter sphere and Facebook but also just the scientific literature whatever like there's a deluge there's way more information um available now than there ever has been and I think language models are the first tool we've ever built to like actually effective more effectively deal with that information and get you the right information at the right time and sort of weighed through it obviously they're not perfect um and and what they what it means is like the the amount of information that you as a writer I as a writer can Traverse in in any given minute of our day is like so much higher and so yes like there's more stuff with less engagement um but what that means is you're you're bumping up against the things that you want to engage with more more frequently uh because you're you have access to many more things for a much smaller unit unit of attention and those things are filtered for you adequately by the language model um and so I think it can you can look at it in another way which is like it will get you to the things that you want to engage with more deeply more quickly um and like that's sort of how I think about it interesting um that was really far off I think how to write with AI um maybe this gets cut in the end but I I don't know it's just like I was like if I'm having some sort of emotional reaction I am sure that listeners of the podcast will be as well um so I thought it was worth bringing up totally no I think it's important it's an un I think it really is unsolved I think you're right like there's there's new problems I I do Wonder with the point of will build antibodies if it ends up being like social media where now in 2024 I think people are more and more rejecting social media than they used to um 10 years ago because they're like oh wait this stuff is like uh rotting my mind and I wonder if it'll be similar with AI in the early years people get sucked in but over time you build up Social antibodies to it I think so and it changes like the way that gen Z uses social media is just different from the way that we do and um and that's just like a a kind of like it's one of the interest interesting and beautiful things about like how technology like changes The Human Experience like we sort of co-evolve together and we've been doing that for a long time um cool so is there yeah what else is there anything else you wanted to show about about using using AI in your audience process or just in any part of the process or I'm curious if you have any Reflections on uh on the conversation I think the last point I'll make on AI in audience is that we've spent all of today talking about AI in the context of Generation Um but a lot more importantly is AI in uh distribution where it's most of the content that we see online is algorithmically selected it's AI selected we don't use large language models but they're machine learning algorithms and so as you think about as I think about the content I make I do have to think about it in the context of the algorithm in which it will be distributed um which is why when you were talking about spiral the spiral that works for a tweet will not work necessarily for a LinkedIn post or the LinkedIn post will not work for Facebook and that is an audience but is an algorith rithmic thing as well and so as I when I think about Distributing online it is like oh I want to automate away like writing tweets because I don't like writing tweets um unless I'm tweeting about movies in which case no one will like them and I'll tweet them anyways um but it's more about as I tweet what you have to think about what's going to engage the algorithm which is a like a multiple hour long conversation on getting into that but I think it's a really important point that most people Miss is that you're serving the algorithm the the AI algorithm as much as you're in the audience in the context of distribution totally and there's a lot of sort of taste involved in in knowing how to do that which is kind of interesting and it can be D dystopian or it can be like a this is this is sort of how you get to people you know um oh yeah no I I think it's just the \[ \_\_ \] sandwich you have to eat if you want to write online like there's just no way around it you just you cannot like you can kick and scream as much as you like but it's just the way it is and you just have to deal with it yeah so uh this is is great we I think we're we're around time uh I'm yeah I'm really psyched that we got to do this I had a lot of fun I feel like I learned a lot I hope you did too um and uh I'm also just psyched about the course you're running so tell us a little a little bit about the course before we sign off yeah so I mean it's very similar topics to what we have today you can think of it in two parts uh well the course's name is how uh to write with AI and it's General sensibilities around how to write um so the elements that we discuss today of taste topic craft and audience and the writing principles you need to understand and then for each of those principles the accompanying tools that you can use to automate away the rot work which is similar to the tools that we discuss today um which you know Claude chat gbt Lex and spiral and then from there so that's that's the lecture format but the thing I'm really excited about is there's uh all these student groups that are going to be working together in writers we'll have editors that we trained um that will be helping each of these groups and then at the end everyone will have a chance to share their essay with uh every's audience of 70 I don't know where we at Dan what did our Monday metrics meeting say 7000 around we 78 78 are we okay 78 78 we're at 78,000 3,000 more than we were last week I think the when I sat sat down when you and I were talking about this idea it was really like how can we take the very hard hard lessons that's taken us many years to learn and just like share those with people um and so they don't have to go through the many years of suffering that we did totally that's what the class is it's going great we launched it last week people really excited it starts September 17th of 2024 amazing so if you're listening to this or watching this and you want to learn more uh we'll we'll put the link down in the show notes um and you should uh follow Evan on Twitter at it's your boy Evan I guess we're calling it X now on x at it's your boy Evan um and obviously subscribe to every where we both write every week and um Evan thanks for joining thanks for having me oh my gosh folks 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