A clip in which host Dan Shipper and writer David Perell explore using ChatGPT as a tool for uncovering vivid memories, demonstrating a prompt-based memory exercise that begins with finding an anecdote for an essay about Manhattan's ornate and storied buildings and leads somewhere unexpected. # Video Identity Observations: "Write Like A Pro with ChatGPT" ## Format & Presentation - **Conversational demo/interview format**: Two speakers — one asking questions ("super curious to hear about like how you have used chat GBT in your own writing process") and one demonstrating a live workflow with ChatGPT. - **Live, unscripted walk-through**: The creator demonstrates prompting in real time: "we're gonna say what buildings in New York are the most beautiful and distinctive… give me a series of buildings built between 1910 and 1933." - **Emphasis on process over product**: The demonstration pivots from the planned topic (New York taste) to an unexpected insight ("we went in thinking we were going to write an article about New York City and taste and we came out with this Max Min thing"), and the creators explicitly frame this pivot as the lesson. ## Intended Audience - **Writers and content creators**: The co-speaker states, "all creators have to get good at is allowing that to happen without filtering it out" — addressing people producing written/creative work. - **People curious about AI-assisted creativity**: The framing centers on how ChatGPT can "push your brain into new areas that you wouldn't have thought of." ## Claimed Scope / Value Proposition - **Teaching AI-augmented writing**: The title itself ("Write Like A Pro with ChatGPT") claims the channel/video teaches professional-level writing with AI assistance. - **Techniques demonstrated**: - Using prompts to surface personal anecdotes via memory association: "memory is basically layered… those memories are stored in space" (with a self-disclaimed basis: "the way that I know this to be true — I'm not a psychologist"). - Following creative tangents rather than filtering them: "the mistakes are the things that… turn into things that are interesting." - **Ideas as worldview-building**: "now we've just given someone a world view just off the top of our head." ## Explicit Self-Description Evidence - No direct channel-level self-description (e.g., "on this channel we…") appears in the transcript. - The guest speaker references intellectual sources by name ("Moonwalking with Einstein"), demonstrating a **book/idea-referencing style** rather than a stated channel claim. ## Demonstrated Tone & Identity Patterns - **Enthusiastic, iterative, improvisational**: Repeated real-time reactions ("I love it okay great," "that's really really amazing"). - **Intellectual / essayistic bent**: The demo meanders through psychology of memory, hiring heuristics ("hiring and dating is a Max function"), and creative philosophy — suggesting a channel identity built on **thinking-in-public** content. ## Distinguishing Claims from Demonstration | Type | Evidence | |---|---| | **Creator claim** | ChatGPT "is really good at… pushing your brain into new areas" | | **Demonstrated pattern** | Actual live prompt sequence producing an unplanned essay concept on the spot | | **Claim about audience** | "all creators have to get good at" following tangents — implies creator audience | # Delivery Observations: "Write Like A Pro with ChatGPT" ## Overall Format A **live, conversational demo** between two speakers: one narrating a real ChatGPT writing session, the other reacting and summarizing. Delivery is informal, unscripted, and thinking-out-loud in style. ## Tone - **Casual and exploratory**: heavy use of "like," "basically," "sort of," "stuff like that" — e.g., > "it's not a Max function cuz you need a bunch of different things that need to sort of play together and stuff like that" - **Enthusiastic affirmation** from the second speaker: > "I love it okay great" ## Vocabulary & Recurring Phrases - **"So what we're going to do is" / "so what we're gonna do"** — repeated framing device (appears at [14], [25], [40]): > "so what we're going to do is we're going to write a piece on how New York City..." - **"basically"** — frequent connective filler, at least six occurrences, e.g. > "and now we've basically given someone a world view" - **"anecdote"** — repeated keyword of the method being taught: > "I want to find an anecdote... I want to find an anecdote" ## Teaching Habits - **Think-aloud prompting**: he verbalizes the exact prompts he types to ChatGPT: > "what buildings in New York are the most beautiful and distinctive question mark give me a series of buildings built between 1910 and 1933" - **Self-questioning then answering** to expose reasoning: > "and why are you asking that because I want to find an anecdote" / > "so ask what is the opposite of a Max function I don't actually know a Min function" - **Concrete example first, abstraction second**: the personal Woolworth Building story precedes the general principle ("Max function") — a show-then-tell pattern. - **Rhetorical questions to the audience/interlocutor**: > "how many things do you think of that you hadn't thought of in a decade" - **Explicit meta-lesson / recap** at the end: > "we went in thinking we were going to write an article about New York City and taste and we came out with this Max Min thing" — followed by the takeaway: > "it's just following the spark" - **Epistemic hedging**: flags his own limits — > "the way that I know this to be true I'm not a psychologist" ## Communication Patterns - **Appeal to external reference**: cites a book as evidence — > "Moon walking with Einstein he's going through and he's walking through the house" - **Repetition for emphasis** with stutter-restarts: > "really really amazing," > "that that that turn into things that are interesting" - **Compliment-and-generalize closing move** from the second speaker: > "one of the things that you're good at and all creators have to get good at is allowing that to happen without filtering it out" ## Pattern Stability - Frequent **"so" as a sentence-opener**, the **"basically" filler**, and **narrating prompts aloud** recur throughout — stable habits. - The **stutter-restarts** ("I W to I wna I want to") appear mainly in the second speaker's excited closing; evidence is thin to call this a stable pattern rather than an isolated moment. # Observation Document: "Write Like A Pro with ChatGPT" (video 01a0f15b-3155-7624-aed1-3a80d1866f58) **Note:** No curated speaker metadata was supplied. Speakers are identified only structurally: one person is an **interviewer/host** asking questions; the other is a **writer demonstrating a ChatGPT-assisted process**. Names are not stated in the transcript. ## Purpose of the Session - The host asks how the writer uses ChatGPT in their own writing process; the writer then demonstrates live. ## Demonstrated Workflow - **Initial premise:** Write a piece on how living in New York City gives you "better taste." - **Prompt used (paraphrased):** Ask ChatGPT for the most beautiful and distinctive NYC buildings built between **1910 and 1933**. - **Stated goal:** The writer isn't seeking facts directly but an **anecdote trigger** — something specific that might connect to personal memory. ## Reasoning: Memory and Place (Writer's Claim) The writer offers an explicit, qualified theory of memory: - **Claim:** Memory is "layered" and stored "behind doors"; we "outsource our memory" to physical checkpoints/spaces. - **Evidence offered:** - Returning to a childhood home surfaces memories not recalled in a decade. - Memory champions associate ideas with spaces and mentally "walk through" a house — citing the book *Moonwalking with Einstein*. - **Qualification preserved:** > "the way that I know this to be true I'm not a psychologist" — the writer explicitly disclaims expert authority. - **Application:** Querying ChatGPT about specific buildings is used to **prime contextual memory** and surface a personal anecdote. ## The Surfaced Anecdote (Writer, as recollection) - ChatGPT's first result was the **Woolworth Building**. - The writer recalls, years ago as a college student/intern, meeting an intimidating Twitter-famous person working there. - Quoted line from that person: > "hiring and dating is a Max function" - **Explanation given:** In hiring/dating, only the top value matters — 99 "duds" don't matter if the one right person is found (you marry one person, hire one CEO). Contrast: designing furniture in a room is **not** a max function because elements must work together. ## Derived Framing for the Piece - The writer proposes a piece contrasting two ways of operating in the world: - Things governed by **maximums/minimums** (only the top value matters). - Things governed by the **broad swath / averages** (how many things you have matters). - Claimed payoff: asking "is this a max function or the other thing?" when entering a project gives the reader "a world view." ## Host's Claims About the Creative Process - **Divergence is not failure:** They started intending to write about NYC and taste, and ended up with the max/average framing. - > "the mistakes are the things that work that... turn into things that are interesting" (transcribed repetition preserved in meaning). - **ChatGPT's value claim:** It is good at "pushing your brain into new areas you wouldn't have thought of." - **Creator skill claim:** All creators must learn to **follow the spark without filtering it out** as "not on topic." ## Unresolved Tensions / Qualifications - The writer is unsure of the precise opposite of a max function: > "I don't actually know a Min function it maybe well there's probably Max Min and then there's probably like a distributed one" — the taxonomy is left informal. - No factual verification of the memory-champion or psychology claims is offered beyond the writer's anecdotal reasoning and the *Moonwalking with Einstein* reference. # Video Attribution Record ## Video - **Title:** Write Like A Pro with ChatGPT - **Video ID:** `01a0f15b-3155-7624-aed1-3a80d1866f58` ## Speakers and Roles | Speaker | Role | Evidence | |---|---|---| | **Speaker A** (interviewer/host) | Likely **creator or host** | Opens with a question, narrates/summarizes what happened at the end ("you just did that live and that was really cool") | | **Speaker B** (demonstrator) | **Guest** (writing demonstration) | Performs the live ChatGPT writing exercise, shares the personal Woolworth Building anecdote | > Note: No curated metadata was supplied, so exact names are unavailable; role assignments are inferred only from conversational structure. ## Provenance and Referenced Sources - **ChatGPT (GPT):** Referenced as the tool queried live for "buildings in New York... built between 1910 and 1933." - ***Moonwalking with Einstein*:** Speaker B references the book's memory-palace technique as support for spatial memory claims; no author named in transcript. - **Third-party claim:** A Twitter figure, unnamed, quoted as saying **"hiring and dating is a max function"** — recalled from a meeting in the Woolworth Building during Speaker B's college years. - **Speaker B self-disclosure:** "I'm not a psychologist" (explicit disclaimer regarding memory claims). ## Promotional Segments - None identified in the transcript. ## Availability and Limitations - **Comment availability:** Unknown — no metadata supplied. - **Curated metadata:** Absent; speaker identities, channel, and publication details are unverified. - **Timestamps:** Not present in transcript. super curious to hear about like how you have used chat gbt in your own writing process yeah so there's a few things I'm going to need your help with GPT please so what we're going to do is we're going to write a piece on how New York City just by virtue of living here allows you to have better taste I love it okay great so what we're g to do is we're gonna say what buildings in New York are the most beautiful and distinctive question mark give me a series of buildings built between 1910 and 1933 and why are you asking that because I want to find an anecdote okay I want to find an anecdote why you start there so what I'm looking for is I want to do something specific and then hopefully it'll give me a building that I've been to and the way that memory works is memory is basically layered and sort of behind doors right so what we do is we Outsource our memory to little checkpoints that we find and the way that I know this to be true I'm not a psychologist is when you go back to your childhood home and you're back in your childhood room how many things do you think of that you hadn't thought of in a decade that all of a sudden become clear that's because those memories are stored in space how do the world's memory Champions think of their ideas they associate them with spaces and then they walk through the house right Moon walking with Einstein he's going through and he's walking through the house and then when he sees that space he thinks of a new memory so you're using this basically to like prime your contextual memory to like surface something that might be interesting so like yeah let's read through through this like what are you seeing and what's it what's it making you think of so we have the Woolworth Building here we go so now I just had an anecdote that showed up in the very first example and we're going to change what it is that we're writing about okay so many years ago I walked into the WW worth building and I had a meeting I was in college and there was a guy who was big on Twitter who I was very intimidated to meet with and he was working there and we were talking about hiring and he had a great line he said hiring and dating is a Max function so here's what that means it means that certain things what you're trying to do so for example if you're designing uh Furniture in a room it's not a Max function cuz you need a bunch of different things that need to sort of play together and stuff like that where is if you're just working on hiring one person you could have 99 total Duds but it doesn't matter as long as the one person who you're trying to find is good you only marry one person you only hire one person to be the new CEO for your company right and I remember that conversation so vividly and the Woolworth Building basically prompted that and I could start that with an anecdote and I could basically say there's certain parts about the world where the averages really matter so ask what is the opposite of a Max function I don't actually know a Min function it maybe well there's probably Max Min and then there's probably like a distributed one so there's some functions where all that matters is how good your top value is and then there's other things where how many things you have are really useful and what I would just say is now we've just set up a piece that basically present two different way of walking through the world in two basically fields that you can play in certain things are about maximums and minimums certain things are about the broad swath so now you asked about an anecdote we went into GPT we found the anecdote I was this college kid I was nervous I was an intern I didn't actually know what this meant and now we can basically write a short piece to say whenever you enter a working arrangement whenever you enter a project you can ask is it the max function or is it this other thing that we're setting up and now we've just given someone a world view just off the top of our head this is I think that's really really amazing and it's like and one thing that I I want people to notice is that we went in thinking we were going to write an article about New York City and taste and we came out with this Max Min thing or Max and average thing and that's just how the creative process works like that is not a mistake the mistakes are the things that work that that that turn into things that are interesting and what what you did is you had a little thing where you're like I'm little I'm inspired about New York like I W to I wna I want to uh think about New York stuff you threw it into chat gbt it like reminded you of this other story and you just like followed that thread instead of being like Oh no this is not on topic like I should filter that out you're like no no this is really interesting and I think that's a that's what chat gbt is really good at is sort of pushing your brain in new into new areas that you wouldn't have thought of and one of the things that you're good at and all creators have to get good at is allowing that to happen without filtering it out and being like that's not on topic it's just following the spark um and I think you just did that live and that was really cool