Writer David Perell joins host Dan Shipper to demonstrate using ChatGPT as a tool for uncovering vivid personal memories while writing an essay. Searching for a lead anecdote, they explore memories of Manhattan's ornate buildings, leading to an unexpected result. # Channel Identity Observations: "Using ChatGPT to Write Viral Articles" ## Explicit Self-Description Evidence - No direct channel mission statement, tagline, or "welcome to my channel" framing appears in the transcript. The video contains no explicit creator claims about the channel itself. - The **title** frames the channel's content promise around **AI-assisted writing** and **viral content creation**: *Using ChatGPT to Write Viral Articles*. ## Observable Presentation Evidence ### Demonstrated Content Scope - The video presents a **live, unrehearsed creative workflow** using ChatGPT as a writing assistant, not a lecture or tutorial script: > "so what we're gonna 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" - Demonstrated topics span **writing craft, creativity, memory, and mental models**, e.g., the host's monologue on spatial memory: > "the way that memory works is memory is basically layered and sort of behind doors" > "how do the world's memory Champions think of their ideas they associate them with spaces" - The video shows a pivot from the planned topic (NYC and taste) to an emergent one (max vs. average functions), explicitly framed as a lesson: > "we went in thinking we were going to write an article about New York City and taste and we came out with this Max men thing... and that's just how the creative process works" ### Format and Structure - **Two-person conversational format**: a host/interviewer and a guest demonstrating a process live. Evidence: the interviewer prompts ("super curious to hear about like how you have used chat gbt in your own writing process") and later debriefs the guest ("and I think you just did that live and that was really cool"). - **Screen-share walkthrough style**: the guest narrates prompts and outputs as they occur ("so we have the Woolworth Building here"). ### Intended Audience - **Writers and content creators** seeking to use AI tools in their process, evidenced by: > "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" - The instructional aside — "one thing that I want people to notice is..." — indicates the video is addressed to viewers learning a method, not just the in-video guest. ### Claimed Value Proposition - ChatGPT positioned as a **creativity-sparking tool rather than a writing replacement**: > "that's what chbt is really good at is sort of pushing your brain into new into new areas that you wouldn't have thought of" - The stated payoff of the demonstrated method is producing a "worldview" for readers: > "now we've just given someone a world view just off the top of our head" ## Notes on Limits - No curated metadata was supplied; identity inference rests solely on title and transcript. - No private motivations are inferable; all observations above trace to quoted transcript passages. # Delivery Observations: "Using ChatGPT to Write Viral Articles" ## Overview This is a **conversational, demonstration-style dialogue** between an interviewer and a creator working live with ChatGPT. The primary speaker narrates his creative process in real time while thinking aloud. --- ## Tone & Register - **Casual, spoken register** with filler and self-correction: "what we're GNA do is we're gonna say," "uh Furniture," "I W to I wna I want to." - **Enthusiastic and affirming**, especially from the second speaker: "I love it okay great," "that was really cool." - **Playfully directive toward AI**: "there's a few things I'm going to need your help with GPT please." ## Vocabulary & Conceptual Framing - Repeated use of **technical/mathematical metaphors** for life decisions: > "hiring and dating is a Max function" > "you only marry one person you only hire one person" - Uses **memory-science framing**: "memory is basically layered and sort of behind doors," "we Outsource our memory to little checkpoints," "those memories are stored in space." - References external material as evidence: "**Moon** walking with with Einstein." ## Recurring Phrases & Verbal Tics - **"So" as a sentence-starter**, heavily repeated: "so what we're going to do," "so what we're looking for," "so we have the Woolworth Building," "so now we've just set up a piece." - **"Basically" as a hedge/filler**, appears repeatedly: "memory is basically layered," "I could basically say," "we've just basically present two different way." - **"Just" as a softener**: "we just set up a piece," "we've just given someone a world view just off the top of our head." ## Teaching Habits - **Thinking-aloud modeling**: narrates each step of the workflow as he performs it — querying GPT, reading the result, connecting it to memory. - **Self-qualifying honesty**: "the way that I know this to be true I'm not a psychologist" — flags limits of his own expertise. - **Concrete anecdote before abstraction**: the Woolworth Building story precedes the "Max function" concept. - **Explaining via contrast**: max vs. average, furniture design vs. hiring — pairs of opposing examples. - **Meta-commentary on the process**: explicitly names the lesson — "the mistakes are the things that work that turn into things that are interesting." ## Communication Patterns - **Two-person structure**: the interviewer summarizes and validates ("so you're using this basically to like prime your contextual memory"), serving as a reflective mirror. - **Interrupted, layered speech**: chains of clauses with mid-course corrections, consistent with genuinely spontaneous live demonstration. - **Closing on encouragement**: the final speaker generalizes the lesson to all creators — "all creators have to get good at is allowing that to happen without filtering it out." ## Uncertainty Notes - The transcript's speaker turns are not explicitly labeled; attribution of lines to "interviewer" vs. "creator" is inferred from phrasing and may be imperfect. - Only one video is available, so patterns like the "so"/"basically" tics cannot be confirmed as stable across this speaker's other work. # Observation Record: Using ChatGPT to Write Viral Articles ## Participants - **Speaker A** (unnamed host/interviewer): asks how ChatGPT is used in the writing process; provides closing commentary. - **Speaker B** (unnamed guest/writer): demonstrates a live ChatGPT-assisted writing session. - No curated speaker metadata supplied; identification is based only on conversational turns in the transcript. ## Demonstrated Workflow: ChatGPT as Anecdote Retrieval Tool ### Setup - Speaker B decides to write a piece on **"how living in New York City allows you to have better taste."** - Prompt to ChatGPT: *"What buildings in New York are the most beautiful and distinctive? Give me a series of buildings built between 1910 and 1933."* - Stated reason: **"I want to find an anecdote."** Specificity increases the chance the model surfaces a building he has personally visited. ### Reasoning: Space-Based Memory Speaker B's stated theory of memory: - Memory is **"layered and sort of behind doors."** - We **outsource memory to checkpoints** found in physical spaces. - Evidence he offers (with the qualification *"I'm not a psychologist"*"): - Returning to a childhood home/room surfaces memories not recalled in a decade — therefore memories are **stored in space**. - Memory champions associate ideas with spaces and mentally walk through them (reference to *Moonwalking with Einstein*). - Speaker A summarizes this as **priming contextual memory** to surface interesting material. ## Surfaced Anecdote and Idea - ChatGPT's first result was the **Woolworth Building**, which triggered a memory: as a college intern, Speaker B met a prominent Twitter figure there who said: > "Hiring and dating is a max function." - Speaker B's explanation of the line: - **Max function domains**: hiring, dating, choosing a CEO — 99 failures don't matter if the one right choice is good. - **Non-max domains**: designing furniture in a room requires many things working together (averages/broad distribution matter). - On the opposite of a max function, he states uncertainty: **"I don't actually know — a Min function? ...there's probably Max, Min, and then there's probably like a distributed one."** (qualification preserved as unresolved). ## Pivot in the Piece's Topic - The article shifted from **New York City and taste** to **max functions vs. distributed/average functions** as two ways of viewing work arrangements and projects. - Speaker B frames this outcome as worldview-building for readers: *"we've just given someone a world view just off the top of our head."* ## Stated Positions on Creativity and ChatGPT **Speaker B:** - The topic pivot **"is not a mistake... the mistakes are the things that... turn into things that are interesting."** **Speaker A (closing commentary):** - ChatGPT is good at **"pushing your brain into new areas"** one wouldn't have thought of. - Creators must learn to **follow the spark without filtering** divergent ideas as "off topic." - Characterizes Speaker B as having done exactly this live: entered with a New York idea, followed the Woolworth/anecdote thread instead of discarding it. ## Unresolved / Qualified Points - Speaker B explicitly disclaims psychological expertise regarding the memory theory. - The "opposite of a max function" is left tentatively defined (min vs. distributed), not settled. # Speaker Attribution Record ## Video - **Title:** Using ChatGPT to Write Viral Articles - **Video ID:** `01a0f15b-30a0-70c1-bf6f-9bfee758444a` - **Curated metadata:** None supplied; speaker identities are **not explicitly named** in the source material. ## Speakers & Roles ### Speaker A — Primary Demonstrator (likely creator or featured writer) - **Role evidence:** Performs the live writing demonstration, describes personal memories, drives the ChatGPT prompts. - **Identification:** Identity not stated in transcript or metadata. - **Notable quotes:** > "hiring and dating is a Max function" — attributed to a third party (a "guy who was big on Twitter" met at the Woolworth Building), recounted by Speaker A. > "I'm not a psychologist" — explicit self-disclaimer regarding memory claims. ### Speaker B — Interviewer / Commentator - **Role evidence:** Opens with a question, then reacts to and analyzes Speaker A's process. - **Identification:** Identity not stated in transcript or metadata. - **Notable quote:** > "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" ### Third parties referenced (non-speaking) - **Unnamed "guy who was big on Twitter"** — source of the "max function" hiring/dating analogy; worked in the Woolworth Building. ## Referenced Sources & Claims - **ChatGPT ("GPT")** — used as an interactive tool; supplied building list (Woolworth Building cited as first example). - ***Moonwalking with Einstein*** — book referenced (without author) for the memory-palace/spatial-memory technique. - **Memory champions** — referenced as associating ideas with spaces; no specific source cited. - **Unverified claim:** Spatially cued memory explanation offered by Speaker A, who explicitly disclaims expertise ("I'm not a psychologist"). ## Promotional Segments - **None detected.** No product promotion, sponsorship, or calls to action appear in the transcript. ChatGPT is discussed as a tool but no promotional framing is explicit. ## Availability & Provenance Limits - **No curated metadata supplied** — speaker names, channel owner identity, publication date, and comment availability are **unknown**. - **No timestamps** present in transcript. - Speaker attribution inferred from conversational turns; roles (creator vs. guest) cannot be confirmed without metadata. 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 GNA 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 so 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 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 Woolworth 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 M 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 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 men 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 chbt 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