Episode 22: Dan Shipper interviews bestselling author Steven Johnson about NotebookLM, Google's personalized research assistant. They load 200,000 words of NASA Apollo 1 fire transcripts and Johnson's Readwise reading notes since 1999 into NotebookLM to co-develop a concept for his next project. The episode shows NotebookLM condensing the transcripts into FAQs and chronological timelines, identifying the fire's catalyst, and surfacing an unexpected story from Johnson's notes to help explain the fire, culminating in generating the opening script for a documentary. Timestamps cover Johnson's approach to organizing ideas and curating information, NotebookLM's design goals, copyright handling, and its restraint when asked to speculate. # Channel Presentation Observations — "Is NotebookLM—Google's Research Assistant—the Ultimate Tool for Thought? - Ep.22 with Steven Johnson" ## Channel Self-Description (Explicit Claims) ### Stated Show Identity - The host names the show **"AI and I"**, hosted by **Dan Shipper**. Evidence: closing outro — "smash that like button and subscribe to Ai and I... it's a journey into the future with Dan shipper as the captain of the spaceship." - The host describes his own behavior as the show's format: going on **live exploratory demonstrations with guests**: > "what I really love doing as part of these shows is to go on a little exploration together and use these tools to do something new that neither of us kind of know where it's going" - The host frames experimentation with AI models as a defining premise: > "this is so much of what our existence is like now with these models... like what will it do in this situation? ... that's the whole PR of this show" ### Host's Background (As Stated by Host/Guest) - The guest introduces the host's admiration-oriented framing: "you're such a great writer" — directed at the guest, not a host self-description. - No explicit self-description of the host's affiliation or credentials appears in the transcript. ## Observable Presentation Patterns ### Format - **Long-form interview + live product demo.** The bulk of the video is a screen-shared walkthrough of NotebookLM by Google's Steven Johnson, with the host asking questions and co-prompting the tool in real time. - **Live, unrehearsed experimentation** is explicitly showcased: "we're doing it live folks" (Johnson, on a feature not fully tested). - **News-break framing**: the episode positions itself as a launch-day announcement vehicle — "by the time this podcast comes out a new version of notebook LM will be out... we actually have some kind of news to break as well." ### Intended Audience - **Writers, researchers, and knowledge-management enthusiasts** ("nerds" for note systems, per both speakers: "why do you think that's every like nerd's dream... to have this sort of like interconnected note system"). - **AI-curious generalists** interested in how creative professionals use LLM tools — evidenced by deep discussion of research workflows, Readwise notes, interview transcripts, and documentary scripting. - **Viewers, not just listeners**: repeated references to on-screen content ("for those of you are listening, it's just like an endless list of quotes") indicate a visual-first format with an audio fallback. ### Claimed Scope - Coverage of **AI tools and their use by creative/knowledge workers** (NotebookLM, Gemini, GPT-3 all discussed). - The outro makes an exaggerated, tongue-in-cheek scope claim: "pure unadulterated knowledge bombs about chat GPT every episode" — note the mismatch: this episode is about Google's NotebookLM, not ChatGPT. ## Guest & Product Context - Guest: **Steven Johnson**, introduced as best-selling author (*How We Got to Now*, *Where Good Ideas Come From*, *The Infernal Machine*) and **editorial director of NotebookLM and Google Labs**. - Product claims made on-air by the guest (creator-side claims, not independently verified in the video): launch in 200+ countries, 50 sources × 500,000 words per notebook, no training on user sources, new inline citations, Google Slides support, image understanding, Notebook Guide templates. ## Notes on Distinguishing Claims from Demonstration - **Demonstrated**: interactive querying of ~7,000 personal quotes, source-switching, citation navigation, note pinning, "suggest related ideas," and generation of a documentary opening script — all shown in the live demo. - **Claimed but not demonstrated**: future agent mode ("please go scour the internet... that's clearly in our future"), copyright/training safeguards, and the "1% of notebook users understand this" usage statistic. - The outro's affectionate, hyperbolic tone ("I'm absolutely hopelessly in love with you") suggests an intentionally playful, meme-adjacent channel voice, but this is a single data point. # Delivery Observation Report ## Speakers & Format A two-person conversational demo/interview: **Dan (host/interviewer)** and **Steven Johnson (guest, editorial director of NotebookLM)**. The episode is built around a **live product walkthrough** — "we're doing it live folks" — rather than a purely scripted Q&A. --- ## Tone - **Enthusiastic and exclamatory throughout**, from both speakers. Dan reacts repeatedly with short superlatives: > "that's so cool" • "oh my God" • "that's amazing" • "it's so extraordinary" - Steven matches the energy, especially during his own demos: > "that's just kind of mind-blowing" • "this is so much fun" • "this product just blows me away" - **Playful banter**, including a running joke about profit-sharing on the improvised documentary idea: > "are you gonna want a piece of this project or 10%?" > "I hope you all — a Dan Shipper Steven Johnson production" ## Recurring Phrases - **"That's so cool"** — Dan says this at least three times, including twice back-to-back early in the demo: > "oh that's really cool it brought up a card... that's so cool that's the opening" - **"Really/very excited"** — Steven uses variants repeatedly: > "we're really excited about that" • "we're very excited about it" • "we're incredibly excited about it" - **"Kind of"** — extremely frequent hedge from Steven ("kind of a prototype," "kind of the basics," "kind of mind-blowing"), softening claims. - **"This is new as of today"** framing — a launch-day motif: > "this is a brand new feature rolling out today" • "this is also new as of today" • "now available in over 200 countries around the world uh as of today" ## Vocabulary & Framing Habits - **Steven's technology-history framing**: he reaches for historical analogies and cultural references: > "I always say it was a little bit like The Velvet Underground of software" > "I used to talk about like a duet between human and computer but this is like a full chorus" - **Metaphor of collaboration/partnership with software**, repeated across contexts: > "this almost feels like a partnership with the software" > "it's just an extension of your memory" - **Concrete numerals for scale** — a consistent persuasive habit: > "7,000 quotes" • "2 million words" • "50 sources" • "500,000 words" • "25 million words" • "200,000 words worth of transcripts" ## Teaching / Demo Habits (Steven) - **Narrates the interface for audio listeners**: > "for those of you are listening it's just like an endless list of quotes" > "I'll just read this for people who are listening" - **Explains subtle mechanics with checkable evidence** — points to small UI details and verifies them: > "it'll say down at the bottom at the chat box it'll say 15 sources" - **Discloses product limitations candidly**, separating what works from what doesn't: > "one thing that's actually annoying to me about NotebookLM right now" > "it didn't have citations because of that I got a note to the team here" - **Uses pre-written prompt notes as a technique demonstration**: > "one little kind of low tech NotebookLM hack... I'll have just a prompt note" - **Anticipates audience skepticism and addresses it directly**, e.g., on copyright: > "it's really important to stress this... we're not training the model on this information" ## Interview Habits (Dan) - **Frames questions as meta-prompts about the tool's limits**: > "do you think it'd be good at that — would NotebookLM be good at finding those things?" - **Iteratively refines prompts aloud with Steven**, modeling prompt-engineering collaboratively: > "can we add a little... ideally the idea is like seemingly unrelated and surprising" > "should we ask it to be surprising or you think we should just do straight up" - **Ends with a standard closing block** — book plug, Twitter handle, and contact info — plus a highly stylized (likely pre-recorded/satirical) outro: > "you absolutely positively have to smash that like button and subscribe" ## Verbal Fillers & Disfluency Patterns - Both speakers show heavy **"um/uh/like" density**, consistent with genuinely unrehearsed conversation. - Steven frequently **restarts words for emphasis**: "and and and," "the the the documents," "is is is" — clustering when excited. - Dan shows **repeated-word emphasis**: "and and it's very good," "that that you've like kind of collected." ## Uncertainty Notes - The transcript is auto-generated and lacks speaker labels; attribution of individual short interjections ("oh my God") is inferred from context and may be imperfect. - The closing outro's tone (satirical vs. sincere) is a **single isolated moment** — no pattern can be established from one occurrence. - Timestamps are fragmentary, so frequency counts of phrases (e.g., "that's so cool") are approximate. # Position Extraction: NotebookLM as a Research and Thinking Tool — Ep. 22 with Steven Johnson ## Participants - **Steven Johnson** — author (*The Infernal Machine*, *How We Got to Now*, *Where Good Ideas Come From*, *Emergence*) and **Editorial Director of NotebookLM and Google Labs** - **Dan Shipper** — host, interviewed Johnson and drove the live demos *Note: transcript lacks explicit speaker labels; attribution below is based on conversational context and self-identifications within the transcript.* --- ## NotebookLM: Product Vision and Announcements ### What NotebookLM is (Johnson) - A tool developed for ~two years at Google Labs, designed from the start with a **language model at its core** — not AI bolted onto existing software. - The goal was "a genuinely new kind of surface to work with," not "adding some AI to a word processor." - **Announced on the show**: rollout to **over 200 countries**, alongside new features (inline citations, Google Slides support, image understanding, Notebook Guide). ### Source-grounding as a design principle - Everything in NotebookLM is **grounded in user-provided documents ("sources")**; users start projects by uploading sources, and the model "becomes an expert" in them. - Johnson stated the team intentionally built a **fully grounded model** first: "let's build a model that is fully grounded and then we'll really just stick to the facts." - He acknowledged a **tension**: he sometimes wants the model "to be a little bit more open-ended," but in research mode they are "erring on the side of groundedness." He said a future "slider" for openness/closedness is possible but not yet built. ### Copyright and training stance (Johnson) - Users' uploaded material is **not used to train the model**; it is loaded only into the context window. - Quote: "there's no chance that this information which is under copyright is going to be used to train the model or be shown to anybody else." ### Design philosophy: "emergent chaos" vs. organization - Johnson described his 30-year principle: **dump everything in one place, use smart tools to find things, spend zero time organizing** — applied even to his email. - He acknowledged NotebookLM reflects this "probably to a fault": **you cannot tag notes**, and he resists pre-categorization because it "limits the connections." - He recognized a competing group of users who want tagging and systematization, and expressed hope the product can "play well with both those groups." - Shipper self-identified as "definitely in the bottom up camp." --- ## Johnson's Personal History with Idea-Organizing Software - **HyperCard (1987)**: a formative experience; he built a class-notes app called "Curriculum" and admits he spent more time building the tool than taking notes. He likened HyperCard to "The Velvet Underground of software" — never a hit but influential. - **DEVONthink (~20 years ago)**: enabled storing book quotes and early semantic search; on *The Ghost Map*, the software would surface forgotten quotes and make new connections, which "almost feels like a partnership with the software." He was careful to distinguish: the connections came from the software, but turning quotes into prose "is my intelligence." - **GPT-3**: convinced him "now it's all really going to be possible." --- ## Claims About Capabilities (Demonstrated Live) ### Scale - New limits (as of recording): **50 sources per notebook, up to 500,000 words each** — "effectively... 25 million words in a single notebook." - Johnson's personal notebook contains ~**7,000 quotes / ~2 million words** of reading notes dating to ~1999. ### Live demonstrations - **Inline citations** (new feature): answers link to the exact source quotes; clicking navigates to the original passage. - **Source focus switching**: the chat bar shows how many sources are selected (e.g., "15 sources"), letting users narrow the model's focus. - **"Interestingness" queries**: Johnson claimed the model understands concepts like interestingness and surprise well enough to serve as search queries — he called this "totally bunkers" (i.e., astonishing). - **Persona inference test** (Shipper's prompt): the model hedged ("difficult to draw concrete conclusions") but correctly identified broad interests (literature, history/politics, philosophy/economics, psychology/cognitive science). Shipper called it "right but... not gonna win any profile." - **Disagreement test** (Shipper): the model identified **Johann Most vs. Emma Goldman** disagreeing on political violence — which Johnson validated as "a pretty astonishing answer," noting (from his own knowledge) that the dispute culminated in Goldman horsewhipping Most onstage. - **Mediation follow-up**: the model suggested **Peter Kropotkin** as a mediator between Goldman and Most; Johnson confirmed it was "exactly the right answer." ### Notebook Guide (new feature) - Generates cross-source summaries, FAQs, timelines, briefing docs, and **casts of characters** from large corpora. Johnson praised the timeline generation especially: "creating a timeline is like the most laborious thing." - Previewed at Google I/O in Sundar Pichai's keynote (per Johnson). ### New formats - **Google Slides support and "true image understanding"**, including handwriting analysis — announced as new that day. --- ## Reasoning About Workflow and AI Collaboration ### Two modes of saving material (Johnson) 1. **Project-driven saving**: notes for a specific book (e.g., *The Infernal Machine*'s themes of anarchism, forensic science, the FBI, dynamite) — NotebookLM is already "incredibly good" at finding passages for defined themes. 2. **Speculative saving**: saving things he doesn't understand or that lack a slot — "when I read something and I'm like that's provocative but I don't really get it, I often try and save that." Whether software can learn his general sensibility: he said two years ago he'd have said "absolutely not," but now "I think it probably will be able to do that." ### Agent-mode prediction (Johnson) - "Clearly that's in our future": software autonomously scouring the internet for material matching a user's sensibility. ### The Apollo 1 exploration (collaborative live demo) - Scenario: ~200,000 words of NASA oral history transcripts (John Glenn, Gene Kranz, Neil Armstrong, Frank Borman, etc.), unrelated to Apollo 1 directly — Johnson described finding Apollo 1 material as finding a "shoe... not a needle" in a haystack. - The model surfaced **pure oxygen environments** as the central scientific idea behind the Apollo 1 fire. - Johnson noted a **fortuitous connection** to his own book *The Invention of Air* (about Joseph Priestley and oxygen), and was careful to qualify: "notebook doesn't know this... it's just fortuitous on some level," though he speculated training data might know he wrote about oxygen. - Cross-notebook query surfaced **Auguste Piccard**'s sealed gondola and an early pure-oxygen environment quote; Shipper reacted: "that's the opening to the book or the documentary." - **"Suggest related ideas"** feature linked the Piccard note to Kranz ("we had become very complacent about working in a pure oxygen environment"), Gene Lunny on redundancy, and atmospheric-control incidents. - Johnson admitted a **current limitation**: notes and sources are distinct — you cannot yet query both simultaneously (there is a workaround: paste the note into the prompt). He also discovered live that "Suggest related ideas" lacked citations: "I got a note to the team here." - The demo ended with the model generating a documentary opening script connecting Piccard to Apollo 1; both participants praised the result. ### Intelligence as "a full chorus" (Shipper's framing) - Shipper argued the workflow fuses multiple intelligences: original authors, Johnson's curation, the astronauts' expertise, and Gemini/NotebookLM synthesizing. He extended his earlier "duet between human and computer" metaphor: "this is like a full chorus." --- ## Unresolved Tensions and Qualifications - **Groundedness vs. openness**: Johnson repeatedly hit the model's refusal to speculate beyond sources; the openness "slider" is aspirational, not shipped. - **Notes vs. sources separation**: acknowledged product gap. - **Citations coverage**: at least one feature ("Suggest related ideas") lacked inline citations at launch. - **Fortuitous vs. trained knowledge**: Johnson left open whether the oxygen connection reflected training data or chance. - **Two user camps** (organizers vs. chaos-embracers): product doesn't yet fully serve both, per Johnson's own admission. - Johnson's repeated surprise ("I'm learning about the product as we use it here") shows he presented some capabilities tentatively, on launch day. --- ## Closing Notes - Johnson promoted *The Infernal Machine* ("kind of a thriller in a strange way"), his Twitter handle (@stevenberlinjohnson, rendered in transcript as "Stephen B Johnson"), and his Substack newsletter *Adjacent Possible*. # Speaker Attribution & Provenance Record **Video:** Is NotebookLM—Google's Research Assistant—the Ultimate Tool for Thought? - Ep.22 with Steven Johnson **Video ID:** `01a0f15b-0d23-7d8c-85d9-5c11230b9d2a` ## Speakers & Roles ### Dan Shipper — Host / Creator - Identified as the show host ("AI & I" podcast, Ep. 22); explicitly named in closing promotional segment ("Dan Shipper as the captain of the spaceship") and by guest: "Thanks Dan." - Conducts interview, asks questions, participates in live demo. ### Steven Johnson — Guest - Introduced by host as: best-selling author (*How We Got to Now*, *Where Good Ideas Come From*, *The Invention of Air*, *Emergence*, and "13 other books"), author of new book *The Infernal Machine*, and **Editorial Director of NotebookLM and Google Labs**. - Demonstrates NotebookLM live; announces news: rollout to **over 200 countries** and new features (inline citations, Google Slides support, image understanding, Notebook Guide, 50 sources / 500,000 words per source limits). - Self-identifies online presence: **@StephenBJohnson on Twitter**, newsletter "Adjacent Possible" on Substack. ### AI-generated voice — Promotional outro speaker - Closing segment is a promotional voiceover urging likes/subscriptions; **flagged as promotional** ("you absolutely positively have to smash that like button and subscribe to AI and I"). ## Referenced Sources & Third-Party Claims - **NASA oral history project** — interview transcripts (John Glenn, Gene Kranz, Frank Borman, Neil Armstrong, others; ~200,000 words, ~7 interviews) loaded into demo notebook. - **Johnson's personal reading notes** — ~7,000 quotes / ~2 million words since 1999, from purchased books, clipped via Kindle. - **Readwise** — referenced as source of imported notes. - Historical tools discussed: **HyperCard** (Apple, 1987), **DevonThink**, **GPT-3**, **Gemini**. - Historical figures cited via the notebook demo: Joseph Priestley, Scheele, Auguste Picard, Peter Kropotkin, Johann Most, Emma Goldman. - **Copyright/training claim (third-party claim by guest):** Johnson states uploaded quotes are used only in the model's context window, **not used for training**, per NotebookLM design — recorded as speaker's claim, not independently verified. ## Promotional Segments - **Closing like/subscribe outro** — promotional, AI-voiced. - **Product announcement content** — the episode functions partly as a launch-day demo of NotebookLM new features; treated as informational with promotional character, per guest's editorial-director role. ## Availability & Limits - No curated metadata supplied; no comment availability information present. - Live demo includes admitted product gaps: notes and sources cannot be queried simultaneously; "Suggest related ideas" lacked citations ("I got a note to the team"). I want to find a scientific or technological idea that is Central to the Apollo one fire here's the crazy thing D maybe there's kind of a version of the Apollo one story that connects to that history of oxygen that I've already written about now we're getting exciting because we can take this and go back to your read readwise notes and try to pull some sources right oh that's really cool it brought up a card this Source provides an example of an early enclosed environment that relied on a pure oxygen supply similar to the Apollo 1 spacecraft that's so cool that's the opening Stephen welcome to the show thanks very much s it's great to be here I honestly I'm so excited to have you you're such a great writer I love your writing and you're also kind of in this like interesting intersection where you're you're doing incredible writing and you're also working at Google uh so for people who don't know I feel like I'm jumping the gun a little bit but for people who don't know you are uh the best selling author of how we got to now and where good ideas come from and a bunch of other books I think 13 other books um you just wrote a new book which I have right here called The Infernal machine and if that wasn't enough you are also uh the editorial director of notebook LM and Google Labs which is notebook LM is Google's AI research product and I'm so excited to have you here oh this is really great um you know we we actually have some kind of news to break as well so uh uh it's going to be really fun yeah so by the time this podcast comes out a new version of notebook LM will be out and we will be on the show today we will be demoing all those new features uh we'll talk about how you used it to write your last book and then like talk about how we can use a new features to maybe write a new book or find a new book concept for you um so I'm curious before we get started talk to us a little bit about what notebook LM is yeah it's a tool that that we've been developing for about the the last two years um at at Google Labs which is this wonderful new division inside of Google um that is really designed to to build a kind of your ideal research and and writing um software knowing that you have from the very beginning a language model at the core of the product right so like really began this you know in the age of large language models um knowing that there was going to be a possibility to build like entirely new kinds of software you know it wasn't just about like adding some AI to you know a word processor adding some AI to a photo editor this is about like what can you build that's like a genuinely new kind of surface to work with and this had been a like that that we can talk about a little bit but like the the obsession in my life with using software to help me with with with organizing my ideas organizing things that I read and and turning those ultimately into books or into TV shows or whatever uh it's just been a Obsession of mine for like 30 years or longer even really um and and so Google's got very interested in this process of co-creating um with people so not just kind of sitting around and building products and then handing them over to writers or musicians but actually having a writer or musician in the room from the from the beginning with the project um it's a big part of the labs ethos in particular and so they they called me up one day you know two years ago and they were like hey would you be interested in maybe helping us build this thing you've always wanted and uh that was an easy yes um and so yeah we we we kind of built a very early prototype and um I think because i' in part because the the technology was suddenly you know available with language models um uh and because I've been sitting on these ideas for so long we were able to build you know a pretty quick prototype and that got a bunch of Interest internally and we launched notebook LM in the US um uh in December of last year and today we are uh announcing that we are rolling out to over 200 countries around the world um so we're really excited about that that's amazing um and I I just want to go back like the thing that like really sparked my attention at the beginning of this is like sort of this obsession with um organizing your ideas and and and and using those to to produce produce work CU like that's I feel that same thing I I like I'm a nerd for that stuff and I just want to understand like tell us about some of those what the what those what that obsession is or what some of those ideas are like what are those things you've always wanted that are kind of starting to come through here yeah I mean it actually dates back I'm gonna really date myself here um which is that that one of the things that changed my life truly changed my life was when I was a sophomore in college in the fall of 1987 Apple released something called hypercard uh which was this like crazy app I always say it was a little bit like The Velvet Underground of of of software like it never really had a hit but it like influenced all these other people and uh it it was basically a kind of prototype almost web like hypertext kind of system where you could organize information pretty much any way you wanted and kind of make links between it and I just got obsessed with the idea that I could use this tool as as a place to kind of keep all my notes from from my classes and I kind of built this little application that I called curriculum that was kind of a way of like taking notes for classes and I spent way more time like building the tool than actually like using it to take notes for classes but I and I kind of stopped going to the classes for a while because I just wanted to build the tool that it was one of those things but it just gave me like a taste it wasn't ready you know in any way for kind of prime time use but I got a sense of the possibility and then obviously when the the web came along I was I kind of jumped on that maybe a little bit earlier than some people because I lived briefly in the world of hypercard an early hypertext um and then in the about 20 years ago there was a there's a program I wrote about a lot actually wonderful program way ahead of its time called Devon think and that was it's still around actually it's a really cool uh application and it it enabled me to uh keep all these quotes from books that I'd read I would originally kind of type them in and then when the Kindle came out I could you know get the quotes digitally and you could kind of make connections between quotes or you could type something and say what quotes in my research Library are related to this we had this kind of associative early kind of semantic search um and I use that quite a bit um on a lot of my books like the ghost map use that and and I I would have these moments where I the software would recommend a quote that I had forgotten from an earlier book it would make a new connection in my mind that I hadn't thought of before and I thought this almost feels like a partnership with the software like I'm kind of I'm curating these quotes So it's me and I'm and I'm I know how to turn them into a chapter or a paragraph in a book that's my intelligence but the connection was really made by the software that seems kind of new and tantalizing and weird but also maybe very powerful and so that was another taste that um kind of got me along that way and then you know when I first started experiencing what was possible with language models starting with gpt3 um uh you know before I came to Google I I thought oh wait now it's all really going to be possible like all this stuff is it's going to get very serious and very real um so that's that's the prehistory and I'm curious like um like why do you think that's every like nerd's dream is like to have this sort of like interconnected note system that you can use to like make stuff like why is that so appealing yeah yeah well and and and they're different you know they're diff this is true on so many levels but they're different kinds of nerds that's true like I do I don't the thing I've always felt like this is generally this is truly the way I organize my like email as well which is to say I spend zero time organizing my email like I am not a my principle has always been like create one place where you dump everything and then use you know Smart Tools like search and and now all these language models um to to find what you need don't spend any time organizing anything just just throw it all in one place and and focus on having the ideas and stuff like that and so um and I think notebook I mean probably to a fault notbook Alm has been kind of designed a little bit with that principle like you can't you can't like tag your notes for instance and you know we probably should have people do like to tag things and and I just I'm always like I'm not going to spend a second tagging anything because I want the software to understand what what categories I don't want to get I don't want to um put things to in advance into buckets because I want it to be an open-ended connective system where I can make new associations or or create new kind of clusters on the Fly and if I spend all this time tagging I'm going to limit the connections that I can do so so uh so there so I'm on the side of you know emergent chaos right don't organize it and just let things bubble up and figure out tools that will let that bubbling up happen um but then there's a whole other set of folks that really like to organize it and systematize it and have it all in these categories and things like that and and so hopefully we can ultimately make notebook LM play well with both those groups I think it's certainly within our power yeah it's sort of it's the top down versus bottom up folks um I'm definitely in the bottom up camp with you so I'm I'm excited to see notebook let's um let's let's roll into that so like give us a little bit of a tour of notebook tell us about because we're going to talk about how used it um for for your your latest book so tell us a little bit about how notebook works and then how you Ed it for for the book that you wrote yeah I'll just give you the kind of Basics um uh the idea is um EV everything inside of notebook LM is grounded in the the documents you you provide so we we may open this up a little bit over time I think it's probably a logical thing to do but you unless you provide notebook with with what we call sources um kind of underlying the the the documents that are the source of Truth for your project um the things that you're working on and it could be everything from your journals to you know work documents or to you know research materials or quotes from books that you've read um you begin each project by opening up a notebook and and uploading sources um and at that point once they're uploaded the model in a sense kind of becomes an expert in the you've shared um now you know we this has become increasingly common it was kind of a radical idea when we were first twing around with it two years ago um but you know the idea of having documents you know attached to a model like gemini or or chbt has become increasing the common but our use is like you're always working with documents and the whole interface is designed to like let you um basically load a lot of different documents move back and forth between those documents potentially read those documents while you're working um and not get into that kind of flow that so many people I think are finding these days where they have like 12 tabs open and they're like grabbing some text from one Tab and then pasting it into the chatbot and another thing and then they're getting the output and they're saving it in another document like we want to have a single integrated surface where you can do all that work um so so in a sense designed to not interrupt your Flow State like if you're thinking or writing or reading you should just have one place where you can do that and not be like wait what was the tab that I had open where I had that quote that I wanted to use and that other think so so that's the the kind of the underlying model um and the if if you if those of you are are watching this um I have open here a notebook that uh this is this is kind of cool this is my crazy notebook this is this is where I have um all of the quotes that I have collected over the years um for books dating back to something like 1999 I think it goes back to this far about 7,000 quotes um oh my God that I've collected so it's really like my reading history um like the things that were important to my books in the past and uh and so uh they're they're lined up here as a bunch of different sources this is this is kind of left over from the fact that um we used to have a kind of a cap on how long the sources could be um so now you can have this this is just changed a couple of weeks ago in each notebook you can have up to 50 sources and each Source can be up to um 500,000 words um so you can effectively be talking with 25 million words um in a single notebook which is just kind of mind-blowing so the these quotes are like um they are uh here I'll let just open up one of them um they are uh I think there's something like two million words total two million 7,000 quotes 2 million words something like that and this is crazy like like so okay so these are all of the quotes from all of the books that you've read since 1999 well yeah I mean not all of the books but significant what yeah significant amount and so this is very valuable like can you just like send me a stripe link like I'll how much how much do you want do you want for this yeah yeah and and by the way I should point out one thing that's really important here so these are these are quotes these are all books that I've purchased right and these are quotes that I've you know clipped increasingly using the Kindle um using the kind of like limits that are built into Kindles and the amount that you can quote and use and we are not it's really important to stress this and I this is important for me as an author we're not training the model on this information so this information we're just loading the information from these quotes into the the context window of the model the kind of short-term memory of the model and we're using that to answer questions or be intelligent about it um so there's no chance that this information which is under copyright is going to be used to train the model or be shown to anybody else um and so you you have this freedom to work with material if you if you have the right to use it under copyright you can use it inside of Notebook on we spend a lot of time ensuring that that works so yeah so this is this incredible this is just one of these I'm just scrolling through this for those of you are listening it's just like an endless list of quotes and I'm just scratching the surface and each source that we put in we create a source guide that summarizes the source now this is normally extremely useful because generally a source is on a single topic and you can get a kind of highle thing it's crazy when you you give it like whatever this is probably like 800 quotes in this one source on all these different topics and so it has to you know it creates a summary like this Source explores the intersection of scientific advancement societal impact and ethical considerations and how you know it's doing a very good job of trying to make some kind of pattern out of all this but uh Source guides for just quotes are not quite as useful so now at this point basically I can I can ask um any question and so I actually I pre-loaded a question here I'm going to close this Source I pre-loaded a question um if we view the chat and the question will be asked of of all of the of all of these sources together yes I can you'll note that they're checked off here so you can always tell this is a really subtle thing but it's really important about it it'll say down at the bottom at the chat box it'll say 15 sources so those that means you are currently talking to all 15 of your sources here if I actually deselect this one for some reason now I'm talking to 14 sources and so you sometimes have moments where you're like actually the information I want is only in this one document I don't want to ignore all the other information so you can actually shift it's like you're able to shift the focus of the model to various different things really really easily so so I asked this question what are the most interesting facts about ant colonies here um mention authors and specific books because I actually wrote a book a million years ago called emergence we talked about you know the emerging approach to these things and there was a big riff about ant colonies in that book um so uh and and the model is smart enough to understand this concept of like interestingness too and and surprise like I often say like what's the most surprising idea here because you think about that as an author and the idea that that can be like effectively a search query is just totally bunkers but so I mean so I'll just read this for people who are listening so it comes back with interesting facts about ant colonies ants use pheromones to communicate in various messages such as danger food location and nestmate recognition this complex chemical Communication System allows ant colonies to function as a single unit or superorganism yes fantastic that is a great answer and now this is new by the way so this is this is a brand new feature rolling out today we're incredibly excited about it we now have these inline citations and so that shows you exactly the quote from the my reading notes that it used to generate this answer and so you can just roll over them and you can see where the model came up with this this one is from orbit Wiener that's pretty interesting um and you can see their their uh citations all over the place and what's even cooler is you can um although a little bit in a way less useful for this project we'll show it in another thing but I can always click on those and it takes me exactly to the point in my documents where the original quote came from so you have this ability to kind of kind of get ask the model to help you get the lay of the land like what's in here I'm interested in this topic what's there and then because the sources are integrated into your notebook itself you can then Dive Right In and start reading um and so you can go through all these things and uh and basically then you and we also suggest questions based on what you just asked so there's always you know there's always something to just click on um can I ask sources yes go right ahead um and and you tell me like whether or not this this is a good question to ask it but one of the things I'm I'm interested just like looking at this and knowing how many things are in here that that you've like kind of collected over the years is like what are the types of things that Stephen Johnson is likely to save like what are the patterns in texts or books that are likely to make you want to put them in there do you think it would be good at that would notebook be good at finding those things yeah it's a great question so so there are two different versions of of why I save things um the first is pretty easy and yes to this particular use case notebook will be great at this um which is I have a very specific project in mind and I'm in the middle of a book and I'm writing you know an infernal machine the new book you know there are a bunch of themes you know you've read some of it I think it's a you know it has the history of anarchist is M the history of forensic science the history of um the birth of the FBI um you know kind of threaded the the invention of dynamite all kind of woven together in this single plot so when I'm in research mode for that it's like you know I could very easily tell notebook LM you know these are the key themes of the book um help me find passages that are relevant to those themes and and you know a little later in this conversation I'll show you that in in practice um that's very easy to do and it's it's just incredibly good at that um the trickier question is like I often save things without knowing where they're going to go you know there's not there's not a specific project that they're attached to um they're often things that I I often save things that I don't understand like you know when I read something I understand I'm like well I already know this on some level so I don't need to save it um whereas when I read something and I'm like that doesn't make that's provocative but I don't really get it I often try and save that and or there's you get a little glimmer I've written enough books by this point I worked on enough projects that you get a little glimmer of like that could be something um and and so you save those things even though they don't have a slot to go in or don't have a chapter to go in or even a book to go in yet and and that's the question like over time will software like notebook LM get to know my general sensibility enough um to be able to detect those things uh I I would have said you know two years ago absolutely not and now I think it probably will be able to do that um and then you start really getting into the the agent mode where you're like please go scour the internet for find for things that could be useful for me and and I clearly that's in our future I think yeah that's I guess that's what I'm asking is like do you think we could ask notebook LM what your sensibility is based on these um based on these sources and then have it return something that might tell us about something about the way your brain works that might be surprising I mean I don't know yeah let's try I'm Steph Johnson the author who maybe we shouldn't say who you are just so that it doesn't it doesn't have that to to go off yeah yeah yeah that's right that's right because it's clearly I'm so uh well represented in the training data I'm sure it knows exactly 13 books will do that okay so um these sources are my reading notes notes from books I've read over the last 20 years please describe what would you say my interest and Sensibility and general sensibility and Sensibility um um what what do I care about most these quotes yeah oh a sorry um uh based on these quotes what do I care about about most and what can you tell about me and what can you it's going to get very intimate D I know I'm excited for this we're going right for it yeah I mean this is so much of what our existence is like now with these models to talk about emergence but you're just like what will it do in this situation like no one ever sat down with Microsoft Word and was like what will it do if I that's the whole PR of this show Okay Okay so this is interesting it you know it does a little Heming and Hong so it says it is difficult to draw concrete conclusions about your interest and Sensibility solely from the provided Source material however the content suggests an interest in a diverse range of topics including literature you includeed reading notes from novels like authors just like Jonathan Franzen history and politics philosophy and economics lots of lots of citations psychology and cognitive science yeah I mean it's right but it's not gonna win any profile doesn't want to go to too far I wonder if like if you said if we did the same prompt but like tell it not to hem and ha and and assume that if I saved it it's because it's interesting to me um like you know give it give it a little extra juice um I wonder if it it does have some memory I'm just like can you please try to speculate on my personality based on my decisions to clip these quotes I know you don't want to but but I'm asking you nicely I would also say okay sorry it's so funny to like to just like learn how to Kajol these things but but you know the truth is this is harder to do with notebook because for instance you know if you try and ask notebook about something that is not in these sources it will decline to answer and so yeah so it's just yeah it's not going to do it it's funny like we definitely like we we have tried to build this model and I think eventually we're gonna have an approach where there's like a slider of sorts where you can choose different different levels of openness and closeness but we really started with the idea like let's build a model that is fully grounded and then we'll really just stick to the facts and so what it's straining against here is that the the sources don't have any psychological explanation of who Stephen Johnson is you know and that's a tension like I and I sometimes definitely use it and I'm like no okay I would like you to be a little bit more open-ended but I think in the research mode we're airing on the side of groundedness um more than we are on the open-ended side I have another one and you tell me whether you think it' be good good for this because it's it's less about you and just more about the sources and that's like what are the two sources that I've saved that most disagree with each other and what do they disagree about okay that'll be interesting because it's so um there's so many right so can it um but let's try I it would be interesting like of all these quotes what are the two let's say authors um authors who most disagree with each other whose position i s are the most opposed this is kind of weird grammar but yeah um figure it out it'll probably understand it's just so it's so much D I'd be surprised it' be interested to see what it says but it may have an OD like hey dude there's 7,000 quotes here like I can't possibly okay here we go here we go that that's interesting well it's something from um uh it's from the recent stuff from infernal machine so these are my notes this is from so this is um Johan Mo and Emma Goldman um disagreeing about the use of violence this is interesting because they didn't disagree at the beginning um but Goldman um it gets in this kind of like major fight with him so it's not a uh yeah she ends up okay here here's an argument for why this is a good answer they had a philosophical disagreement about the use of violence in politics that got so intense and most got up in New York City and gave a speech uh and uh Goldman jumped on stage and uh attacked him with a horse whip so so actually this is actually a pretty astonishing answer because like it really like it really found I this the only probably May arguably the only place in the notes where two figures who were mentioned in the quotes physically attacked one another so okay well done I have I have one more followup um and then and then I'd love to move I love to move on but so the the followup is um something like uh of the other sources in this you know in this Corpus um who is the author or or what is the set of ideas that these two should have come in contact with that would have helped to mediate their dispute okay um it'd be interesting to see it's like um uh in I'm just going to just make sure it keeps the dispute in its mind so in the dispute between Goldman and most over violence which other author in these quotes would have been most helpful in kind of resolving their dispute yeah resolving and mediating their dispute resolving and mediating their dispute and why and why you're pushing the boundaries of this I love it we shall see yeah yeah yeah that's that's exact that's what I would have said that's so funny so who Peter Peter kotkin is the um a Anarchist philosopher who um Goldman was heavily inspired by um who had a kind of uh Middle Ground position on the use of violence um and was yeah I mean like that is exactly exactly the right answer as well okay good good well done well done I love it I love it um this is very cool I would love to get into I know we have um you know another another segment which is what I really love doing um as part of these shows is to go on a little exploration together and use these tools to do something new that neither of us kind of know where it's going and so I think what you have prepared is um another instance of notebook with a bunch of um a bunch of pre-loaded information uh documents that we've never really gone through um and we're going to use that information to help us find what could be a New Concept for maybe a book or a documentary can you like can you sort of set the scene for us here what are we looking at yeah okay so this is a new uh notebook that I've created um one of the things that uh notebook LM is incredibly good with is um which is useful across a lot of different domains is is interview transcripts so you know it so many workflows involve people like if you're a reporter if you're a documentary filmmaker or if you're a you know user researcher or you know Market researcher you do all these interviews and you're trying to like discern what the patterns are figure what the lessons are and you you dump you know a huge number of words of interviews it's very disorganized and notebook element is just amazing at at at going through those interviews and finding the relevant quotes and things like that so so this is an example where the the scenario is I'm actually I have been thinking about this legitimately um which is there's a great oral history project that NASA um created uh on the history of the Apollo missions and and others um there are like thousands of interviews um and I've gone in I've taken um about oh seven of them um from people like John Glenn and and Jean CR and you know some famous people and it's I think it's about 200,000 words worth of transcripts um that are in this particular notebook and I'll show you one other thing this is also new as of today we're very excited about it you know up until recently we we've supported Google Docs um PDFs text files and so on and now we have Google slides for the first time and we have we have True Image understanding um built into notebook as well so you can have slides in there as well and in a sense kind of talk to your images and do queries and it will um understand the the images so so it's it's amazing it will do handwriting analysis and things like that it's it's it's pretty powerful so we're really excited about that's that's a brand new feature as well so uh in this what I was thinking we would we could walk through is this idea of like I I'm thinking about the project um that uh might involve the history of the tragic Apollo one fire that killed three astronauts in 1967 and um thinking about that maybe is like could you make a documentary about that what would that look like and and and the kind of the question is like I've dumped a bunch of sources here what do I have that I could use to kind of build the beginnings of a script maybe for for a documentary um and I want to show you one other new thing um that is related to this in a sense this this process of like I have a lot of information and I need to get my bearings just like what is in what are in these sources you know it's like this is not a situation like my reading notes where I've already read it it's like somebody gives you a bunch of files you're trying to make of it or you've downloaded all this stuff you don't know you haven't listened to the interviews yet and so we've added this this is a really cool thing we previewed this at at iOS um in su's keynote a couple of weeks ago um it's this new feature called notebook guide and notebook guide basically gives you a summary across all your sources in the notebook um gives you some suggested questions that are kind of higher level um how do I really understand everything here but we also have these templates that um that are kind of pre created FAQ study guide table of contents timeline and briefing Dock and so those are ways to get kind of like the big picture view of what's in the documents and they take a little bit of time to generate so I pre-loaded a couple of them um so they're back here um you by the way I forgot to mention this before you can save anything as a note in this kind of noteboard area so you have this area can be filled with notes you can write your own notes um if the model says something interesting you can pin it to this not board area so you're able to kind of capture this stuff as you're having conversations as you're reading you can capture everything to this noteboard I'll show you a little bit more about that as we go on but here's here's the FAQ it generated based on these sources so went through you know 200,000 words worth of material and decided you know figured out okay here are some good questions what motivated individuals to join NASA what kind of rigorous training and selection processes did aspiring astronauts endure how did NASA manage the immense technical challenges and risks and there answers for all of these um and the other thing that I love to do because this is something as a writer you're constantly dealing with is like it'll create timelines which is just Inc useful like creating a timeline is like the most laborious thing but it's really something you need if you're writing a book like you need to know like what is the sequence and it just will go through all these disparate transcripts and pull out this is not based on its like training data this is based on like the information that's in all these transcripts and and it goes through and it it breaks it up into like the early pren NASA era the Mercury program The Gemini program the Apollo program their bullet points you can see for each of these um uh that break it down um so and then there we also have it do a cast of characters whoa so it pulls out all the people who are mentioned who are important gives them a brief description I mean it's just like it's so useful to to understand what's in the material so that's a St now I pre-wrote um those are but this is the point here is that these transcripts are not at all focused on the Apollo one fire so the you know it's not a needle and a Hast stack but it's like um there's a giant Hast stack of NASA related information in this notebook and then there's you know something I don't know like something the size of a shoe not a needle about the Apollo one fire but it's spread out throughout all the documents and so what I'm trying to do in putting together ideas for this documentary is figure out what's there that's relevant to this particular topic and so I wrote I pre-wrote this prompt and here you know again I'm trying to give it a little bit of context about the kinds of things I'm interested in so I'm the author and TV Creator Stephen Johnson I'm interested in making a TV documentary about the Apollo one fire in the multidisiplinary style of my books and shows like the ghost map and how we got to now with a focus on surprising scientific explanations and compelling narratives give me a reader Guide to the most important sections of these interviews that I should read in getting started with this project and actually I think it's still in the chat actually if I bring it up yeah so this is this is the reader guide that it created and it just goes through interview by interview and pulls out the most relevant sections um and so it it talks about the craft interview and explains who he is and then he talks about the Apollo one fire as a turning point in the lunar program and then it moves on to this Yardley guy and then Frank Borman um and so so let's say I'm interested in in the Borman quote uh so I think it's this one uh um let me see yeah yeah okay so I click on that so there's a citation next to this quote and I can click on that citation it takes me straight to this passage and the passage is talking about the the trouble they were having the spacecraft before the fire um and so let's say I'm thinking this is an interesting quote I'm working on the documentary um I like that and so I can just select this quote and then I can say add to note and so it'll take that quote and just add it right there to my noteboard so I've got this saved response from this interview so then I can kind of go through I can go back to the chat and I can see if there's okay here's a quote from Neil Armstrong um and he's talking about uh let's see I can flip through these one ones um I think the last one's probably the best um yeah okay so he's talking about the Apollo one fire some very traumatic times I suppose you're much more likely to accept the loss of a friend in flight but it really hurt to lose them in a ground test so I'm taking that quote that's doubly doubly traumatic so I could also save that I can add to another note so I'm kind of starting to collect ideas here that could be useful um and then I can obviously I can ask anything else do you want to anything you want to I have a I have a lot of questions I'm full of questions um so I guess one of the things that that strikes me a lot about your books is um you find like a little like a pivotal moment where everything sort of like changed and then you sort of Trace how different technological innovations or different ideas like led to that moment and created it and I'm wondering if if there's a way for us to find some of those in here in ways that like we might not know already so it's like what are the sort of key technical ideas or key underlying innovations that or lack of innovations that led to one of the pivotal moments in this narrative I don't know how how you would frame that exactly but that's sort of what I'm getting at yeah no I love that okay so let me show you one one little kind of low te um notebook LM hack that I often have a written note with prompts because sometimes you're reusing your prompts right so so inside the notebook I'll have just a prompt note and so for instance like I I actually want to continue this idea of you know I'm interested in the Apollo one fire I don't want to have to rewrite that so you know we can just take that and then create a new prompt um with that kind of introduction and then say um I I want to find a scientific idea or scientific or technological idea um that is Central to the Apollo one fire that I could develop into a major set piece for this project what would you recommend based on these you don't really have to say based on these sources but I sometimes like do that can we can we add a little like a little bit more like y ideally the idea is like seemingly unrelated and surprising but um but in hindsight inevitably led to the to the fire it's it's yes it's G It's Tricky again because it has this it's limited to the sources this is a you know this is but let's try it like the you you modify in a way that you think will work best um yeah yeah ideally the scientific concept will be surpris Ing and involve an unusual connection that the viewer might not have originally thought of okay so then I'm just going to copy and paste that so we have it we could reuse it too um and let us see what it comes up with it came back with a note called pure oxygen environments and it says the use of a pure oxygen environment in the Apollo Command Module while seemingly counterintuitive played a significant role in the Apollo fire the unusual Choice stemmed from a desire for Simplicity and weight reduction in the early spacecraft designs um this is this is what made it so flammable um and so here's the crazy thing Dan when I was thinking about this a little while ago just kind of as an early idea um independent I mean I was kind of searching with notebook but I I saw this stuff about pure oxygen and I notebook doesn't know this so this is this is just fortuitous in some level but I wrote a book called The Invention of air that was about the discovery of oxygen um Joseph Priestley uh the 18th century chist who kind of isolated and and and isolated and kind of name didn't quite name but um first identified oxygen and I thought oh maybe there's kind of a version of the Apollo one story that connects to that history of oxygen that I've already written about and that could somehow like be set up here so like the fact that it like folded that out now it you know I suppose uh maybe there's some training data that it knows that I've written about oxygen I mean well now we're get now we're getting exciting because we can take this and go back to your read readwise notes and try to pull some sources right do you have op yeah I could I could yeah let's see um uh so that would be be interesting I can't remember what's in there from that book because that was a long time ago but it probably has some stuff in there um let's try it we'll go back over to that other notebook and we'll say I'm writing about the use of a pure oxygen environment that caused the Apollo one fire what um sources in these what um what quotes in these sources could be relevant um to the use of oxygen and the his and its it's history explain how I could use those ideas should we ask it to be surprising or you think we should just do straight up first let's just let's let's not over tax it D it's it's a very sensitive model I'm not going easy on it it can handle it yeah and this this does raise an interesting question like I have to jump to the other notebook um to do this and there you know certainly there's this idea that perhaps you would want to have okay well let's start it right away so it just goes straight to Joseph Priestley who I just mentioned um uh and and and sheal who also discovered oxygen independently um oh that's really cool it brought up a card yeah this is great um this is another idea I actually never wrote about um I think we're building something good here Dan I love this are are you gonna want are you gonna want a piece of this project or 10% you know so so this guy P card I wrote about this because um I wrote about the um discovery of the ozone layer because I wrote about this the guy who invented the freeon CFCs that caused the hole in the ozone layer and so there's this Explorer um August peard who went up to the kind of Stratosphere for the first time um and so like this this product just blows me away so so so many times so look at what it says here so it it reminds me of this story which I thought was fascinating but have never used and it briefly describes it I've got a link back to the original you know citation so I can go and read more about it but this is what notebook says this Source provides an example of an early enclosed environment that relied on a pure oxygen supply similar to the Apollo one spacecraft and notes the importance of respiration in such an environment oh my God and it gives this quote as the professor remarked when you face the possibility of shutting two men up in an airtight space of such small Dimensions you must study very carefully the problem of their respiration that's so cool that's the opening to the book or the documentary or whatever that's amazing that's so cool I'm actually going to just um go and copy that into the other notebook I Am shifting tabs here but we gotta we got to add that so I'll close the chat briefly and so here I'm just like creating a new note that it's like a written note so I can paste that in there um okay do you have another one well so now we now we've got this this sort of August Picard um yeah idea and I'm curious if there are any other like parallels between the two stories so we've got the like pure the the the oxygen and the sort of sealed environment do you think we could like search through you know given this as context this note that that you just put in there do you think we could search through the sources to see if there are other parallels um in other parallels to August card in the in in the NASA transcripts yeah yeah so this is a one thing that's actually annoying to me about notebook Lum right now which is the um the contents of your notes and the contents of your sources are kind of distinct so I can this this is you know a key feature that people actually most notebook users I think probably don't fully understand but if I select all my notes I'm now effectively talking I focused the model you see down at the bottom it says six notes I'm now focusing the model on the notes and not on my sources yeah and so I can do things I can summarize I can suggest related ideas that's what I could do actually I could actually this this will work but what we really want to be able to do we just haven't built yet is have the option of talking to all of your notes and all of your sources at the same time it doesn't quite work that way but there is a hack that will work actually so what we're going to do is couldn't we just P the note into the prompt yes we could but I have an even better version okay um we have a dedicated um prompt that we've built um called Suggest related ideas and so I've selected the note about August peard right or ugust I don't know how to pronounce it um and and now based on that note I'm going to click on suggest related ideas and basically what it is saying is take this note and find things in my sources that are related to this note um and you know eventually you can imagine where this is going you could be writing a note and be in the middle of a paragraph and you're just like okay I just wrote this paragraph tell me other things are like that and it's just an extension of your memory like that's obviously where we're headed um but right now you have to kind of select the note okay so here we go we suggest related ideas um actually haven't even tried this one I wonder if it comes in with citations um this is kind of an older feature that I wonder if we've updated for citations I'm learning about the product as we we use it here we're doing it live folks yeah yeah yeah yeah this is a beauty of launch day okay yeah did I'm sure this is gonna be a great answer but it didn't have citations because of that I got a note to the team here um okay so it says um the original passage focuses on his Innovative use of a sealed uh Gondola um it it makes a connection to The Perils of a pure oxygen environment which is great but it actually quotes from genan CR so it gives it gives you a quote from Jee CR the famous like flight director we had become very complacent about working in a pure oxygen environment we all knew this was dangerous so that's you know gonna be helpful um then it talks about human factors in spacecraft design um and says of Jonathan yardley's oral history um and he gives a quote and then it says this quote while seemingly humorous reveals the initial crude understanding of the challenges of human space fight um Yardley also discusses the challenges of atmospheric control which is really important for Picard's flight um and he highlights an incident where a test engineer passed out due to unexpected nitrogen buildup and then uh he talks about the notebook brings up the importance of redundancy as another idea um and It quotes Gene Loney talking about redundancy which was you know really important in the Apollo fire that they didn't have enough redund you built into the system um so you see what it's doing here is it it's basically been told the prompt is basically saying find three related ideas um and you know explain what they are and explain how they connect to the original thing you've given it and so this is like that it was such a like high level form of intelligence of like making those conceptual leaps um yeah and again it gets back to what we were talking about at the beginning like there's this is this is is a fusion of like so many different um separate intelligences coming together here so you have the original sources whoever wrote about you know peard that I quoted from um you know that is an author somewhere who's come up with this idea or written about this person or biographer um there's Stephen who has curated these quotes and put together this idea of the NASA project and you know gathered all these transcripts they the individual astronauts or flight directors who are talking and their expertise whatever and then in the middle of it all there's you know Gemini Pro and notebook LM synthesizing all these things and making these connections possible um so it's like I used to talk about like a duet between you know human in computer but this is like a full chorus right it's so it's so extraordinary so let's see we're gonna pin so so let me show you this I haven't showed this before this is a key part of it so this is way you save interesting responses you just pin them um and so that becomes part of your noteboard here got it um and so we've got um some stuff about peard we've got uh uh some quotes from Borman and Neil Armstrong so we've got the beginnings of uh you know maybe a way of framing a documentary about this so let's we're gonna select these specific notes that we've curated and you know you could imagine this would be you know a much larger collection but this gives you a sense of how the the kind of the new workflow that's possible um and this is the kind of thing I really think that like 1% of notebook users actually understand that you can do this but um so once I've selected these notes not only can I summarize or suggest related ideas or create study guides or create an outline based on those specific notes I can do whatever I want with them in by typing into the chat and so what I'm going to do is say you know I'm GNA take that uh original quote about um the thing I'm interested in making so I'm interested in making this um documentary I'm Stephen Johnson and I'm going to add um based on these notes suggest an opening script for a documentary episode about Apollo one and the prehistory of space flight just adding that for theard um I will try and a little extra twist here suggest images from these sources that could be relevant let's see what it does so now oh shoot actually it's not gonna work because it's not gonna be able to do this the images because it uh it's focused on the notes right now um but uh we'll see what it does but it should be able to generate a pretty interesting script yeah there we go okay so opening script visual open on black and white footage of the card's high altitude balone Gonda from the 1930s it looks surprisingly modern narrator in the 1930s Swiss physicist AUST Picard looked at the skies and to the Fantastical novels of Jules Vern to imagine a new way to explore the world yeah and then we cut forward to like it says visual black and white still photo of the Apollo one crew in January of 1967 tragedy struck on the Launchpad at Cape canav roll um and look at the transition it does between these two narrator says decades later a new generation of explorers would borrow from Bard's Vision sealing themselves into a metal capsules breathing pure oxygen as they slipped the bonds of Earth but the dream of space travel would soon be met by a devastating truth that's so good I love I love this whole journey of like Apollo on fire peard and then we get a little script like it's it's a beautiful idea and it's a beautiful parallel it's so cool yeah this will be coming out in two years folks um I hope you all a Dan shipper Stephen Johnson production uh do you heard it Dan only gets 10% though he that's what he said you're you're writing the rest of it so you know I'm just I'm just the idea guy um um yeah this is this is wonderful um I really appreciate you taking the time to show us this um this product taking the time to go on this intellectual Journey with me um I would love to have you back anytime uh for people who are looking to uh read your book uh your latest book or to find you on Twitter or anywhere else on the internet uh how how can how can they find you and tell us about your latest book where can they find that yeah the the the new book is called The Infernal machine the true story of dynamite Terror and the rise of the modern detective um so it is very much in the spirit of what you've just seen being created here weaving together a bunch of different stories about the history of Science and Technology but also uh political violence and it's kind of a thriller in a strange way in the second half of it um it's really fun just just in bookstores now um and I'm Stephen B Johnson on Twitter and uh I write the newsletter um uh adjacent possible on substack where a lot of information about notebook LM will be there and of course notebook LM is notebook lm. goole.com and now available in over 200 countries around the world uh as of today so please do check it out incredible thanks Stephen thanks Dan 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