NotebookLM Blew Our Mind | Interview

we really see this as a tool for understanding things right like you have word processors help you create a document and Photoshop helps you you know adjust pixels in an image this is a

tool that helps you understand things well Casey we talk a lot about AI tools and products on this show and I have one that I'm really excited to talk about today yeah I'm excited to talk about

this too this is a new product called notebook LM it is a tool from Google and uh you can think of it like a kind of personal research assist it's a piece of

software that allows you to upload documents PDFs Word files even audio files websites whatever you want into these things called notebooks and then

use AI Gemini Google's AI model to basically chat with the documents to sort of have a conversation to ask questions to create study guides or

summaries um and you can even use it to create a podcast about the material that you've uploaded yeah and you know this was a product that was announced at Google IO it they called it project

Tailwind back then and from the moment I saw them talking about it on stage I thought I have got to get my hands on this thing and while it is true that you can use other tools to chat with

documents that is not unique to notebook LM they have really focused on making sure that you can cram as much material as possible into their system so that

you can have conversations with not only one very long document but many very long documents and that has really been the the difference for them but as you knowe they recently came out with

something that is maybe even more impressive yeah the AI audio overviews feature uh is really what has been sort of lighting up the internet over the

past week or so like I'll just be honest uh we see a lot of AI products we get a lot of Early Access and demos of things and many times they show some potential

but if you actually start digging in uh they are not all that useful or they hallucinate or they're just not reliable enough to be useful for people like you and me yeah notebook LM is I would say

one of my favorite AI products that I have used this year because it is uh it is not trying to do everything for everyone it is a tool for research for

writing um it is uh really really capable at what it does and the audio feature in particular is just pretty stunning so today I want to talk about notebook LM So today we're going to

bring in one of the key people who helped conceive of build notebook LM uh stevenh Johnson Steph's path to working at Google is pretty unusual his main career the thing that he's most known

for is a writer he has written uh for many years for the New York Times and New York Times magazine and other places he's the author of more than a dozen books including his latest The Infernal

machine a true story of dynamite Terror and the rise of the modern detective and he's been one of my favorite writers about tech and the future and a few years ago uh Google approached him and

basically said hey want to help us make a tool for writers yeah yeah and you know I got to know Stephen a little bit uh as they were launching notebook LM and we met and he told me all about his notetaking process and how he wanted to

use AI to to sort of improve his writing and we we truly just became fast friends because we have the exact same view of this stuff which is give me the most technology to make my job as easy as it

possibly can be and um unlike me he's now actually working inside this company trying to make something that does just that yeah and why haven't you written 14 books for well you know I've been busy lately Kevin but I'm going to get around to it one of these days let's bring in

Stephen Stephen Johnson welcome to hardfork guys it's great to be here Hey Stephen so Stephen I remember reading a piece you wrote for the New York Times magazine back in April of 2022 it was

about six months before chat GPT came out and you had this big great piece about how AI was starting to get really good at language through these new

things called large language models and your sort of predictions about how that would have all kinds of profound effects on society but I remember that piece so

vividly because it captured this feeling that I uh was having at the time which Casey now start has started calling AI vertigo basically this sort of head spinning sensation when things are just

moving so quickly I'm curious like what got you as a writer interested in AI to the point that you decided to sort of build AI products at Google you know I I

just have spent all of my career as a writer always dabbling with tools to help me do the writing with with with all the latest software like Casey and I have this kind of shared obsession with

no taking software one of those I know you know don't even get started about scrier and all the different things that we can talk about I always saw the computer and software as a kind of

companion and a kind of brainstorming partner like and I was always pushing the technology to do that in my own work and so the idea that I could just kind of say hey let's think out loud about

this particular topic and it would understand on some level and respond with coherent sentences you know obviously there were hallucinations and there were all the things that we know are problems which I also wrote about in

that piece but it was clear that some new set of doors of possibility had just opened up for the first time and and I just got really interested in walking

through those doors so how does Google first approach you and is the idea hey we want to make a tool for writers like you or was it something else yeah it was a little bit like that so Google had just spun up right around this time a a

new division called Google Labs there was an old Google labs this is kind of a new iteration of it and there was a guy running it named clay bore who's since left um but uh and now Josh Woodward is

running it and clay and Josh had this idea that Google Labs could be a space where you could do kind of product focused experimentation with new emerging Technologies and they also had

this idea that there would be co-creation would be built into the kind of ethos of labs and so if you were making a music product you would have a musician in the room like as you were

building it so it wasn't just about you know we're going to go out and do some user research with musicians we're actually going to have somebody through the life of the product there and so they were just kind of cooking up these ideas and they had both read my books

over the years they' read that times piece they read my substack and all that together caused them to think wonder if stevenh could be the first kind of guinea pig for this so um you know

Stephen you and I have had a chance to chat before and um I truly aspire to be the notetaker that you are because I have talked a big game on this podcast

about how I'm trying to write down sort of every interesting like quote or idea that I come across and Link those together and I made some strides there but like you showed me your system at one point and it is the real deal like

you truly have been keeping track of every idea that you've come across for for seemingly quite some time what was the moment that you said oh like this

intersects with AI in a way that maybe this notebook LM can realize in a product I want you to remember Kevin that every time you think that Casey is such a super nerd with his no ticking

like there are even more dous people in the world so you are the alpha nerd of the the not taking community so uh yeah I can tell you exactly what it was so so

I have been collecting quotations from books that I've that I've read initially by typing them up in the late 90s um and then once you know ebooks came out I you could save quotes and things like that it an

amazing program that I think you use called readwise that let you organize all your quotes from if you read on the Kindle or any other ebook and so I have something like 8,000 quotes from books

that date back to the late 90s um that I've collected and that is really the history of all the ideas that really shaped who I am right like my mental model of the world is shaped by the

other ideas that that I've read from other people and so notebook now lets you have um up to 25 million words in a single notebook put that in terms of

pages how many pages is that what would that be that would be like 40 books yeah right something in that order and do your 8,000 quotes fit in one in one of these 25 million word uh documents yeah yeah they're only about three million

words so I've loaded them all in as you know a bunch of documents 30 years of collecting quotes fits easily into one of these things and what I'm slowly adding to that notebook is all the stuff that I've written too so it's kind of everything I've read that's important

and literally every word I've published is eventually going to be in that one notebook I just haven't got Kevin can't do that because it would poison the data set but I think it's good it works for you the safety Flags would be going off

it' be terrible so so when I was able to do that which was really I don't know about a year ago for the first time where I can get all that stuff in there um I call that notebook my everything

notebook and then I could sit down and just be like I'm thinking about you know writing a piece about X like here or here's a paragraph from the piece that

I've just wrote just written um what am I missing what am I forgetting um give me give me an overview of all the stuff that I've read that is related to this particular topic and it would return particularly once we switched to Gemini

like Gemini was the big kind of Paradigm Shift here um I get this like incredibly nuanced response that is constantly reminding me of things that I've forgotten and now as of like three

months ago we have inline citations in in all the comments from the model and you can click on each citation and it takes you directly to the original quote yes I love this feature I've been

playing around with with notebook LM and it is truly one of the best features about it is that you know it'll show you something you're talking to it about something you've read or something you've written and it just has that

little sort of like citation you click on it it takes you right to the source material so you can see see for yourself like this actually is an accurate representation of what was in the PDF I uploaded and you know that that's one of

the things that's like what an incredibly interesting like learning mode that is right like up until now if you wanted to have a conversation with the material in a book

like you had to find the author or you had to find a tutor and an expert who knew the material really well and those people are in scarce Supply but now you can actually like load in the book and

navigate it through conversation and dialogue which is a a form that people really obviously like to use so that that is amazing and I think will probably be the primary way that people access it but because of the fact that

you have taken these notes for 30 years you're able to use this in this different way which is essentially like take me through my own intellectual history and let me talk to the entire

like course of learning that I've had over three decades remind me of things right or make new connections for me and that feels like the kind of augmentation

that I truly have always wanted AI to give us right like that is the good stuff right I'm glad you you said that that that means a lot coming from you um I I think though I think there was an

early tension in um in in creating no pokum which was the question of like how normal am I and you know we have this amazing colleague RZA Martin who's the product

manager who's been incredible was on on it from the beginning and I think like you know she she was kind of like this has to work for people who don't collect 8,000 quotations over 30 years of their

lives right if it doesn't you know work for them and so but I think one of the things that we've learned is you actually you know particularly in a digital age like you have you know you

can import docs and slides and so if you're a Google Drive user the history of all the docs you have in there is actually a history of the last four or five years of things that you've been interested in and that you've been

working on whatever your job is and so one of the things I often tell people with notbook Alam is just first thing to do is create a notebook if you are a drive user grab the last 20 docks in there and just don't even think about

organiz them just dump them all in even if they're for different projects and just start having a conversation and the the sense of oh this AI actually knows what I'm doing and understands what I've

been working on and can piece together kind of you know insights from that is pretty is pretty amazing and by the way I should say you know when we do this we're not training the model that was one of my questions is like I think a

lot of people would say okay well if I upload a a copy of my book or some some documents that are personal to me is Google going to then be able to sort of see and so what we are doing is not training the

model that would take a long time to train a model on your data um and it actually wouldn't for complicated reasons work as well as as the way that we're doing it um we're just taking the information you have and putting it in

the models context window which is kind of like the short-term memory of the model it's the easiest way to understand it and um the beauty of that is one the

model is much more accurate with information in its context um and and so the the hallucination rates drop down dramatically you can do things like citations that you wouldn't be able to

do otherwise um but it also means that the second you close your session that information goes away and so there's no way for we're not learning from it we're not making the model smarter in the long run and there's no way for that

information to kind of leak out into other users and that has been a a fun fundamental principle of the product from the very beginning yeah I hope you take this next thing that I'm about to

say the right way because I do mean it as a compliment um but notebook LM strikes me is an extremely UNG googly product right it is it is probably not the kind of thing that's going to get a

billion users which is how Google has historically decided what to build um it didn't have like a big splashy launch with ads running on the Olympics uh it's not sort of promoted on a bunch of other

Google products as far as I can tell it has a Discord server uh and and the design of the actual tool just feels different than a lot of what Google has built in AI um it sort of feels to me

like it might be this kind of isolated kind of semi-autonomous region within Google uh that doesn't have that much contact with the rest of the company is that

right well that's an interesting question um yeah some of that is right um and some of that is a reflection of what labs set out to do right which is to like let let's create a space where

we can um be be more comfortable with being experimental and that enabled us to do some things like um experiment with different types of interfaces that would not necessarily

have the Polish that you would expect from other Google official products um the Discord is a great example that was one of RIS Martin's ideas you know we just wanted to like build a community

around it and I remember Risa coming to me and saying you know I want to build a Discord for this product and I said what is a Discord I had no my kids were were Discord users so I rang a bell but I'd

never been on Discord before and now I'm in there all the time and we have we have like 45,000 people who are members of this community now and so kind of and we just discover so many things from

them like it's like notebook is taking off with um D and D players like Dungeons and Dragons like dungeon Masters because they have it's a very like literary genre of game right and

you have these long campaigns Rich lore yeah yeah it's same thing with like fantasy novelists and sci-fi novelists where they have a backstory that's enormous and they can't keep track of at all like if if George R Martin would

adopt our product like we would we would have winter yes maybe we could actually get a new book I spent some time in the in the notebook LM Discord it's a very fun place because you get to sort of see how

people are using it and sort of get ideas I also love that there's one person in there who's just constantly posting about how they're using notebook LM to analyze a huge database of Sonic the Hedgehog fan

[Laughter] fiction talking about 100% they've been for a while it's really interesting they they found a lot of use cases for Sonic related uh you know work and they're

going to be on the show next week but you know what Kevin I I want to disagree with you about whether this is Googly or not because I think this is like old school Google and this is the Google I like like do you remember back in the

day when the googlers could just do anything they wanted in their 20% time they give them a day a week to be like hack around on something right do something interesting to me this is the sort of thing that would come out of 20%

time where it's like let's find some of the you know the biggest everyone to Google is a nerd but let's let's find people who are nerdy about something really in particular that could be massively useful to maybe a narrow group

of people but maybe we find something in there that who knows does scale up to a billion people eventually yeah but maybe we should talk about the audio Kevin yes we have to talk about the audio feature because this is what really has put this

uh this tool on the map for a lot of people um this is an amazing feature the first time I saw it I did have a moment of AI vertigo and I think I emailed you

and was like oh my God what is this thing how is this feature so good how does it work uh what is it trained on how did it learn how to do podcast banter just tell us about this feature

there another great Labs um case study um it was another team inside of labs that had basically developed a a tool that would take any Source material you wanted um and generate an audio

conversation that would sounded like two engaged entertaining people having a conversation you may be familiar with this genre uh about the whatever material you gave it and the the kind of two use cases that

we were talking about in in the early days was um M kind of source material that no no one would ever build a real podcast for so Arcane City Council meetings that no one there's no

economics and turning that into a podcast or personalized learning where you're like you're an auditorial learner learner and you want to you know do a review of the week's you know uh

assignment and you'd rather Digest in the form or you'd like to augment it with the listening to a conversation um because people remember better with conversations and they can do it on the

go and so they had this incredible demo and the thing about it like behind the scenes is that a lot of the Breakthrough is actually the the edit cycle so behind

the scenes it's basically running through you know stuff that we all do professionally all the time which is it generates an outline it it kind of revises that outline it generates a

detailed version of of the script and then it has a kind of critique phase and um and then it modifies it based on the critique and and so it's it takes about four or five minutes to generate and it's because it's going through all

these different passes and you know you can call that like Chain of Thought reasoning or you know you could do but when I saw it I was like no no no that's an edit cycle like that's what you you did a draft and then you revised it and then you got it got better over time are

you taking notes you could do this for your book you help go ahead Stephen so and and then at the end of it the there's a stage where it adds my favorite new word which is disfluencies

so it takes a kind of sterile script and turns adds all the the banter and the pauses and the the

likes words and that turns out to be crucial because you cannot listen to two robots talking to each other no one it would be just painful to listen to um it

be like I don't know the Lex Freeman podcast is pretty popular Sten oh boy so not even going to bring that up uh

follow up on that so so that was crucial and then on top of that all there is a um um there's some new voice technology

which I'm I'm not qualified to kind of explain but that adds an really an incredible layer which is like figuring out without any coding in the script

figuring out that this is a point that they are trying to emphasize and so they're speaking more slowly or they're trying to imply that they're hesitating a little bit and so they're raising

their intonation a little bit all that stuff it does and having two people talking to each other like that it just it is one of those moments when I first heard it I was like this is incredible

and we were already we were already we rolled out these notebook guides that take your all your documents and turn them into a briefing dock or an FAQ or a timeline which is incredibly useful for

you know kind of writers um and so this was just like oh we can now do it in another form like if maybe you want to take your sources and listen to a conversation about them and so it just

was a beautiful fit inside of notebook LM and so we just have been scrambling all summer to get this out and uh we're it's it's been really cool to see the really awesome I made a podcast about uh

my my new uh vacuum cleaner that I got by feeding it the the user's manual PDF and out pops this 8 Minute explanation of all the features of my new vacuum it's really cool okay so I have a confession which which is I am obsessed

with this stuff and Stephen was very kind and and gave me early access to this but at the time I was you know getting ready for meta connect and some other things and I just did not have the the the time and attention to focus on it but then when I found out when you

were coming on the show I thought I am not going to listen to any of these until we're all in the room together oh my gosh and here and here's why because I've learned from YouTube that the most popular thing that you can do on YouTube is to hear something for the first time

so you know I don't know if you've seen this Kevin but it's like if if you listen to Metallica For the First Time on YouTube you got a million views but I already listen to Metallica in high school so I thought I'll do the next best thing and listen to The Notebook LM

audio right here on hard so let's listen to a few examples of this audio feature uh I have been playing around with this for a couple days now having a lot of fun with it uh so a lot of times in our

work as journalists we have to sort of make sense of a bunch of different documents whether they're legal filings or or what have you and um so I was doing some research about weo and their

self-driving cars and there have been a few studies that have come out recently about uh the safety data of these cars of human drivers sort of how how safe are Whos compared to human drivers and

it's been a really hot topic we've talked about on the show totally very controversial but it's a it's a little hard to understand the data is a little mangled and and they're just these papers are quite long and so uh this morning I was going uh into the studio

and I thought I'm just going to dump a whole bunch of these PDFs of these studies into a notebook LM and generate a podcast that I can listen to on the way to the office and maybe get a sort

of high level overview of what this these Studies have shown so I want to play for you the the first sort of 30 or so seconds of my whmo data podcast all right ever see one of those weo cars

just cruising around with like no one behind the wheel yeah I always wonder is that thing safe I mean no offense to robots or anything but handing over the keys to a machine it just it just feels

different yeah it really does make you think about like trusting technology with our lives exactly especially when it's something as important as like driving you know totally so that's what

we're diving into today the safety of those driverless Whos we've got a bunch of research lined up including some really recent data to get past the

headlines and figure out what's really going on so that's that's amazing that's one clip um that's amazing it's really cool okay and it it does actually continue on for like minutes after that

and sort of break down the data in these papers quite well from what I can tell I also put in your uh latest platformer newsletter uh into this and had it

generate a podcast about that so here's a clip from the platformer newsletter AI podcast wow speaking of risks Newton's decision to leave substack that was a

risk but it sounds like he's thinking long term he is he really is and I think that's key building a sustainable media business in this day and age it's not easy it takes more than just great content you need smart business

decisions too it's a balancing act right you got to stay TR your vision but also make sure you can you know keep the lights on and Newton's been very open about Platformers finances about the

challenges that come with going independent transparency builds trust and these days trust is invaluable and let's be real leaving a platform like

substack even one with its problems it's going to come with some Financial growing pains for sure it's like jumping off a cliff and hoping you can build your wings on the way down I like these people they're smart

people what they're talking about yeah they're big fans of you the last clip I want to play I I was just sort of thinking like how how esoteric can I get here like what can I

make a podcast about using notebook LM so I uploaded my most recent credit card statement to notebook LM and had it try to make an AI podcast about some of the

things that I've been spending my money on and uh so this is the uh the the most recent uh credit card statement that I got in podcast form I love it okay let's

see I'm noticing a pattern here quite a few Uber rides between August 8th and September 9th yeah and that's something to consider right especially if you live in an area with you know readily

available public transportation or by friendly routes most fre ride shares can really add up for sure they do I mean for example let's say an average Uber ride costs you $20 and you're taking

four of those a week well that's $320 a month think about it that's money that could be going to other things other financial goals yeah absolutely small changes can make a big difference yeah

it really told me to get my ass on the bus it's it's like a financial advisor in your pocket truly so this uh blew my mind does what do you what's your

reaction it it really is extraordinary and um you know again I knew we were going to do this today I wanted to wait until this moment to hear it but in the meantime I was seeing so many folks on

social media saying you have to listen to this like it is so eerily good and you know my mind is already alive with you know a problem that I have which is

because we do a podcast we often talk to the authors of books and often we decide we want to talk to them you know a week before and then I get a PDF in you know in my inbox and and now I have seven days to read it and it's incredibly

difficult if I could listen to a podcast about it I would love it now I realize how painful that's going to be to hear for every author who exists but um you know if it

information more accessible I want to try it yeah and and probably people will make podcasts about a lot of the books that we talk on this talk about on this show but no one's going to make a podcast about my credit card statement

or uh you know the policies at my kids daycare or something like that so I it's a really interesting way to to sort of transform these sort of more uh esoteric uh documents I mean once I heard about

your Prof at Uber spending I do kind of want to do a podcast about your spending habits but go on well I I think actually that one was really interesting because one it its ability to figure out a way

to rationalize a podcast is amazing we would give it kind of internal notebook LM documents and they would be like well it's really exciting we've got our hands on some internal documents from Google

and you know they just they want to turn it into something that's a show um but but what you could hear there is an interesting thing they are generally um

instructed to be enthusiastic and engaged so one thing people are doing is putting their CV and resumes in there and they're like John Smith I mean what an amazing career he's had I mean assistant vice president at the bank

that's impressive you know but what happened there apparently because your Uber writing is so excessive was an interesting suggested mode which is

critique yes right so you can imagine a future version which is like I actually I want some tough love here like here here's the thing I'm working on like talk me through like what the problems are I I want to hear that and that could

be something that I didn't give it any prompt I didn't say criticize my spending on Uber it was literally just make a podcast out of my credit card one click upload the PDF I

pushed a button I waited a couple minutes I I listened to this podcast and it had pulled out some details and spending patterns for my credit card statement that's just an incredible are we are we seeing the seeds of our

demises podcasters like in this segment well that was the second thing I was going to say which is that they're they're instructed to and and my mind is is kind of changing on this as users are

experimenting with it more but um they're instructed to be fun and engaging and I listen to dozens and dozens into hundreds of these you know as it was in development over the summer and um they were always fun and engaging

there's banter and all that stuff I never once heard them be funny I never once laughed and I thought about I'm you know since you've been saying so many nice things about me I thought about

hardfork which I laugh at out loud all the time when I listen to you guys and it occurred to me like the the one thing interestingly that the models they're so

good at so many things so almost you know superum in some of their abilities but they can't yet be funny in this way and the kind of the banter back and forth between them is never actually

funny it's fun but not funny right and then somebody on the internet there's a there's a fake scholarly PDF the chicken PDF have you ever seen this which is

know this one yeah it's just it looks exactly like an academic PDF it's got charts and graphs and things like that but every single word is chicken in the entire document I don't know why this

was made but they put it into as the source and the host just kind of went insane but were hilarious and there's a whole riff where they're like this

document is making us insane it's just chicken chicken chicken chicken chicken chicken chicken and they do all these things with their intonation and at some point the host says one of the the guy says something like it's it's like we've

been taken hostage by chicken and the ransom is our Santa I literally laughed out loud so I it is possible to elicit stuff that is genuinely funny from them um so you know

who knows obviously being able to to push it in directions and give it some guidance is something we're getting a lot of requests for um so I would expect to you could also imagine being able to

sort of pick like do you want this to be a two-person sort of hosted podcast um you know or do you want it to be just one person do you want do you want someone to one of the hosts to be like super annoying and like always

interrupting you could call that Casey mode if you wanted to that's a free idea that reminds me I think we should do Kevin's credit card statement but as a true crime serial you know so do you do any kind of moderation

on what people are uploading into notebook LM could someone upload you know a a mine comp and make an AI podcast about it so there's there's basic safety low-level safety that

Google has that will will block really offensive things from happening um and basically what we've the the kind of the latest version of it um when there is

politically charged content from either left or the right um the the hosts are instructed to take a neutral kind of reporting tone and to basically say we

are we're not taking sides in this we're just reporting what is in these sources and we feel like that's kind of the best way to do it um and and so there's there's kind of an extra instruction for

them to make that clear if it if it seems like it's it's politically charged in some kind of way yeah I uh I did actually try making an AI podcast about minec that

wasn't hypothetical and what happened it did it but it was like it was very judgmental at the top it was like we're going to talk today about mine comp a book about how Hitler became such a monster which I actually thought was good which is like actually how we teach

history by the way you know people do read minec comp in history classes but someone's up there telling them that it was bad totally so in Google's press release about this feature that was a brief mention of some other features

that might be on the horizon for Notebook LM uh including the ability to generate overviews uh podcasts in a language other than English and the ability to actually take part in the

conversation yourself to sort of interrupt the host of this AI generated podcast uh maybe ask a follow-up question about something they just said how far away do you think those things

are uh we're actively working on both of them um I would expect some version of them to be uh you know in in in the next few months I mean it's not that you know

they're they're doable there's a there's a you know there's kind of a lag like how willing are you to wait for the the you know the steering that you give it with your own voice um to to affect the

model um we actually just uh just this week allowed you to uh input audio as a source too so now you can go like this kind of classic format in the student

use case you go record your lecture um you know take handwritten notes um just at the most important things but mostly just listen and then you go back to notebook upload a scan of your notes and

upload the audio lecture and then basically say take my little highlevel summary and expand it based on the full text of the lecture so I can really just write down the most important things and

let the model fill in all the details based on the recording and then take that and turn that into a podcast so I can review it at the gym like that sort of workflow likeable I would be so good at College if I went to college today I

mean TR I truly think that I could be at the top of my class and by being good at College you mean you would just be using AI or do all your work I would be using AI to a augment my natural human abilities Kevin something I suggest you

try yeah well that's I mean no seriously like we really see this as a tool for understanding things right like you have word processors help you create a document and Photoshop helps you you

know adjust pixels in an image this is a tool that helps you understand things and like if you are trying in good faith to understand the material as a student or as a knowledge worker as a writer or

whatever it is like this is a tool that should really help you do that better yeah um what's next for you personally are you going to stick around at Google and build some more stuff uh are you uh are you are you yearning for the

solitary life of a writer again I am not yearning I am really enjoying this and there's so much to build um and to be in the middle of you know the most

important technological change of my life life um working with really interesting people on this thing that I've always wanted like I would kind of be an idiot to stop now yeah also the snacks are way better at Google

unbelievable cafeteria all right Stephen Johnson thanks so much for coming on thanks guys hey that's the end of this clip if you liked what you saw head on over to our page and subscribe and you can get the

full podcast we do a show like this almost every week on Tech and the future head on over there now and subscribe

[Music] n [Music]