Transcript#
This transcript was generated automatically and may contain errors.
Welcome to the test set. Here we talk with some of the brightest thinkers and tinkerers in statistical analysis, scientific computing, and machine learning. Digging into what makes them tick, plus the insights, experiments, and OMG moments that shape the field.
On this episode, we sit down with Paige Bailey, DevRel Engineering Lead at Google DeepMind. She started out coding text-based games from Byte Magazine onto her Apple II computer, which is a real throwback. Her website mentions she makes weird things digitally in IRL, like a bot that emails her, roasting her taste in music, or solar-powered, silent-film birdhouses as street art in San Francisco. She runs us through her background in geophysics, where she was introduced to Python and open source early. She discusses how she weaves a variety of Google APIs and services together to make things fun, weird, and educational.
Paige Bailey, welcome to the test set. Awesome. Thank you for having me. Yeah. So we were here in San Francisco, and you mentioned you took a Waymo in, which seems very relevant. I did. It is very on-brand, yes.
Just by way of introduction, so you're a Developer Relations Engineering Lead at Google DeepMind? Correct. I've had an incredible career of doing a lot of things, which I really want to get to. Because I always forget, I want to make sure to say, I'm Michael Chao, the host. And I'm joined by Hadley Wickham, Chief Scientist at Posit, and Isabel Zimmerman, credible Posit software engineer. And we're so happy to have you on here in beautiful San Francisco.
From text adventures to open source
I know we talked a little bit before you came on, and I thought maybe you could just catch us up on your career, starting with your love of text adventures. Oh, yes. Absolutely. So I got my first computer. We rescued it from being thrown away around the time that I was eight or nine years old. It was an Apple II. And there weren't a ton of games that were available for the Apple II at the time, certainly not ones that you could like go to GameStop and purchase. So I was beholden to all of the games that came with this computer that just missed getting thrown away. And also a whole bunch of books that talked about how you might build your own software programs. And old magazines like copies of Byte, which had additional games that you could type in. So my first programs were all text adventures, kind of like either transcribing choose-your-own-adventure books or like building my own. And that just sort of made computers feel like a fun thing. And loved open source as well, like can pretty much give my entire career to open source.
It does feel like a really — it feels so strange to even think about it right now, of how different everything was back then. It was also the situation where I remember going to my professors and being like, hey, I really like programming. I think this is really cool. We should totally have libraries for doing earth sciences-related things. And my professors being like, no, that's not real science. Why are you wasting your time? Nobody needs — if you're writing libraries, that's not actually contributing to your career. It's actually a waste of time.
Nobody needs — if you're writing libraries, that's not actually contributing to your career. It's actually a waste of time.
Yeah, but tooling versus doing the actual research. And now it's — if you're not writing code or using code to analyze data, you're probably not doing research. What are you doing?
From geophysics to TensorFlow
I'm really curious. You were somebody who has been in the AI space before it was cool, and I'm putting that in air quotes. How did you make that jump from, you know, I'm doing geo stuff to now I'm doing AI, I'm doing deep learning, working on things like TensorFlow? Yeah, so geophysics — geophysics is like — I always feel like we are the sort of the more stay-at-home type kind of earth scientists, right? We're the ones that care about computers and that are trying to find more efficient ways to analyze data.
And the geophysics world actually adopted GPUs before most everybody else, for things like velocity modeling, like fluid dynamics simulations, like all sorts of stuff, even before the gaming industry kind of like caught on to GPUs. And so I was doing that a lot for some of the geophysics work, just like trying to bang my head against CUDA. And when TensorFlow was first released, I don't think most people remember, but it was CPU only. So you were doing analysis across large numbers of CPUs, not really thinking about GPUs until later on. And so that was something that I could do that was helpful of just kind of like, hey, you're thinking about accelerators now. I know CUDA. I can help with that. And it's a useful way to kind of collaborate with the team, I think. If somebody releases an open source library and you contribute to it or you build something with it and talk about it, then they get a flavor of what it would be like to work with you as a person.
There's such a strong pipeline of people from like physical sciences like that too. It feels like AI. There's the whole conference about ex-astronomers, now data scientists. It's so surprising to see how all this comes together. Yeah, linear algebra. And like also, you know, JAX has the same spec as NumPy. And a lot of the libraries have the same like general flavor of scientific computing libraries. So I think there's definitely a lot of love between the kind of physics and mathematics world and the JAX world. Also, like all of the JAX machine learning frameworks authors came from mostly like mathematics backgrounds, which is quite cool.
Being a curious generalist
Yeah, it's interesting. It seems like you've done a lot of both like development and product management and DevRel engineering. When did you know this was kind of the work that you really wanted to be doing? How did this work come together? Yeah, I think I, again, just like I feel so stupidly lucky, like in the sense that I've just always done whatever I thought would be useful and interesting.
And now we're in this really happy place where a long time ago, people would kind of artificially put people into buckets of like, oh, you're an engineer, you're a product human, you're a design human, you're like these other things. And you could only wear this one hat, which is really frustrating if you like doing a whole bunch of stuff. And now we're in this place where it's just like, oh, you want to do data visualization and you want to understand large scale datasets and you also want to be able to build tools in order to do all of the above, like go for it. Like that's — you can be this auteur of anything you want to enable.
So so I didn't have like any sort of design other than like I'm going to work on things that I feel will be important and useful and interesting. And when I was a product person, I was exclusively a product person on developer tools or models. So like highly technical, like lower level sort of sort of thing. So I was still writing code every day.
It does really feel like like Cloud Code and similar tools like such a win for people who have just got like weird interests in lots of places. Exactly. Like it's and and like suddenly all of these things that were like 70 percent finished on your GitHub, like you can like actually get out into the world. There's never been a better time to be a curious human who wants to like create things.
Silent film birdhouses and side projects
Yeah. Like I made an iPhone app like it's just a little timer for talks, but just like something that would be my head for years. And like that's like a weekend project now. It's like it's really cool. Exactly. I don't have it in my backpack right now, but there's one of my side projects is there's something called a cheap yellow display. It's called a CYD ESP32. And it's like this little tiny board with just a visualization screen on top. And to update it, you have to like rewrite the firmware. So it's not as flexible as something like a Raspberry Pi with the screen. But I would have never been able to do anything with it. And now I'm using those to power these silent film birdhouses. So it's like you have a birdhouse, you put the little screen on the inside, people look through the little hole and you can watch the silent film.
It's I'm putting them. So I'm putting them around San Francisco as art installations. Like next to the tiny like borrowing libraries. But you can you can have like site specific films for each location. And then like there's just ever like a little battery and then that lasts for ages. And there are also like super like low energy requirements. So even if you had kind of like a solar panel on top of the birdhouse, like that would be enough to power it for for quite a bit of time.
Like your website is just such a beautiful, curious, joyful experience. And like just the amount of fun side projects and whimsy that you're bringing to all of these like really hardcore tools. I'm really curious, like, what are you working on? What tools are you building, whether they're the funkiest things like silent birdhouses or what are you excited about right now?
Oh, man. So so I also love all of my all of my side projects. Like they're they're super fun to build. Like I get a lot of joy out of them, but they're also kind of like sneaky ulterior motive is stress testing some of the features that we have coming out for the Gemini APIs in our models. You like hid vegetables in them.
Well, it's well, so so as an example, we released something just recently, our second iteration of the multimodal embeddings model, which allows you to embed in the same space video, audio, images, text and code. So you can like pull together audio, video, like you could you could type in like Alan Kay and then see like every time Alan Kay utters words in a video, but also like every time he appears in a video, anytime he appears in a photograph, etc. And it's it's just really, really cool to see that. So that's powering folklore.dev, which was pulling a lot of the the oral histories from the Computer History Museum into kind of like a contextual space. So you got to see the transcript. You got to see interesting anecdotes extracted. But you also got it grounded and kind of like, well, when they say this computer and they were able to do this on this computer, like what kind of compute power does it have? How does that compare to your mobile device? Like what would it cost in today's dollars?
Those sorts of things. And it's the same with the stacks.dev, which was pulling in all of the Byte and Omni magazines and more on the way to kind of extract out insights using the Gemini models, whether it's like telephone numbers or addresses or whatever it is, and then also putting the covers and the articles in a similar embedding space. So if somebody like wrote in to complain about their experience using a Commodore 64, like what other articles are similar in vibes to that?
And I also thought it was quite cool in the sense that, like, pulling in, you know, 40 years or so of those magazines and then mapping out the different, you know, places that people were sending letters from or, like, the stores and those sorts of things. When you visualize them on a map, you can start seeing, like, oh my god, like, in Houston there were these pockets of people who all cared about this thing. And in, you know, like Sunnyvale or in Cupertino, there were, like, five people within a six-block radius that cared about this thing. And you can start realizing that, like, you know, geographic location might have impacted or influenced some of the creations of these products. But all of that's, like, locked away otherwise, and now it's not, which is kind of amazing.
Yeah, and also the cost changes, too. So, like, the Gemini 3.1 flashlight model, which came out just recently, ended up kind of, like, it's like a 90% reduction in the costs associated. So significantly more powerful than, like, you know, Gemini 2.0 Pro or 2.5 Pro, but at a fraction of the cost and much faster. And it's the same with the batch API, like, you can get a 50% reduction in costs just by using the batch API. So the cost of maintaining all of these websites over time has actually gone down, even though, like, more features have been added and they've gotten much cooler just because the model prices are also going down pretty exponentially.
Are you willing to tell us, like, how much does it cost to run one of those nowadays? Is it, you know, hundreds of dollars to have this all be running on your website? Yeah, so I deploy everything via Cloud Run, which is pretty low cost. And in sum, I think for all of the things that you see on webpage.dev, now that I've replatted to use Gemini 3.1 flashlight and Nano Banana 2 instead of Nano Banana Pro for the number of ones that use Nano Banana 2, I think the most expensive service is the embeddings, but it's still been less than, like, $200 to maintain everything over the course of a year. Wow. For as many prolific projects that are on there, I am shocked. That's impressive.
Speed-running apps and Wikipedia rabbit holes
It seems like the turnaround sometimes is just immediate that you might deploy a project in hours. Is that? This is true. Like, the latest one, I haven't added it to my website yet, though this is a good incentive to. It's a traffic cam guesser. So it pulls in all of the live traffic feeds from around the United States for at least, like, a half dozen cities so far. And then, like, removes using Nano Banana 2 any street signs or identifying sites. And then you have to guess which neighborhood the traffic cam is from. And then, like, it gives you kind of geoguessr-style hints of, like, here's what you should have seen to help guide your choice. And you can also use, like, OAuth to log in and kind of track progress, too.
My favorite one, though, is the Wikipedia Racer, which is, like, I am just, I am enchanted by depths of Wikipedia and Wikipedia rabbit-holing. And so having something that will just create Wikipedia rabbit holes for me is pretty magical. Yeah, I love that. I think I went on there, too, and there's, like, levels of difficulty as well. Oh, yeah, yeah, yeah. It's not point A to B. There's actually, you can customize your Wikirace journey. Exactly. Yep. And then also you can commission your own adventures. So if you want something that's, like, related to Kanye or, like, related to, like, meditative Gregorian chants or whatever it is, like, it will create a Wikipedia race for you specifically for that. And then it will also show you over time as more people try it, like, what their score is and how their paths diverge from yours.
Do you think you've always been into this, like, speed run, will it bring joy, like, beautiful form of tinkering? Do you think, like, when you were a kid, someone could have guessed this person's going to speed run apps? Oh, gosh, no. I grew up in, like, the tiniest little farm town in Texas. So, like, 1,300 people, 15 miles away from the nearest grocery store sort of situation. And also in university, like, I don't think any of my professors would have guessed it. Though they probably would have said something to the effect of, like, oh, Paige cares about computers too much. Like, she's going to be a bad physicist.
So I think the world has changed kind of recently to appreciate people who are whole humans, who care about not just, like, one thing, but, like, lots of things and who are capable of seeing connections between lots of things. So a couple of favorite anecdotes, like, Claude Shannon came up with information theory because he took a philosophy class. Like, there are other scientific breakthroughs that have been inspired by things that are completely outside of the sciences that are in the arts.
And then also, like, as an example, Ted Nelson introduced Alan Kay and his wife. Because Alan Kay's wife, Bonnie, was trying to write the screenplay for Tron. And she ended up basing, like, one of the characters in Tron on Alan Kay. And that was the first screenplay to ever be typed and printed off on a computer because it was using the Alto at Xerox PARC. So it's, like, one of the most beloved, like, entertainment things — Tron, like, was only possible because of this interplay between, like, tech plus computers.
And last one, Larry Tuzler got inspired by zines for the copy and paste feature for Mac, right? So, because he was, like, making zines, like, cutting out things and, like, pasting them together and, like, that inspired copy paste. So I feel like, you know, the magic happens in these margins. And, like, people had historically kind of been pushed into these silos. And now we're getting to the place where we're bringing back people into appreciating whatever they think they're interested in.
So I feel like, you know, the magic happens in these margins.
Sort of, like, interesting when you think about, like, the kind of Victorian, like, polymaths who, like, did all of these different fields. It kind of feels like we're heading back in that direction a little bit more. And also we're, you know, like, just doing what enchanted them, too. Because they would, like, play an instrument or they would, like, go hang out with their friend who was, like, doing art in the park. And, like, it's, you know, those things are important. Like, we should all be whole humans, not just, like, feel like we need to over-index on one strength.
How projects evolve and constraints inspire
How do you choose what to try? Like, how do you choose, like, ooh, I'm going to stitch A to B, I'm going to try this tool today. How are you figuring it out? And, like, how many, like, of the things you try, like, how many do you think are successes and, like, failures? So some of them, like, a lot of the time the thing that actually gets published is not the thing that I originally wanted to do. It's, like, and, like, I find that there's some sort of constraint in the tool or constraint in, you know, the API that I'm trying to call, that means that I have to pursue an alternate path.
So as an example, one thing that I had been working on was, like, I also have a whole collection of just, like, emails that get sent to me every morning. One of which is pulling a new painting from the Art Institute of Chicago, or, like, a new art piece from the Art Institute of Chicago. Describing it like a rough-and-tumble Chicagoan in a cool way. And then also, like, peppering in, like, really interesting insights about the city or the author that you wouldn't expect, which is using the Google search grounding feature. And then formatting it nicely. But the reason that that happened was because the Art Institute of Chicago was one of the only ones that had an API that you could call that did not require a kind of, like, username password. And I didn't want to store that in plain text. So, like, that entire experiment was only possible because you could sort of ping the API and get that response back. Like, originally I had been like, oh, well, I should pull from a whole bunch of different museums and just do this generic thing, and then this gave it a little bit more of a flavor and personality.
I think that's kind of one of the things I think I've learned from like making images with Nanobanana2 is sometimes you've just got to like roll with it. Like you can't, that initial idea you had, you can't hold on it too hard because it's just too frustrating to get to and just too good to be open to like what the model brings you, what randomness brings you today.
It feels one of the things that's been most enchanting about AI as a person who, you know, computer programmers historically have very much wanted to control everything. Like, I must control everything. Like I must deterministically know the input and deterministically know the output. And now it's like, it's definitely not that. It's kind of like, all right, you can set the constraints or like you can attempt to set some constraints, but like what you're going to get is like real different. And so you either need to be able to kind of do that in an artistic way that appreciates, you know, randomness and serendipity, or you're going to get real frustrated and not want to be a computer programmer anymore.
That does make me wonder like if statisticians are kind of like have a bit of a heads up there because you're so used to the idea of like randomness. Like I always like found this idea of like, you know, like sort of quantum physics. And it feels to like many people, I think that if the foundations of the universe are probabilistic, that's just like horrible. To me, that just like, I'm just like, of course it's that way. That totally makes sense to me. Like why does it, why does it need to be deterministic?
Exactly. And I think it also is a lot more inspiring in the sense that, you know, the real world is messy. And if you see something that's unexpected, then it might inspire you to go a completely different way or to see something in a way that you wouldn't have imagined necessarily. And it's also just a lot more fun. Like, I feel like one of the biggest challenges right now is that, you know, universities have kind of over-indexed on problem sets. And now like if you have a problem set, like good luck finding a person that's actually going to do the problem set as opposed to just like paste it into whatever their favorite chat bot is and get a response back. And so they're not quite learning anything unless you kind of set up the constraints for the assignment to be like, all right, well, today you have a whole bunch of different hardware. You're going to, you build it and then explain whatever physical processes are required and throughout the building phase. And if you're trying to connect something and it doesn't work, you have to explain why it didn't work and the physics behind that. Like that's a much cooler assignment as opposed to just like, hey, you know, what is the velocity of A versus B?
Yeah. When I like think about teaching like data science today, it's like, you know, the cost of creating a shiny app or a little interactive applet to explore something is now like zero. Like you should be doing that all the time. Like we don't need to ask these like deterministic, is this right or not questions. We can be like, hey, create a tool to explore this and then tell us what you found. Yeah. Or create your own dataset. Like figure out some, like figure out a really gnarly question that you want to answer and then find a way to automate the creation of a dataset that will help you answer the question.
Yeah. I actually had a really like, I had a use, like I tried this with, like I only realized like I flew to California like last week when the lines at Houston's airports were getting really, really long. And like only at that moment, I was like, oh, I need to be scraping the wait times and like recording them in a parquet file on GitHub. And so I like, I did like a little bit on the website to kind of find, and I was like, oh, there's actually a JSON endpoint I can call that gives me nicely formatted JSON. But I was like, oh, maybe like maybe there's like a historical API hidden here as well. And I was like, hey, Cloud Code, like, can you just like try this out? And it came up with like 15 different like plausible looking URLs and tried them all out. Like none of them did actually yield the historical data. Like one of them looked really promising. Like it was like the API slash date, but then it just returned the same day. But just that, that kind of like exploration you can do now, like you don't have to know a ton about API. You need to know what an API is a bit about how it works, but that ability to just like iterate, create datasets that matter to you, collect them and store them. I think it's really, it's really cool. Yeah. And if they matter to you, they probably matter to somebody else too. In which case, like suddenly the world is filled with a lot of, a lot of more datasets that can be used or expanded.
DevRel at Google DeepMind
So we heard a lot about your projects and we learned that your projects actually involve a lot of important things that are coming out. Like you've hidden your vegetables in them and we just didn't know we were eating them. I'm curious how it ties into being a developer relations engineering lead at DeepMind. Are these all connected somehow? Oh, a little bit. Yep. So most of the, most of the models that I'm using are DeepMind specific models. So, so they would be like the different flavors of Gemini that we have, mostly not pro, mostly flash and flashlight and, and some of the others, the nano banana models, VO for video generation. We also have an open model family called Gemma, which we also exposed via the API. So you can either download it and use it yourself, or you can kind of use it via our API for $0, which is quite cool. And then also there are some tinier versions of the Gemini models that are small enough to fit on mobile devices. So we've embedded one within the Chrome browser, we've embedded them into pixel devices, and you can kind of use the onboard intelligence without Wi-Fi connection for, for $0. And that's, that's getting better by the day as well.
But, but so those are kind of the, the products that we would expect developers and increasingly like people who are developer adjacent to use to build things. And I'm, I'm actually really, really excited about getting information workers to be able to create and to use these tools. So not just, not just people who are coming from engineering backgrounds or who, who understands software engineering, but like all of the people outside of that world.
What's, you said information workers? Yep. What's a information worker? Yeah, so it's just me being a barbarian. No, no, no, no, no, no. Excellent question. So, so like information workers, I feel like it's, it's such a nebulous term that could apply to, to pretty much anybody, but like people who, you know, are data analysts or people who might be like working, working in the sciences to like take in primarily CSVs and like do, do interesting analyses on them.
Like one of the first things that I used TensorFlow for back when it came out a long, long time ago was one of the, the projects that they released with it was being able to classify five different kinds of flowers, but you could also just like have five different kinds of things that you wanted to classify and, and do, do that classification process pretty simply. And so in the earth sciences as well as in the biological sciences, but there, there were a lot of grad students, self-included, who were having to hand classify like different kinds of features in reefs or different kinds of you know, shapes of things on Petri dishes or whatever it is. And instead of having, you know, a grad student spend a month like going through and doing that, like you could do it really easily just with the most basic classification task. And so, so like all of these people who are working in the sciences there are tons and tons of those kinds of use cases that are ripe for automation, that tools exist that would like save time and energy and accelerate the scientific process that nobody just knows about. So, so like now that the models are good enough to do this kind of work, like just blazing a path for people who are experts to like automate away the parts that are frustrating and like focus on the parts that are fun.
I think like inside businesses too, there's like a lot of people whose jobs like center around Excel spreadsheets and like painstakingly carefully copying bits from one sheet to another sheet and making sure they line up. Or like getting information out of a JIRA ticket and putting it on a spreadsheet and I've got a PDF and extracting three bits. There's all this stuff that's just like really like no one enjoys doing this like it's often like it's high stakes. Like, you know, it's really easy to make a mistake. It's like no one enjoys doing that and there's just so much potential. Yeah, and it also is like very hard on the human body too because if you're like copying and pasting things like a lot of people use mice for that in which case like the the potential for RSI is like the repetitive stress injuries are really high. And so so like anything that can take away like the parts of work that are boring and like not fun I think is a is a great use for these models.
Choosing the right model for the job
All of these all of these models that get released they're basically like supercharged engines right. And so like one of the one of the things that can be a little bit disheartening to hear sometimes is that people want one model to kind of be the one model that they use whereas I think that what we see is that you it's it's a much more effective path to like pick a model based on what it's really really good at or what you need. Like if you need a model that has really low latency and that is really really cost-effective and that can get the job done for a given subset of tasks like pick that don't reach for like the highest end model every single time. And I find like so for the Gemini models they're really good at analyzing video, PDFs with images embedded in them, audio, like translating between different languages, like doing real time interactions those sorts of things. And I find that the anthropic models are exceptionally good at kind of writing in a way that feels like I'm talking to a friend and also writing code.
And so so if I couple together like Gemini's ability to understand video to generate images to understand PDFs with like images embedded and then also anthropic stability to like write code and then to maybe like plan out what the work should look like then that's a really magical experience. Whereas the if you were trying to use one model to do all of those things like you would just not have a satisfying a satisfying journey. But that's but it's not I guess answering which is just like it is a 24 7 sort of situation of like constantly trying out new things and seeing what works for you and what works for the different tasks that you care about.
It feels exhausting sometimes right like I've never really felt like FOMO in my career but now it feels like sometimes it's almost like paralyzing like I can't be like if I'm working I'm like oh my God maybe there's a new model that just came out that would like do my work for me or like you know do what I'm doing now better. It is like it's an exhausting time to be. This is the AI psychosis.
Yeah it's it is definitely like and the cost of writing software is going to zero. But that means that taste is more important than ever right. Like so the ability to the ability to create things that feel still human and special and serendipitous like like one of the one of the things that I loved most about you know like reading Byte magazine or like whatever whatever else is that I would sometimes find a thing that was something I absolutely needed at the time but I would have never known to go look for it myself.
And now I feel like with with AI kind of driving you know the content that you see on social platforms or like the code that gets generated in a specific style or format or tone and that kind of like again is forcing people into silos or like one way of viewing the world when the thing that that's really magical is like helping people understand that the world is bigger to see it in a different way. And so so like that I try to view the models as just tools and then like part of my job is figuring out how to take their outputs and to craft them in a way that would resonate with with people.
But that means that taste is more important than ever right. Like so the ability to the ability to create things that feel still human and special and serendipitous.
That really speaks to me as like somebody who has developed open source and telling people all the time like there's no language for and you understand like you know it's not R versus Python it's the right tool for the job and hearing you say you know that applies to models as well and just trying to deconstruct that in my mind like this is the model I should be using for coding this is the model I should be using for helping me with docs or something like that feels very empowering. And we have these muscles already. Exactly. And it changes it changes monthly. So like the ability to if not weekly right like the ability to just kind of try things out and to to accept that things will change and then like again statisticians have the edge like and people who have worked with data have the edge because we all understand data drift. So so it's it's just never been a more exciting time to work in this space. But also I I absolutely agree it is kind of exhausting.
I know we're getting long and you have to hop a flight to L.A. for a hackathon. Heck yeah, it's going to be awesome. Yeah it's the it's a generative media hackathon so it'll be like a VEO but also NanoBanana and also hopefully like the Lyria API as well so like people can create music. Oh nice. I also don't doubt that on the flight there's a high chance you push some kind of app. Just the time you're in the air I fully believe that's possible.
I know we learned one really fun fact that we chatted about a lot too which was that you have an app that roasts your last song choice. Oh yeah on Last.FM so like the last so Last.FM I am also like a super super fan of like I have a Scrabble history that is like a decade deep. So so like if you look at pages listening choices like from from the last decade plus like there's definitely been an evolution but the but it will tell me like based on what I've just listened to what my what my estimated age is and then also like how pretentious am I or like how basic based on those choices.
Could you if you had to pitch humanity on why they should get roasted on their last song choice how would you do that. Well so so we all take ourselves way too seriously like we and and in all honesty like if you if you're listening to the same thing over and over again or reading the same thing over and over again or using the same model over and over again like the part of the joy of being a human is is like learning from new perspectives. So like if you if you get roasted like it's a good incentive to kind of laugh at yourself a little bit and then maybe experiment with something new. Yeah. That's a great takeaway message.
I can't think you know I'm so inspired by your yeah your just ability to like code and mix things and just find serendipitous combinations. So can't thank you enough for for coming on and I'm so excited for the next one or a dozen things you you do. Thank you. Thank you so much for having me. And I really feel like you know there's never been a more more interesting time to care about data and to care about the way in which information is communicated.
The Test Set is a production of PositPBC, an open source and enterprise tooling data science software company. This episode was produced in collaboration with creative studio Adji. For more episodes visit the test set.co or find us on your favorite podcast platform.
