Episode 23
AI Can Build It. It Can't Make It Good.
Published · 1 hr 22 min
Paul Bakaus created jQuery UI, sold a startup to Zynga, and spent nearly a decade at Google — then went solo to prove one experienced builder, amplified by AI, can do what used to take a team. His company Renaissance Geek is backed by a16z; its first product, Impeccable, stops AI coding agents from shipping design slop.
What Paul talks about
Pick a question to ask it of this episode. Answers come from the transcript.
Transcript
Transcribed automatically, so names and words may be wrong. Each time opens the video at that moment.
0:00Paul Bakaus: The most important skill right now, where I think a human is needed is to remove things, say like what not to do. This is a misconception that Steve Jobs used to be this like super creative genius, but I don't think that's what made him so unique. He was just the greatest editor of all time. He would just say no to 99% of things, and the 1% that it's a yes to it made it to us. Today's lab looks very different than the slot from a year ago. I don't want to hire ten people to do the actual building so that I can be the middle manager. You are the one who is very good at building in the first place. And that's why you have customers.
0:30Julian Weisser: What is the bare case for being a solo founder?
0:33Paul Bakaus: It takes a certain type of crazy to found something in the first place, but I think not knowing whether you're actually crazy or not, not having a sounding board can be really, really hard sometimes.
0:41Julian Weisser: What is the case for solo founder?
0:43Paul Bakaus: You only have to account to yourself. It's a big mistake to wait for the right person to join you. Start it.
0:51Julian Weisser: Can you share a little bit more about what a Renaissance geek is and and why? It's the era of of older founders?
0:58Paul Bakaus: Yeah. I mean, I'm not saying younger founders don't have it, but I think in my case, and I think I'm seeing this over and over. I just saw a bunch of tweets along those lines as well. It's an interesting time because right now, when you have a lot of intuition for what works and what doesn't, and when you learn a lot about, I don't know, different roles in software development, like the smaller teams, larger teams, whatever. Like in my case, I have started my journey as an individual contributor like many. Right. Front end engineering, design, etc. and then I started going to FAANG. I did my own startup. I went to, sold it into Zynga, went into FAANG, worked at Google for a couple of years. So I basically did the whole thing from like engineer to engineering manager to manager of managers. So and at some point you kind of feel like, okay, well, in order to climb the hills, you have to give up founder life or you have to give up making things yourself. Um. And I hate that. In fact, like I thought, that's the only way to have impact. But now, through AI, I think if you have good enough intuition for what works and what doesn't, and you've learned enough about your craft and your adjacent crafts and you know you have less hidden unknowns, basically less unknown unknowns than before. And you know what you're not good at? I think it's a kind of an ideal time to work with AI, to simply shape whatever you want to shape. And so that's how I feel about being a founder now. I think I might not have the same amount of energy as a 20 year old, but I can make up. I can make make up for it in intuition and in craftsmanship.
2:48Julian Weisser: It feels like in a lot of ways, you've been at the forefront of kind of unlocking the ability for more people to build using the internet and the latest technologies. Over the last, the last while. I mean, maybe you can take people who are listening through kind of like the jQuery stuff and the and the, the, the Chrome stuff. And uh, to where you are today is, it's a really interesting arc. And, you know, I think that at one point you describe this as, uh, lowering the floor and then raising the ceiling. So maybe you could share what that actually means and sort of how your kind of life has led to you kind of consistently working on this.
3:31Paul Bakaus: Yeah. For sure. I mean, at the long for the longest time, I actually called this anti gatekeeping because I wanted to open the gates for more people. Like, I mean, whether that's Gamergate or, you know, whatever. There's so many different moments in internet culture where one group didn't allow another group to participate. And that's been a recurring theme, I feel for my internet experience, at least for my digital experience. And the first time I noticed that was as a as a teenager, I started putting myself out there. I kind of called myself a prototype creator of sorts, because for me, I wasn't really that interested in the syntax of syntax of coding, but I wanted to put a website out there to just have my my voice heard. And I think that was kind of like the quickest way to do it. Um, so put a website on your own computer, connect it with a plug, right? And then the whole world can see what you're up to as opposed to, I don't know, like going to TV or radio or whatever where like you have to ask for permission to get accepted. And so I thought that permissionless culture was really cool, and I wanted to do more of that. And so I invested a lot of my career into the open web. But then a couple years later, I noticed that building anything really amazing and interactive and beautiful on the web had a lot of gatekeepers. So there were all these hardcore JavaScript engineers who were like, no, no, no. If you're a web designer or if you're just like somebody who's not a programmer, you can't participate, right? So this was pre WordPress or, you know, around the time WordPress started to become a thing, it wasn't really CSS weren't really a big thing yet. Um, and that never really sat right with me at the time. I wanted to build more interesting experiences. I worked on these large scale JavaScript applications for Deutsche Telekom, T-Mobile back in Germany. And that was pre Gmail, right? Back then, those were actually like the biggest, I would say JavaScript clients like web clients that would do email and calendar and stuff like that. Um, maybe not as cool as Gmail, but you know, at least it was a really interesting large scale project. And
5:45Paul Bakaus: back then there wasn't really a lot of JavaScript work going around. So it was very, very interesting, but I hit the edges of what was possible with just vanilla JS all the time. So I looked out for frameworks, and one of those frameworks that I found that opened the gates for a lot of people was jQuery. So jQuery was like a couple of months old. It was this quirky JavaScript library that a lot of people found really odd at first. I remember that it was like people were like, this is a weird way of scripting. I don't know if that makes sense, but it gave so many web designers and people who maybe didn't call themselves engineers the chance to participate. And I love that. I love that it gave me the chance to participate in a bigger way. And so I invested a lot of my time into jQuery, fixed a lot of bugs, became part of the core jQuery team in the process, and then I was particularly interested in UI, so I invested a lot of my time into drag and drop accordions, whatever was needed to build rich user interfaces At the time there was a library, a third party framework called interface at the time that a Romanian developer created and was also really buggy. So I fixed a lot of the bugs and helped participate and contribute that too. And the guy became really busy. I remember at some point I wanted to do his own thing, and then John Reznik, who created jQuery, asked me to to start an official library for for jQuery, and I turned into GUI, which gave me an interesting front row seat at the web one zero to web 2.0 conversion. I would say going from static sites to more interactive experiences.
7:34Julian Weisser: Now we'll talk more about sort of the transition from that time to, you know, working on DevTools in Chrome and, and to, to where you are today. But it's really interesting because I think that a lot of people, you know, they they might be watching this or less. They're going to say, well, this guy has worked on, you know, all sorts of really big projects. And he's, you know, worked at Google and he like, sold a company to Zynga. It sounds like he's really deeply enmeshed. And he, he just raised a massive round from a 16 Z. So he must be like, you know, he's an insider, right? But growing up you were pretty removed from all this. As I remember, you came the first time we met you, uh, you came to a late night coffee shop that we hosted here at the house, and you were telling me about this, and it turned out that you, uh, you grew up in the Black Forest in Germany. Uh, a town that I actually studied abroad in. Really briefly, um, and is about as far away, both geographically and, uh, maybe, uh, from a mindset perspective as what you'd expect to be sort of in the Silicon Valley. So maybe share kind of what it was like growing up in a place that was pretty removed from startups and technology and sort of how you ended up, you know, getting involved in all this is I'm assuming that this was still pretty early on in your life that you started tooling around with, with JavaScript and then getting involved with the jQuery team.
8:58Paul Bakaus: Yeah, totally. I think back then it's a good point. It wasn't really perfectly obvious, and I didn't grow up with a tech family in Silicon Valley. Right? Um, I did grow up in the Black Forest, and I also moved ultimately moved away from, uh, from that place because I always felt like it was like ten years, 15 years behind when it comes to technology now. Uh, no shade. I think there's some cool startups there now. I mean.
9:24Julian Weisser: Yeah, it's incredible.
9:25Paul Bakaus: Black forest labs amazing, right? A huge success story for for Freiburg, for the Black Forest. Um, but yeah, back then, uh, there wasn't really a lot going on, right? And I, I know I read about Google, I was really interested in Google. Uh, my mom reminded me recently that I always wanted to work for Google, and I totally forgot, Like, I worked at Google at the time. And she said, you know, you always wanted to work for Google. What? Um, but apparently that was my dream when I was a teenager. Um, and, uh, and then I the web for me was kind of a normalizing factor because at least in the early 2000, uh, they went really so many pockets of the web, I feel like, you know, it was a much smaller crowd that even was active on the web in the first place, was all. At least where I was at was all in English and, um, and not that many subcultures yet, you know. Um, I mean, that's arguable, but it really felt like a big village in ways that connected me to the rest of the world and where I could be at the actual cutting edge. I mean, the kids call it frontier now. Right. Um, as opposed to, uh, I don't know what's happening in local offices, you know, down the road, which might still be. You know, it might not be that relevant anymore. Right. And that helped me tremendously. I remember right clicking. I mean, this is a similar story that many had early on. Right clicking on websites view source, reading the source code. Just seeing what's going on. It's also interesting because you then build things and then you never know whether you are hopelessly late or really advanced. Like you have no idea. Right. Because there are no other people to talk to. I mean, I was just this weird kid in a basement who was coding and putting things out there, and I got some early validation when I worked in a, um, one of my summer jobs, I think, was working in a, like a, like a phone shop, and they had like a support program thing, and they didn't have any software to manage support requests. So, um, uh, the, the owner realized I could build him something. So I did, and he was like, whoa! This is crazy. And so I got some initial early validation through some of these odd jobs. But it took a while until I realized, yeah, okay. I think this open source stuff, these things that I'm building, they're actually very useful to more people than just my local community.
12:00Julian Weisser: It's interesting, too, because you're talking about back then when you were getting started, it was relatively early in the days of the internet. Um, and, you know, you could be working at some odd job and the owner could say, oh, could you build that for me? And in many ways, the story is still the same right now. Right. I mean, there are people who are, you know, young people who are starting, you know, maybe their first job outside of high school, maybe it's a job while they're in college, and maybe they're not even thinking of themselves as engineers. Like you were, you're much more of a coder mindset. But nowadays there's so many problems and things that could be built and addressed with the tools that are available. And it feels now more than ever you could actually get a differentiated insight for something to work on through some odd job. There's a person in the Solo Founders program. He had a high school internship. He ended up then going, he really enjoyed it, but he ended up going to school at college. And you know, after he was in college, he said, well, that high school internship taught me about this problem that I really want to solve. He ended up working on it. Now he's at 3 million ARR, completely on his own, you know, and it's and it's all from that insight that he developed at this internship. And you can just take those insights and go build businesses now. So I'm curious um, what's the story of going from, you know, being a contributor to such an incredible sort of foundational infrastructure? What's the transition from that to, like, going and starting your first company? What did that look like?
13:27Paul Bakaus: Yeah. Um, and it's it's it's funny you mention the internships too. Um, I think the I've done a few of those over the years, and I remember creating my own consulting business when I was 11 or 12, and I had to go in front of the, uh, in front of the city office. I remember that in my local community to, uh, to get a special exception, to be able to create a company.
13:53Julian Weisser: Because you were so.
13:54Paul Bakaus: Yeah. Yes. Because I was so young.
13:56Julian Weisser: This is interesting. So this was in Freiburg.
13:57Paul Bakaus: Was this. This was in in a city near Freiburg called Volker.
14:01Julian Weisser: Yeah. Okay. So. So you actually need to go get permission from the city? Yes. Interesting. That's not something that happens in America, I don't.
14:08Paul Bakaus: Super strange.
14:09Julian Weisser: Okay. So? So you go. What happens when you go up to talk? You have to actually talk to them in person.
14:12Paul Bakaus: Yeah.
14:13Julian Weisser: Yeah, yeah. What did they say? What were they asking?
14:15Paul Bakaus: You get a hearing and they, you know. My mom had to come along with me. Right. And they're like, wait, this. This boy wants to create a company. Like, how does that make any sense? And then just please explain. And then they gave me a special permission.
14:26Julian Weisser: So it worked. They let you do it?
14:28Paul Bakaus: It worked. Yeah. I didn't make much money with that company, but it did work.
14:31Julian Weisser: Okay. So? So you. So that was your first. That was your first kind of company. When when did the concept of startups come into play? And what was your first, like actual startup?
14:41Paul Bakaus: Yeah, to to be honest, I almost I always stumbled into my next problem. So I was never really looking to create a company. I was always looking to solve an interesting problem. And that's actually still true today with the first startup that was a game engine startup, so I worked on jQuery UI. I
15:00Paul Bakaus: would say that was a really good success. A lot of people started using it to build user interfaces on the web, and
15:09Paul Bakaus: then I figured out, okay, well, what else can I do on the open web? What? How can I enrich the open web even more? And I was always an avid gamer. I love games and I wanted to bring games to the web. I thought, hey, well, maybe we can anti gatekeeper instead of opening open the gates for everybody who wants to be a game developer, maybe every web developer can be a game developer. So that was my next idea of where to take this.
15:36Julian Weisser: And just to give people an idea, when was this? Like, that.
15:38Paul Bakaus: Was, uh, two, 2010.
15:42Julian Weisser: Amazing. Everybody can be a game developer in 2010. That was that was a great that was a great view of the future.
15:48Paul Bakaus: That was.
15:48Julian Weisser: The.
15:48Paul Bakaus: Idea right now. It didn't really work because I mean, technology, we made technology work, but the distribution was the problem. So distribution monetization wasn't really a soft problem, but we built a whole game engine from scratch that would then be able to power isometric games like Farmville or something like that. And so we made it work on the original iPad, which was really not a fast device by any means. Um, and built this game engine startup, we wanted to build more than just the game engine. We wanted to build an isometric version of Facebook, basically like, you know, a fully visual isometric world as a flagship product that would then sell the engine. But it never quite got that far because, frustratingly. And so this was, um, uh, me and a previous colleague of mine founded this company together and we figured, hey, this is going to be like, this is a novel idea. Nobody has done it before. How hard is this going to? Is it going to be to raise some funding for this? Right. It turns out very hard. It turns out in Europe at the time, the most successful investors were the Samberg brothers, who created a copycat culture in Germany in particular. That made it very difficult for a new founder who doesn't have any successful commercial track record, at least to start something new, completely new that isn't proven. So the number one question that we got from every investment meeting was, um, well, is this a proven idea that we can invest in? Right? No it's not. It's a new idea. And so it was really, really challenging to raise capital, but at the same time it was very, very easy to get interested customers. So we had all of these very large companies lining up like Microsoft wanted to license the engine. I believe Zynga wanted to license the engine. Many big names that are that I didn't see coming. Like knock on the door of a small German startup. But there was a lot of demand. So in the end, we went through an acqui hire and got acquired by Zynga, where I worked for a couple of years building R&D. But yeah, it was a it was just the search for the next big problem that led me there. And the next big problem was bringing games to the web.
18:07Most people think that starting a company without a co-founder is a bad idea. We believe the opposite, that solo founding will become the default way great companies get started. And that's why we built the Solo Founders program, where solo founders spend three months in San Francisco building solo together. Our alumni say it's like having co-founders, but getting to make their own decisions and for cohorts, then we're starting to see just how much solo founders can accomplish One secured a formal partnership with a major US government institution just five months after incorporation. Another hit 20,000 GitHub stars and 3 million downloads, and a third got to 2 million ARR before making a single hire. The demand for the program continues to grow. Our first cohort got 1000 applications for six spots. Our fourth cohort got 4500 for ten, and today we are officially opening applications for cohort five. We'll select about a dozen founders. I'll work closely with each of them and will invest $100,000 in every company. We kick off September 10th. If you're building solo or you're ready to start, apply at solofounders.com.
19:15Julian Weisser: You said you'd worked with your co-founder previously. What was that? What was that like and sort of how did you decide to end up starting a company together after working together previously?
19:25Paul Bakaus: Yeah, we worked in the same agency back in Germany. Um, as this was, that was my actually very first, uh, um, W-2 job sorts salary job. And we just got along really well and we meshed well. And he was also, uh, really avid gamer. And so we figured we have something in common. And he saved a bunch of cash to invest into the company. And so it was it was a good. It worked out really well where I brought in the tech chops. And he, uh, was the CEO who would, you know, try to raise and, uh, and set up commercial partnerships and do everything around around the thing. Um, but yeah, we just reconnected after after a few years and then got going.
20:10Julian Weisser: That's so cool. So that was around 2010, you were saying. And now it's, uh, 16 years later. Crazy to say. Um, because it probably doesn't feel like 16 years and crazy. You're you're now building a company solo. Um, and you were the you weren't you were not the CEO, uh, for that that company that we were just talking about. You're now effectively, at least until you have decided you're hiring. You started out as everything right with this new company. Y y sold this time.
20:42Paul Bakaus: Y sold at this time? Yeah. So now I'm solo. And to be honest, there was this moment in my life last year where I really realized I need to get building again. And so I found myself suddenly without a job. I think this was around March or so last year, and again, I kind of climbed up the hill to essentially like upper middle management or something like that and leading larger teams. And I realized I don't really want to do that anymore. It's not interesting to me. Um, and I want to figure out how far can I push a new idea by myself? How far can I scale myself? Because I've I've read about this idea of the, you know, solo company that becomes $1 billion unicorn, right? But I didn't fully believe it yet. I'm like, hmm, I don't know. Like, is this real? Like, can you really be a hundred x engineer by scaling yourself that way? And I just wanted to prove it to myself. I think that was the first. That was the first moment where I thought, yeah, let's let's give it a try. Um, let's see how far I can push it. Um, and so I built myself a lot of tooling to scaffold. Um, I took on some really intentionally very challenging contract projects that would replace, like, you know, 5 to 10 person dev agencies to see. Is that possible? Um, and I think the answer is yes, but we're still early and we're still figuring out how to, you know, I think the interestingly, the biggest problem right now is attention. I think I can
22:19Paul Bakaus: use a lot of agents, spin up a lot of agents that would work for me, but my attention span is limited. So that's the most challenging aspect. Peter Steinberger talked about this a couple of days ago as well.
22:30Julian Weisser: Yeah. What did Peter say in particular that resonated with you?
22:33Paul Bakaus: Uh, he talked about detention. So he talked about how, you know, you can create these software factories and that you can scale almost anything related to software development except human attention. And so now he's he's optimizing for his own attention and figuring out how to do effective work in bursts. And that really resonated.
22:53Julian Weisser: What have you what have you learned in this process because you've been at it now for a little while building. Yeah. The stuff that kind of like was the precursor to the company, which is building impeccable. The company is called Renaissance Geek, but what are the things that you've learned so far about this, about your own sort of insights into your own attention?
23:11Paul Bakaus: I think the most important thing is that I have to protect my time building. So for the last couple of months, um, initially, I intentionally did not raise any money because I wanted to give myself time to gain momentum and just create maximum value. So every time I, I wake up and I still do this, by the way, I wake up and think about, okay, what value am I going to create today? Because a day without creating value is really sad. So I think about that every day and that drives me. And for the first couple months of the startup, that's the only thing I would be obsessing about. Like, how can I make impeccable my project better? How can I make it a slightly, slightly better? How can it solve a current user problem? Um, and there are so many things of the CEO job, of the founder job that are not about creating user value. And that's that's something that I'm very, uh, focused on to make sure that I protect that build time. And I don't think that's unique for me, but I'm, I'm trying my utmost possible to contract the way or like just remove a lot of the actual operation work so I can focus on building. I also don't want to change that, by the way. I don't want to hire ten people to do the actual work, to do the actual building so that I can be the middle manager again, like there's zero interest in that on my side. I want to operate completely differently.
24:45Julian Weisser: So I know, at least at the time, that you wrote the blog post announcing the company and the funding and the GitHub partnership, you talked about hiring a chief of staff. Are you still hiring that or did you find that person?
24:57Paul Bakaus: I found the person. I can't really talk about who it is for sure, but yes.
25:01Julian Weisser: Could you share could you share a little bit about kind of how you think about hiring a chief of staff as a solo founder who's getting started? This is one of the first hires that you're making. What have you heard from other people about that? Maybe you maybe you already had some intuitions about what you were looking for. Um, what advice have you gotten about making that type of hire?
25:20Paul Bakaus: Yeah, I think I initially thought I'd need a combination between chief of staff, head of operations and executive assistant. One of the first pieces of feedback that I got is, that's a terrible idea. Do not try to make that. Also an executive assistant. And so feedback heard right. Makes sense. The work is different. But I, I put the EA part into the job description because and I still have I don't have EA in the job description anymore, but I still have bullet points that say like, you know, do grunt work or whatever and have some examples of really basic, intentionally basic work because
26:01Paul Bakaus: I'm the type of founder, but also a manager who will do that naturally. Like, I mean, even in my previous job where I led a pretty decent sized team from time to time, I would bring somebody a coffee if they needed, if they looked like they needed a coffee. Like, I, um, wherever I could create value. No matter what job, no matter. No job would be too small for me. And that low ego mentality that sort of like everything is my my job. I needed that in that role. So that's very important for me. I also intentionally did not call it head of operations because it would attract sort of like McKinsey consultants who might have been in like a FAANG position for a while and are too senior and maybe don't really understand the grind of a small startup anymore. That's the other thing. Um, so intentionally, if you look at the job description, um, it's not boring. Um, it's actually written the way I would write it. Just naturally, when I explain it to you, it's like, hey, this is a job where you have to get shit done, where you really have to roll up your arms and just do whatever is needed to, uh, clean, make sure that we all can spend our time on the most effective use of of of our skill set. That was most important to me. And so it's, um. Yeah, you need to find somebody with low ego, um, who can naturally transition along with the company. I mean, maybe that starts being, for example, right? Initially, it's maybe a bunch of investor projects, um, some certifications that we still need. Maybe it's like setting up some bank account or getting more employees credit cards, but then later on, it's a special partnership with some large company, or it's, uh, something that is completely different, like
27:59Paul Bakaus: set up stripe at scale. Um, it could be anything, but I've worked with quite a lot of, uh, operations people in larger companies like Google who would be eaten alive in that role. So that's something I will say, right, who have focused on just one aspect of operations, and they think they can do it in the real world, but they can't. I can guarantee you they can't or they're not prepared. At least maybe they can learn how to do it. But I had to have had to have that conversation with a few of my friends from these larger places and, and, uh, you know, give them some real expectations.
28:43Julian Weisser: And the reason I ask about this is because, um, my guess is that when you're building your first company and you were thinking about who you're going to hire, um, chief of staff is probably not the second hire or the first hire. I don't even know if you had a chief of staff at that first company. So I just wanted to get a little bit more about the philosophy around hiring a chief of staff for an early stage startup, especially as a solo founder, because, um, you know, there's less you don't have co-founders to have sort of early division of labor. Um, and I think it's it might be a role that becomes more prominent earlier on at solo founded companies than maybe it would be at traditional sort of multi founder companies.
29:22Paul Bakaus: I see. Yeah I think that's spot on. I think the reality is I need that chief of staff to protect my time. I think that's the most important goal here. I am a very reluctant CEO. I would say I really don't want to be the type of CEO that does everything that a CEO does. Like, you know, the operations bits. I never loved it. I always loved the building. Now there are multiple ways of solving that, right? One is you hire the people who actually do the building for you. And I think that's what most people do, right? Most people, instead of hiring a chief of staff, they hire an engineer, a designer, a product manager, whatever is needed to actually get the building off your plate, right? So now you're getting the building off your plate and you're the chief of staff, essentially, right? You are the operations person. That's that's now your role. I think that's a trap. I think that's really silly because, like, if you are the one who was very good at building in the first place, and that's why investors invested in you and that's why you have customers, etc., why give that up? That doesn't make any sense. So I think this is probably true for a lot of solo founders right now. And so I guess my one recommendation would be don't fall in that trap. Much better, in my opinion, to hire somebody who's very good at operations. Also, like a chief of staff's left operations hybrid role, who can scale up with whatever operational stuff is needed and have them be the the acting person that, you know, takes all that clutter of your, um, yeah, of your plate. So you can actually focus on building.
31:01Julian Weisser: Super, super good advice. I think it's something that we will see a lot more of. Um, let's talk about let's talk about impeccable. Let's talk about Renaissance Geek. Um, you know, I think that the first thing to say is this is clearly struck a chord with a lot of people, because it's got tens of thousands of stars on GitHub, uh, for impeccable itself. Um, maybe you share for those who were hearing about it for the first time what impeccable is and then why you decided to start a company around it.
31:29Paul Bakaus: Yeah. Impeccable is an agent skill, I would say, first and foremost. So skill for those who don't know, is a way of extending your coding. Harness your coding agent with some additional functionality. In this case, it's one that makes your coding agent better at design. So it makes you better at design, hopefully, but also your actual AI better design so that it doesn't produce the same bad outcome. That is clearly I mean, you look at it as clean made by AI. You don't really want that. You want something intentional, and you want to steer it in the proper way to get to where you need to go. So that's impeccable in a nutshell. It gives you the vocabulary of design, and it also comes with a visual iteration mode that allows you to generate variants on the fly together with your coding agent, and then it removes AI. Slop. So slop is a big topic nowadays and slop is also a moving target. So like today's slop looks very different than the slop from a year ago. And impeccable. It sort of does two things. It creates a really solid baseline. So like decent good design. And that's what I meant by like lowering the floor. So basically allowing more people to participate, but also um, raising the baseline of, you know, decent design. And then the second one is getting from good to great. That's still where like a human is needed right now. And inserting that human at the right times is super important. And that's also something that impeccable focus is on. So yeah, it's been a bit crazy. I will say I have impeccable was something that I've built for myself because I needed it. Um, I became really frustrated at the time working with Claude code because it would never quite understand my intention. I would say like, make this bolder and then, you know, it turned everything black or whatever, like blue. And it's like, that's not what I meant. I mean, like, no, it needs to be, you know, attracting the eye of the consumer more. And you shouldn't move away from my design system like it needs. It means something specific in the world of web design. And I noticed when designers will be using cloud code and I am one. But, you know, I've also worked with large engineering teams and coached them
33:47Paul Bakaus: doing these contract jobs. And I noticed when designers would use these tools, they would get better outputs. And really the type of language that you use matters. And so I package that up and put it into a scale for myself first and foremost. Um, impeccable is, by the way, not the first open source project project that I shipped earlier this year. I released a whole bunch of others, but impeccable was the one that had the most impact on people.
34:14Julian Weisser: Similar to OpenClaw, how Peter had released a lot of other things. That's right before that, and they all sort of fit together. But that one was the was the big one.
34:23Paul Bakaus: Absolutely. Yeah. And so it, uh, yeah, it really struck a chord with people in ways that I didn't expect. And then it just developed a life of its own.
34:33Julian Weisser: It's really cool because, I mean, we use impeccable all the time. I think the thing that we like the most about it is we talked about with regard to understanding a design system versus just being good at sort of baseline design ideas and concepts. Uh, because as you said, usually when you give a prompt to claw to code, um, unless you're extremely specific and even maybe sometimes if you are, uh, it still can tend to sort of ignore, uh, some of the nuances and it will shift away from maybe the design system that you have in place to something else. and maybe that's good from a prototyping to see what this could possibly look like. Perspective. But it's not a good, you know, thing for from a production perspective. And I've been really impressed by just how much we could take a design system from one place that we have, um, for solo founders and be able to spin up new applications that are in the solo founders universe that have a lot of the flavor and the verve that we've developed for solo founders, but could be translated and ported over to new systems, new user interfaces. And I know for a fact that when we try that with just something like Claude Code or Codex, it's actually really lacking. But when you when you loop it impeccable, um, it actually works quite well. What's actually, what's actually going on behind the scenes there? What sort of what was the insight that you had in terms of how to make it so that it doesn't stray? And it also sort of follows these principles?
36:04Paul Bakaus: Yeah. I mean, it started with the vocabulary. So basically allowing you to steer in different directions. But then why does it. Why does it work? Why does it say in brand? It's a good question. The first thing is it does. When you initialize impeccable, it first does a product interview with you. And so it asks you about your app or your website or what you're building. Right. And it's not just superficial. It doesn't just ask you what colors does your page use or whatever. And sure, it looks through a code base as well, but it also asks about who's your audience? Who's this for? Turns out if you are building, let's say like an iPad app for kids, right? It's very important for design. Let's say go to a real agency, right? Very important for a designer to know is this website that I'm building for the parents of these kids or for the kids right now, if you go to Lego, you get like a kids website and a parent's website. They branch. And so that's critical. Like in many other design tools, AI design tools, that question never pops up. And so the first is a product interview. The second part is um, design MD. So, uh, Google, the Google Stitch team created this new spec called design MD and that holds your tokens, your topography, a bunch of other things about your own brand, your own design system. It doesn't create. It's not a substitute for your whole design system, but it's good enough to at least stay somewhat on brand. It gives information about the components in your system, and so impeccable creates this design. MD if it's not present for your own website as well and keeps it up to date over time. So anytime you actually don't use a command, it's like, well, I need to redesign this case study website for instance, or section, it will actually load both the product MD and the design MD as context. And then there's also design hooks under the hood that if it writes something and it maybe didn't follow all rules in the skill, There is a hook that fires afterwards in the coding agent to keep it honest. So for instance, it will detect if there's certain AI slop introduced, but it will also detect. For example, let's say it introduced a different font or a color that's not in your design system. It will actually flag that under the hood without you even seeing it. It's transparent. And then sometimes cloud or codex or whatever it supported GitHub copilot will react and say,
38:31Paul Bakaus: um, actually I just noticed that I made a mistake here. I'm going to revert this and stay in your system on your brand. So there's a lot of things that have to be orchestrated to keep you on that lane.
38:45Julian Weisser: Now oftentimes people come across like their business idea in different ways. Or they start out thinking they're going to start a business, or they start out just wanting to solve this particular problem. In the case of impeccable, and that's just one of the projects from your company, Renaissance Geek. How did you actually come to determine that this was going to be a business? Was that something that was pretty intentional from the start, or was it more you were sort of exploring this and you said, you know what, I kind of don't want to do this management thing that I'm doing at a larger company. I kind of want to go and start a company. So how did how did that actually come to be?
39:26Paul Bakaus: Yeah, I think two things happen at the same time. The first one is um, with my partner Anish at Asics and Z, um, who I'm, you know, very lucky to be friends with. Um, I went in a bunch of walks with him in the last couple of months, and I used him as a sounding board to pitch my stupid, hopefully some of them stupid, some of them not so stupid ideas too. And at some point, I think we both had we both got to the conclusion that there's probably enough there to even even if like two thirds of them don't work out, I'll figure it out. So that's the first aspect. That's beyond impeccable. And so as a solo founder and as a founder in general, you're always going to have some pivot of some sorts. I mean, it's so rare to never pivot, right? Um, I think that was the first, first important realization that if if I'm now creating a company, there's definitely enough there in my own arsenal of ideas that one of them would probably work. That's what I had to tell myself before starting. That was really important. That's the first one. The second one was with impeccable. Almost every week I get somebody tweeting at me, saying something along the lines of, I don't understand why this is free. Like, why is this free? Or like, I want to pay for this. How can I pay for it? And that's really great. PMF signal, right? I mean, that's a signal that sometimes I would create something like a failed project. And I would hope for this. I would hope for this. So much for this to come. And I was convinced that it was a good idea, but I never got quite got there. You know, people would always be very nice. And, uh, on a call when I were on a customer call with them and was like, yeah, I've tried it out. It's pretty good, but you never quite got that response. And so that's happening organically. Now I'm getting these tweets all the time, and that gives me the sense that there is a commercial story there. There's something that I can I can do here. So that that was the other really important factor.
41:32Julian Weisser: The it's really interesting to release something that just so immensely valuable for free. Um, it clearly gains you a lot of mindshare, a lot of love. Um, what's what's sort of the logic behind it? Or did you originally know that the first thing you'd be putting out for people with the company would be free? And, uh, and how do you think that that maybe extends to other people who might be building things in the future. So how they should think about putting things out. You know, there's there's all sorts of different opinions about focus on growth and focus on sort of distribution first versus focusing so clearly on monetization that other people say, you got to have people paying you immediately. And I'm curious. I'm curious sort of what you've learned from all this and how you think that that might be something that some people can take away a lesson from?
42:21Paul Bakaus: Yeah. I mean, I think maybe I'll do a hot take here, but I think a lot of the plug stuff like product led growth. I mean, it can work. But I do think in today's age where everybody I mean, it's an explosion of new vibe coded products. Everybody is building something. So many people are building something for the first time, and it's exciting, but it also means it's so much harder to break through with an initial audience. And I think if you have no distribution whatsoever, no followers, no no outlet to at least tell a few people about it. Super, super challenging right now. And I definitely felt that a couple of months ago when I embarked on this journey again, because my ex account, uh, I guess Twitter account, I don't know, like I've used it very actively in my jacket days. And I was known for specific thing, and I was sort of like UI slash front end development. And back then I was active. I tweeted almost every day and it was good social media, um, platform for me right then. I completely neglected it for a couple of years. Then I started it using a little bit in the creator economy jobs that I had, but then people followed me for creator economy stuff. And so then a couple months ago, I stopped tweeting again and I tweet about this new stuff. I tweet about AI and design and generative user interfaces and zero interest whatsoever by the algorithm. Right? Zero. And I think these treats are all certified bangers and like, nobody cares, right? And it's so frustrating. Um, and so I realized, okay, well, this doesn't it's not going to work. Like, I, I can put anything out there like the best thing since, I don't know, like, sliced bread, right? Um, but if it doesn't find an audience, I was never really quite the guy who would put on Facebook ads and hope for the best. I always needed some sort of organic spark that would work. And so the first thing I did was to think through, okay, well, how do I how do I optimize for momentum in the first couple of months and put myself on the map again? That was honestly really important to me. Um, because it didn't it clearly didn't work anymore. Uh, the people who followed me from before, I still had a bunch of thousand followers. Right. But the one that followed me followed me for different reasons, and the algorithm didn't pick it up. Uh, and so the first I did was realizing, okay, the X algorithm now rewards value. So I'm just going to create the most valuable thing and put it out there that I can for free to see if anybody cares. And so I've done this with a bunch of projects. Now some of them worked, some of them didn't. But that really was a good strategy for me because then I gained like, you know, a thousand followers here, a thousand followers here. And then at some point, the algorithm changed overnight and picked up the signal and realized, okay, well, he's clearly in it for the right reasons now with the right audience, and now we will reward him or something along those lines. But that's what I tell myself.
45:30Julian Weisser: It also feels like nowadays, with so many people making so many things so quickly, the faster you can lower, the better, the more you could lower the barrier to somebody actually trying your thing and experiencing it, then telling other people about it. It seems like that is just generally quite beneficial at this point.
45:46Paul Bakaus: Yeah, I was so always obsessed about this k factor thing. Right. Um, Through virality. And I think the most important thing is what happens. Like, how do people talk about your product when you're not in the room, right. So you have two people who have tried out your product, and now they have a conversation about your product. That's the really interesting stuff. And that's where the magic happens or not, right? If they're like, nah, I tried, it didn't really work. Right. Okay. Dead. But if they're like, you know what? I told five other people because this is the best thing. Yes, you have something. And I'm hearing that more and more often now about impeccable. And it makes me feel like I'm onto something.
46:28Julian Weisser: What did you learn about virality and K factor at Zynga? I mean, you were there for a little while.
46:33Paul Bakaus: Yeah, I mean, with Zynga, that was pretty much the only thing that mattered when I was there. Right. We tried to create these games at hyperscale, and I think anything, if I remember correctly, anything that wouldn't hit at least 100 million, like die or something like that or more. Um, was was a failure, right? I mean, insane, if you think about it now. But that was the times where Facebook really rewarded games and there were so many ways of gaming, the profiles of people where, you know, Farmville is a great example, right? Anytime you did some action, you click on like, uh, tell all my friends about it or something, right? And then, um, and then it would post in your profile. And so you have this massive influx of profile posts that all lead back into the games. And it was very easy to gamify virality at a time. Now that's dope, though it's not as easy anymore. I think it was really great for a while. And then it became much harder again. And then there's also this thing with the whales. So, uh, I don't know if you read about this, right, but in many of the Zynga games, there were people who were extremely active, the whales who spent significant amount of money, and they kind of carried the whole ecosystem. And so you had virality on one end, and then you had these paying moguls on the other side. And it was very lucrative for a while.
48:01Julian Weisser: How do you how do you juxtapose sort of that kind of very consumer oriented k factor stuff with something that has some? I'm sure there are a lot of people who are using impeccable in nonprofessional ways just for passion projects and stuff like that. But how do you think about virality when it comes to more business oriented?
48:21Paul Bakaus: Yeah, I mean, so I think there's this huge difference between forced virality. And I think that's something that we did at Zynga. And, you know, I was never actually I was rarely building these games directly. I built 1 or 2 games, but mostly I was responsible for the technology behind the scenes. But talking to those game managers who were in charge of these game studios, definitely it was like a it was it was not something that would come organically. It would really make sure that that comes at all cost.
48:55Julian Weisser: Yeah. I mean, same thing with Facebook engagement. I mean, they just like not just Zynga on Facebook but Facebook itself.
49:01Paul Bakaus: That's right. Yeah. But for my business now, I'm specifically not trying to force it. I think there's no good way of forcing, uh, forcing it. In my case, I think either people find it valuable or they don't find it valuable. The only thing I can optimize for is the individual experience. Um, and then and then hope for the best. So it's it's. I haven't done any, uh, outbound, for example. Right. No paid ads. No. Nothing like the only the only thing that I've done is tweets.
49:33Julian Weisser: No. UGC, no trying to get influencers to post about it. That will some of that will happen just by nature of it being a great, you know, a great product.
49:42Paul Bakaus: Yeah. But it has happened. Exactly right. I mean, Fire Ship has done a video about impeccable, or at least a slice of a video about impeccable, and that was completely organic. And people asked me afterwards, was this a paid play thing?
49:54Julian Weisser: No, that's always a good sign when people are asking you, wow, that was incredible. Was that paid? You know, it's like it's like, no, no, they actually just really like that.
50:02Paul Bakaus: But I also I will say I have seen some businesses and I have some friends who are running businesses that don't work without that growth loop. And so you have a product, you have a front door, and you have to make sure there's always enough Facebook ads, always enough TikTok influencers talking about it. Right. And so people come into the front door and then there's massive churn and you just get more people and fix that problem that way. That just isn't very interesting to me. I don't I don't find that idea very pleasant. I would much rather have a really solid customer base and core who loves what I'm building than a lot of people who maybe like wipe code something with it or one shot something and then just like, move away again. It's just not interesting.
50:46Julian Weisser: It also feels very aligned with kind of how you want to prioritize your time. You know, when you're talking about sort of having people join the team to work on certain things while you focus on others? Uh, that that seems to really be in line with it. And it kind of it kind of goes back to this idea that I'm constantly thinking about, which is like the shape of the business, and there are lots of different business shapes, and some of them could be great for one type of founder and really awful for another type of founder. I'm curious, as you sort of discovered who you are and who you're becoming, um, what you've learned about sort of your personal relationship to the shape of a business.
51:26Paul Bakaus: Mhm. I think the shape of the business, but also like personal relationship to customers and to users maybe. Yeah. Uh, one thing that I learned is that integrity is probably more important to me than to many others that I work with. For example, it would be devastating to me to have somebody say, like, I've used your thing and you advertise that something that didn't work. Um, I would feel like a total failure at that point, because then I felt like a snake oil salesman, and and I never wanted that. I always wanted to be respected for my craft and for what I put out there. And so my own sense of like, quality and perfection is very, very important to me. And the same is true for team building and for like creating a business. I think, um, uh, it's very important for me. For instance, like one of the things that I have is be nice, but, uh, be kind, not nice. And, um, I'm trying to be kind by being not nice sometimes. And I think that's a really good way to treat your coworkers with respect by giving them real feedback, as opposed to just niceties that are actually not true are not meant. So I feel like especially in the world of AI right now, there's already so much snake oil. Yeah. Like skills are a great example. Most skills, I'm sure, are completely vibe coded. You created it maybe for your own project. You test it 2 or 3 times and then you ship it and you're like, okay, here you go. And then you send it to others. But this is like building your own software, right? Compiling it on your own computer. And as long as it works on your computer, you think it works on every other computer. That's not how you distribute software. Right. You have to actually test it. You have to make sure it works everywhere else. Um, many people don't know this, but impeccable. Every single line of the impeccable skill is tested. I mean, in an effort to actually figure out. Does it do something? I went to great lengths, and I spent a lot of tokens and money to make sure that everything is ablation tested. You know, if there's like an AI slop rule and it doesn't work. Actually, we removed it from the score because it's so important for me. And still people people will tell me, um, or question, you know, and say like, hey, I don't know, like, I mean, I installed the skill and then I asked to do something, but maybe I also can can do it without the skill. Um, and so at a conference a couple of days ago, I showed up before and after with GPT five five and one. One of it was using impeccable and saying, like, you know, make this case study section builder. And one of them was saying, okay, same thing, same problem, same everything but vanilla. And the differences were pretty clear. Yeah.
54:30Julian Weisser: So I think that we we've covered a lot of interesting ground with regard to your philosophy. Um, talking about things like how how to focus your time as a solo founder. Um, you know, uh, essentially lowering the floor for accessibility to great technology and, like, abilities to actually make things about them out of the world while also, um, increasing the sort of what, what's actually possible in terms of what, what the average like builder is capable of. Um, we've talked about sort of how you've learned that over, over the years at a variety of companies. Um, I'm really curious about your philosophy as it relates to sort of humans and like humans being in the loop for, uh, these creative practices right now. You know, it is really necessary for a human to be involved on that. Maybe last 20%. Last 10%. Uh, but I think that in a lot of ways, it seems like your philosophy is around human involvement sort of perpetually. And the idea that, um, humans are, are essentially having a challenge with regard to, uh, kind of being able to pass their intent successfully to the AI to actually have the AI execute based off of what they really want. Can you share a little bit more about your philosophy around humans interacting with AI, and maybe that can we can go a little bit onto like interface side of that, but also just more of the general prescription around what the, what the real problem is, uh, with, with humans and AI right now.
56:06Paul Bakaus: Yeah, absolutely. Yeah. So with humans and AI,
56:10Paul Bakaus: there's two conversations right now happening. And I just came back from a conference where a whole bunch of people were talking about loop mixing and software factories, and some people call it orchestras, you know, but the idea is the same, right? You create agents, these agents can work to other agents. And at some point you have agents working with agents working with agents. And you might still say, you know, here's my goal. But then all the work gets executed in like days and days of autonomous agenda work. That's one idea that people are pushing. Another idea is, you know, people are saying, no, don't touch AI at all. Or, you know, when you're using AI, do it piece by piece, right? You're just in one thread and then you observe what the agent actually creates. You look at all the code that gets created. You read every line, right. You validate everything. That's the other extreme. I think the reality is actually somewhere in the middle. And when I say like, put the humans in the loop, I actually think when you put them in the loop matters. Um, in my opinion, performances for creative design work and most creative work, I think there's ultimately three big phases and the reality is a bit more messy. You can go back and forth, but usually you have the the earliest stage, sort of the what phase, right? What am I even making? Like you're making a website. Um, what is even on that website? Who is it for? Right. So this is more like product. At that point, I think it's pretty important to be in a loop. Like, if you don't know why you need this, why do you make it? Why do you tell an agent to make it in the first place? Why does the agent determine to make it like that's one, right? Now the other one is the actual building. Now the building aspect. I think right now agents are still very easy and capable, like agents are still very much drifting from an initial vision. And they do that sometimes randomly. So sometimes an agent will work on something for an hour and everything looks great and then shoots in a completely wrong direction. Right. So with without you monitoring and checking in from time to time, you might get terrible results. That might be a temporary problem. But anyway, it happens. And then there's the last part. So let's say the agent comes back to you produce a pretty adequate website. First draft. Now, how do you get it to 100%? I think for those first. For those last 1,020%, you need to actively iterate with the agent. You need to put in your own point of view, your own judgment, your own perspective. One example is most agenda work today. Like most code that's being written is actually too much code. Most articles that are being written are too long, right? Most design that's being created with AI is too verbose or
59:09Paul Bakaus: too cluttered. So the most important skill right now, where I think a human is needed is to remove things, say like what not to do? No, no, no, actually this. You have to remove all of this part, right? Or this, you have to simplify that. And so that type of judgment is super, super critical at the current moment in time. And I also think this kind of like a philosophical argument here to be made. And then there's a practical argument. I mean, I've talked to a whole bunch of my friends at the Frontier Labs about this. And I would say, overall, most people think at the labs at least, that the models will soon be good enough to build something adequate. You know, something pretty good. I also design something pretty good. But the question is, you know, if in a in a philosophical argument, if you have agents creating things for other agents in a world made for agents,
60:06Paul Bakaus: what will we do? Right? How do we come in? Like what gives us purpose? Who is this all for? Where is this all going? I don't know. So there's definitely that. I think about that all the time. I actually would really like to ensure that these agents are working for humanity, not against humanity. But then there's also the practical aspect of, I think, at least for the next couple of years, AI will simply not be good enough to create great creative output. I truly believe that. I think we're getting to like decent in some categories, but I haven't seen anything one shot it. Not video, not images, not definitely not anything written. Um, I mean, I tried to do a first draft of my announcement post, and it was so bad that I had to basically reword everything. Um, definitely not code and also not design. So none of these things get you to 100% right now. Um, and this is why I'm sometimes quite frustrated with this narrative of, you know, AI design tools and other types of tools positioned for vibe coders to be able to make a problem go away. Right. Just use this and you'll have a landing page. Right? Um, you just put a prompt and you get something good that doesn't work. It has never worked so far. I have never seen anyone nailed that, I think. Design is an iterative process and has to have a point of view of a human.
61:35Julian Weisser: It feels like in some ways pretty good is always what a lot of people are striving for. I mean, you know, in pretty good, it just continues to get a little bit better. But it's incremental. I mean, look like Squarespace, when it came out, it looked better than the other options that existed before it for the average person to set up, you know, maybe a website for a business. Um, they marketed the heck out of it. They spent so much money on advertising on every podcast imaginable. And, you know, they they did build a business off of that. Um, but arguably, I would say that it was pretty good. And then also, um, not not impeccable. Um, and then also, uh, once Squarespace hit a certain saturation point of adoption, everything started to look like Squarespace. Right. And similar to what you were talking about, how slop is a moving target? I remember when Twitter Bootstrap came out, which was sort of their open source library for, uh, for web design, like web pages. Um, everything started to look like Twitter bootstrap and people would constantly complain about, oh, it's just another bootstrap, uh, themed website. And, you know, now it's with clod and various various things, kind of just like, kind of look, they're pretty good, but there's a big gap between pretty good and something that's truly amazing. Uh, that feels one of one that feels artisan. And I know you've written about sort of that idea of artisan versus factory made. I think it's really important. Another thing that you touched on, um, around sort of this idea that more is not necessarily better, you know, more, uh, more words, uh, more writing, uh, more code. Like the whole idea that, you know, uh, a book, most books should be blog posts. Most blog posts should be tweets. Most tweets shouldn't even exist. Um, you know, there is there is so much to be said for. There's a lot of bloat out there. And then there's also a lot of pretty good. And your goal is to essentially say to people, hey, if you're not just looking for pretty good, we're going to help you with pretty good, but pretty good, it's going to be even better. But if you actually want to do go from pretty good to outstanding to one of one to singular, uh, that comes from being in the loop. And we're trying to develop systems that really help you be in the loop.
63:52Paul Bakaus: Yeah, absolutely. And by the way, like on the,
63:56Paul Bakaus: on the on the thing about like removing right. As opposed to adding this is common misconception. Misconception that Steve Jobs used to be this like super creative genius. Right. But I don't think that's what made it made him so unique. I think what made him so unique is his judgment. He was just the greatest editor of all time. He would just say no to 99% of things, and the 1% that it's a yes to made it to us, right? Is the stuff that we got into our hands. I mean, a lot of the work was created by other people, but he just had the capability, the uncanny ability to know what not to ship. And I think that that's just so much more important now. It's kind of crazy.
64:43Julian Weisser: It's also interesting because I was just reading an excerpt from the Walter Isaacson biography of Steve Jobs, and it was talking about when he was going through his medical treatments. He was complaining about the designs of the face masks. And I think it was maybe the, the, the one of the machines to check your pulse or something. And he was talking about how they just weren't very good. And he, he wanted to see better design and he would design a better one. It's like the guy was just obsessed with with elimination and with really, like, cutting down to the core of what it is. Um, another thing that, uh, that comes to mind from all of that Is. It feels like, uh. It feels like in many ways, people. Uh, people maybe take away the wrong lessons from people like that, which is that it's always about subtraction or it's always about minimalism or something like that. I think that really, when it comes down to is, um, everybody has sort of their perspective, their thing that they put on the world. And when things don't stand out, it's often because the people are just kind of like doing whatever is on trend or what is normal, or in this case, it's whatever the whatever the system is sort of set up as the default to do.
65:58Paul Bakaus: Yeah. But it's also interesting that it's not necessarily a bad thing. It depends on what you're doing. Right? For example, if you're building an internal tool or if you're building a system level application, uh, use system fonts, right? Use fonts that are already in the system. Make people feel at home. Right. If you're building something that would benefit from an enterprise customer already being able to orient themselves. Right. Yeah. Like copy an existing UI and make it work like something they already used to write. Great. Amazing. Because enterprise is a good example. These these things are not sold by people looking at websites. Right. These people are sold to CTOs. These things are sold to CTOs. And so that's a very, very different problem than you're building something in the consumer space. And you have five seconds of time to convince somebody arriving on your landing page. They clicked on from Instagram. That's something is worth your time. Right. Hugely different. And now in a in a sea of vibe coded sites, sticking out is actually really, really important. So I think depending on the type of use case, you just need a completely different approach to design, which is also interesting.
67:06Julian Weisser: One of my favorite things that I heard about, um, about editing, um, specifically when it comes to teammates is, uh, is Keith Rabois. He has this concept of, when you're working with someone, you want to essentially expect that there will be times to take out the red marker and edit, you know, and put line edits and really be thorough there and correct things and give people feedback. But the idea with management and editing is that the more time goes on, you want to use the marker, the red marker, less and less. I'm curious how you think what if, how that resonates with you, and then to how you think that relates to working with AI versus working with people?
67:50Paul Bakaus: Yeah, I think that's completely true. And I think with AI, I think the same is true. Um, I think the there was this cool like gif that somebody created or like some, some meme graphic forgot who did it, but it was about the process of getting the results right. And so usually you have like this, you built this like, uh, I don't know, like parts of a car first and then you kind of build up on it until you have the final car, right? And so now in that picture, you saw this fancy alien car first with all belts and whatever, like, you know, like crazy extrusions, right? And it's blue and whatever, you know, and then you kind of, like, trim it down until it looks like a real car. Right? I think that's certainly true. And to your point, if you're doing a first edit for a novel, it's usually way too much in it. That's usually like you're meandering in all sorts of directions. There's continuity issues. And the same is true for design work. If you're building a large landing page and you first describe what you want. I think any AI model right now, GPT may be a bit lesser than clod. We'll first try to put everything on there that you might need.
69:02Paul Bakaus: Uh, not that you will need, but that you might need. And one common principle to actually counter that is to say, afterwards you're going to cut until it hurts, right? You will remove more than you intended to remove because you can always bring things back, but there's usually too much stuff. And then you kind of do the squint test and say, does it still work? Um, but it is. It is a challenging process, especially because you so quickly feel ownership over something that you created, even if it was created with AI, right? You create something and then you have this beautiful case study section maybe, or like this logo section that has like logos of companies. Right. And you get attached to it because it looks cool. Maybe it's a happy little accident that the AI model generated, but then to have the discipline to say, I'm going to remove this again. It's sometimes really hard. So that's that's tricky. But I, I do think it's very similar. So the editing process of getting to multiple iterations until there are no red markers anymore, red lines, it's very much the same thing. And in fact it's exactly the same thing if you're using impeccable because there's this design linter that runs behind the scenes and design hooks. So when it edits your code and the linter runs under the hood and for instance, finds 30 issues, the model can then fix 20 of them so it produces ten issues. And so it continues polishing your work until it finds at least no reported issues. That doesn't mean the design is great, but there's a process there that feels very similar. I actually called this. I was working on this other library called Radiant Shaders, and this was an open source project that didn't blow up as big as impeccable, but it has some happy users, and it's a collection of shaders and so animated shaders that you could use on your website. And I documented my process of how I got there, and I called it carving Shaders out of cloud code, because I really liken the process of working with an agent as like carving something out of a stone block. Almost. Right. And I think it's an interesting way to think about it. It's everything is already in the model, right? But then you have to, like, shape it.
71:22Julian Weisser: This is really interesting because I, I've, I've talked about startups in a lot of ways as chipping away from a block of marble versus versus starting from a blank canvas. Because I think oftentimes startups come from revealing something, um, that is already there. And, um, and I just remember this, this quote or this idea that, um, that sculptors are not necessarily, uh, are not necessarily starting from nothing. They're actually trying to, um, trying to free the object from the block of marble. Yeah. And I think about startups is they're actually trying to free that what they're making from the marble, it's they're trying to pull it out of there. And in many ways, what you're talking about with, you know, with an LLM is there is this block of marble, um, or this block of information. And what you're trying to do is you're trying to pull that out. Um, and so you actually reveal it and, and in many ways, um, you need to adjust as you go. It's not it's not that you're going to have it come out perfectly, but you're going to adjust as you go and start to see something reveal itself and say, that looks good there, but maybe not over there. And I think that that's, um, I think it's a really powerful analogy for, for working with AI.
72:41Paul Bakaus: I think so, and it's also how you navigate the latent space in a model. That's the other interesting thing. For example, there's this common saying that llms are not funny, but that they don't have humor. But that's simply not true. They just have 500,000 definitions of humor. Hmm. There are so many different funnies in the room, but they probably don't understand what you find funny. And so for you to figure out, okay, well, how do I create this camera? Just like, you know, hold to pinpoint light though, right? That focuses on the exact definition of funny that you find funny. That's an art form in itself, but it's very similar, right? Like navigating the latent space.
73:25Julian Weisser: Yeah, it's it's a really interesting point because pretty much anybody's definition of anything is fairly, uh, fairly specific to them and their preferences and their experiences where they grew up. Uh, I mean, just think about spicy food, right? Um, there's different types of spicy, and some people can't handle spicy food at all. Uh, some people love spicy food. Uh, it's just this it's just this entirely subjective. Well, they try and have objectivity to it around these different units of measure, but I think that a lot of people would describe something as, as, uh, subjectively spicy, uh, in their, in their own way, depending on where they're from or what they like.
74:02Paul Bakaus: Completely.
74:03Julian Weisser: I'd love to. I'd love to maybe close on, you know, the kind of customary questions we ask which at the end of conversations, this has been super fun. Um, you know, the first question is, uh, sort of the bear case for being a solo founder, like why you shouldn't be a solo founder. We'll talk about that for a second, and then we'll transition over to what the what the case for solo founding is. But what's the what's the reason that somebody should maybe consider not being a solo founder at this moment?
74:29Paul Bakaus: Well, I think there's a saying that, uh, it takes a certain type of crazy to found something in the first place, right? But I think not knowing whether you're actually crazy or not, not having a sounding board can be really, really hard sometimes. So I think if you're a solo founder, if you're going on that route yourself, which is great, at least find some people that can become your sounding board. That can be your friends and family. But better to have somebody who's actually objective. Um, so I would say that's probably the biggest one. And then protect your attention. Right. Protect the thing that you are truly capable of doing. You might be able to do that in another way by contracting things out, etc., but I think it's a bit harder to do. I think it's possible, but it's harder. Now it's also liberating because you can move faster. You don't have to negotiate with others. Um, but, uh, but those things I would say get harder when.
75:26Julian Weisser: You, when you talk about and you touched about on this a little bit about doing the things that you like and sort of focusing on them and having potentially other people who can help with the other things, even if you don't have a co-founder. Um, maybe you share just a tiny bit more about that, focusing on the right things, because, uh, I think that it could be very easy to focus on the things that you like, maybe sometimes, to the extent that you let the things that are important sort of fall by the wayside. One way to do that to to avoid that is to potentially hire a chief of staff early on. But you have to juggle a lot of things. As a solo founder, is there anything else that you've learned in this process before you brought on the chief of staff about sort of being able to focus, but also getting all the other things done as well.
76:09Paul Bakaus: Yeah, I think one advice that I would give is look at your biology. And what I mean by that is, you know, look at your decision fatigue, for instance. In my case, the way you organize your work through the day is really important. In my case, during the mornings I have less decision fatigue. So I do more critical meetings with people. But then in the afternoons I'm more creative. But I have decision fatigue. So now I start building. And so for everybody that's different. Everybody operates differently. But like really listen to your body and what it tells you. That's one advice I would give. I think the other one is um, focus on creating value. We talked a little bit about this earlier, but so many days during my corporate jobs, I woke up in the morning. Actually, no, I came home in the evening and I thought about, well, what value did I create today for the world, for anybody? And I didn't have an answer. And I think that's a terrible feeling. That actually leads to burnout. And
77:10Paul Bakaus: it's so important to sort of honor as well. But what is the value that you create on every, every single day? And I think it's also the key to building a small company. I think people built large companies because they couldn't build a small company instead.
77:27Paul Bakaus: And so if you want to build a small company that's really effective, make sure that everybody you hire creates value every single day. You create that structure without middle management.
77:39Paul Bakaus: So you make that true. And you have to focus on what it is that you you put out there that's valuable.
77:47Julian Weisser: That's that's a great point. The other thing about burnout, which is similar to this idea of make sure you're creating value, is that I think that one of the reasons that people experience burnout is due to a lack of momentum. Like momentum will solve for burnout. Very quickly. It's very energizing to have momentum versus burnout. You're usually not very energized, um, because you're trying to push something. And I think that if you focus on creating value, that's sort of the, uh, the early sort of leading indicator for, you know, you know, creating momentum.
78:20Paul Bakaus: Yeah. Momentum. I will say I mean, it brings up a good point because there are so many things that can kill momentum. I mean, one thing that can kill momentum is hiring somebody into a role, uh, that cannot come in at the right elevation, but somebody who's really bad at 0 to 1, but who has been very good at 5 to 10. Yeah, super, super easy to kill momentum that way. You know, first thing the person wants to do is create a mono repo or introduce a ticketing system or whatever it is, right? But, you know, things that worked in a large team at some big fortune 50 company, but certainly not the right thing for an early stage startup, right? So so I think that's the other thing. Like, figure out what feeds you, what gives you energy. What gives you momentum versus what stops your momentum? What stops in your tracks? There are so many things we learned about software engineering that are simply not true anymore. That's the other thing, right? The the handoff process, the agile workflow, like going from design to engineering, like product design, engineering. None of that stuff matters anymore. It's really interesting. Like, because it cannot matter anymore in a workflow where we ship 50,000 lines of code every day. It's just not possible. So I'm seeing designers move in the code. I'm moving, engineers moving into design. I see product managers move into everything, and we just have to work completely differently. So I think there's a lot of things that we assume are needed that are not actually needed in order to build something valuable. So that's one way I protect my momentum.
79:56Julian Weisser: Cool. Final question. Uh, the case for solo founding. What is the case for solo founding?
80:02Paul Bakaus: The case for solo founding is you only have to account to yourself, and you can move at the speed of your own thought and don't have to wait for anyone. I think it's especially important if you're in the early stages of exploration, and
80:22Paul Bakaus: you also don't really need anyone when you're first building something that you envisioned in the first place. Now, unless you need help from outside, that is a bigger operation in the first place. But I think don't let it stop you from starting something. I think it's a big mistake to wait for somebody come around the door, right? The right person to join you. Just start it.
80:47Julian Weisser: Well, this has been awesome. I'm really excited to, you know, maybe in a few months or a year, come back and, you know, talk about what what the Renaissance geeks are up to, uh, in the future because, I mean, it's incredible. Right now. We love impeccable. We use it all the time. And. Yeah, thanks for doing this.
81:04Paul Bakaus: Thank you so much for having me.
81:06If you enjoyed this conversation, we would love it. If you can share solo founders with everyone you know, particularly people who are considering starting companies solo or who are already doing it, you know, the entire goal of what we do is to normalize solo founding, to encourage more people to solo, found instead to end up with co-founders of convenience, if you'd like. And we'd really appreciate it, you can go leave a review on Apple. You can go give us a thumbs up. You can subscribe on the YouTube channel. Anything helps. And of course, if you are starting a company or considering starting a company, you should go look at the Solo Founders Program. We work together with you in San Francisco alongside of a bunch of other solo founders. The idea is it's much better to be solo together than to be solo alone. I'll spend a lot of time helping you, and we also invest $100,000 in your company. So if you're excited to learn more about that, go check out Solo Founders com Slash program.


