The Pragmatic Engineer - From IDEs to AI Agents with Steve Yegge

Episode Date: March 11, 2026

Brought to You By:• Statsig — ⁠ The unified platform for flags, analytics, experiments, and more.• Sonar – The makers of SonarQube, the industry standard for automated code review• WorkOS – Everything you need to make your app enterprise ready.—Steve Yegge has spent decades writing software and thinking about how the craft evolves. From his early years at Amazon and Google, to his influential blog posts, he has often been early at spotting shifts in how software gets built. In this episode of Pragmatic Engineer, I talk with Steve about how AI is changing engineering work, why he believes coding by hand may gradually disappear, and what developers should focus on, instead. We discuss his latest book, Vibe Coding, and the open-source AI agent orchestrator he built called Gas Town, which he said most devs should avoid using.Steve shares his framework for levels of AI adoption by engineers, ranging from avoiding AI tools entirely, to running multiple agents in parallel. We discuss why he believes the knowledge that engineers need to know keeps changing, and why understanding how systems evolve may matter more than mastering any particular tool.We also explore broader implications. Steve argues that AI’s role is not primarily to replace engineers, but to amplify them. At the same time, he warns that the pace of change will create new kinds of technical debt, new productivity pressures, and fresh challenges for how teams operate.—Timestamps(00:00) Intro(01:43) Steve’s latest projects(02:27) Important blog posts(04:48) Shifts in what engineers need to know(10:46) Steve’s current AI stance(13:23) Steve’s book Vibe Coding(18:25) Layoffs and disruption in tech(31:13) Gas Town(40:10) New ways of working(51:08) The problem of too many people(54:45) Why AI results lag in business(59:57) Gamification and product stickiness(1:04:54) The ‘Bitter Lesson’ explained(1:07:14) The future of software development(1:23:06) Where languages stand(1:24:47) Adapting to change(1:27:32) Steve’s predictions —The Pragmatic Engineer deepdives relevant for this episode:• Vibe coding as a software engineer• The full circle of developer productivity with Steve Yegge• AI Tooling for Software Engineers in 2026• The AI Engineering Stack—Production and marketing by ⁠⁠⁠⁠⁠⁠⁠⁠https://penname.co/⁠⁠⁠⁠⁠⁠⁠⁠. For inquiries about sponsoring the podcast, email [e-mail]. Get full access to The Pragmatic Engineer at newsletter.pragmaticengineer.com/subscribe

Steve Yeghi has been a software engineer for 40 years. He spent decades as Amazon and Google, is famous for his brutally honest rant about the industry, and for being right, a lot. He recently built Gastown and open-source AI agent orchestrator and co-authored the book VibeCoding with Gene Kim. In today's conversation, we discuss Steve's eight levels of AI adoption for engineers

from no AI to running multiple agents in parallel and why 70% of engineers are still stuck at the bottom levels. Why AI is creating a vampireic burnout effect on development, where you can be 100 times more productive, but only get three good hours a day. His prediction that big tech companies are quietly dying and that small teams of 2 to 20 people will rival their output. And many more. If you want to understand what the day-to-day of software engineering look like in the near future

and how not to get left behind, this episode is for you. This episode is presented by Statsig, the Unified Platform for Flags, analytics experiments, and more. Check out the show notes to learn more about them and our other season sponsors, Sonar and WorkOS. So, Steve, really good to have you on the podcast again. What have you been up to? Gerge, great to be back. It's been 10 months now.

Closer to a year, yeah. Close to a year, yeah, boy. Seems like forever. Yeah, sure does. Yeah, there's been a lot going on. I'm unemployed right now, which has been incredibly fun. Unemployed or fun employed. I am just doing whatever I want, what I'm doing, which is real nice.

And I had a couple of software launches, which was nice. I had a book launch last year, which was nice. I've been living life. Yeah. So for a very long time, you've been known as this kind of truth teller of bringing in, sometimes comical, sometimes really uncomfortable facts or observations, should I say. You wrote like often in really kind of fun ways with rant. And a lot of them resonated with people.

Do you remember what was a rant that really stood out? at any point in time that, like, you got some really good feedback, either at that point or later you felt validated by it. Oh, well, so a lot of people tell me, well, those who know your favorite TV blog is actually execution in the kingdom of nouns. I don't know if you remember that one. Way back in the day. I was at Google, early days Google, and I was trying, I was struggling to sort of, like,

get this idea across to people that Java's growth was super linear with the amount of code. The amount of code would grow more than the amount of functionality, which is not a good place to be. And Goddava's gotten a lot better since then, right? But my post raised a lot of eyebrows at Sun because they were like, what is this guy complaining about? Why does it you just shut up? But I was like, I want to use a language that has first class functions. And so I wrote a very, very, very unusual log post called The Execution in the Kingdom of the Nouns. People really loved it where it was a story.

It was just a fairy tale about a land where there were no verbs. And it was fun. So one of your lesser-known blog posts, or for a lot of listeners, it's called a rich programmer food essay, rich programmer food. And this was about compilers. Do you remember what you argued about or what the point you made? Of course. That's one of the most important blog posts ever. I'm going to tell you, I met a guy, okay, who he introduced himself at SWIX's AI engineering conference in New York.

And he's like, I've wanted to meet you, Steve. I'm one of your players, okay? And I'm like, whoa, because this dude's, you know, in his 30s. And, you know, he's played my game. You understand the game that I wrote. It's something that most people, Wyvern. Most people haven't seen it because I didn't open source it. I will someday.

It's just a pain in the butt. It's a really beautiful thing. And it created so much love in the players for decades. They would come back, right? But this guy was so into it. And he's like, I read your, I read your rich programmer food blog post and decided to become a compiler expert. I became a PhD. He was in high school when you read it.

He became a PhD, started his own company. He's got a startup that's doing really, really well now. And he said it was all because of that post. And this post talks about, I think you argued that unless you know how compilers work, you're not going to be a good programmer, an efficient programmer. I'm not sure what the phrase it was. There's going to be a layer of magic between what you're doing and what the computer is doing that is forever going to be sort of friction for you.

And I think you even argued that some PhDs don't even understand how compilers work. and this will make it really hard for them to be efficient. At the time, that was definitely true, right? How do you think that post has aged? Because at that time, I think it was like 2012 or so. Like, even then, I would assume it was a bit unconventional to say, like, you need to understand assembly because it was high-level languages, right? Java was in its prime, C-sharp, Ruby was starting to come out.

Heck, JavaScript was starting to become big. React is we'll start in a few years. And most developers would have thought, why would I need to know compilers, assembly? I mean, that's what the compiler is for, right? Yeah. You're asking a really, really, really foundational question. You're asking you what universities should teach is what you're asking me,

Gary Gaye, okay, in disguise. And, you know, those goalposts have moved every few years since I got into this game in the 80s, all right? What you need to know in order to be a software engineer, it used to be assembly language. It used to be like lots of bits and stuff like that. And over time, my buddies and I realized that our favorite bit manipulation questions were starting to bounce off candidates who had never seen a bit before, right? And we really, you know, we did some soul searching in the 2010s, you know, and we were like, yeah, do you really need to know how to manipulate bits and a bite with XORs and stuff like that anymore? Probably not, right?

And that was a depressing realization because we had pride in ourselves and knowing how that stuff works, but we just don't need it anymore. And the sad reality is that I had a lot of my own ego and identity wrapped up in my sort of compiler background. It's all interesting, right? But it's not useful in any meaningful sense anymore. And is it not useful because the compilers have gotten so good at optimizing, for example? Is it that the problems have moved on to higher layers? Yeah. Why do you think that is?

We're just walking up the abstraction ladder. That's all. And we're not even talking about AI just yet. Like this happened even... Didn't say AI. Did you say AI? No, not yet. We will say it. But even in the...

I remember, like, you know, late 2010s, it didn't really come up. Like, in my career, I can only remember one time where it would have been nice to know what the compiler did, but even then might have been a red herring, honestly. Look, what you have to know just keeps moving. They just, they keep changing the courses. They keep changing what they teach. Many people don't see this because they're only looking a year or two or three back and,

you know, looking a little bit forward. but I've been done this for 40 years, and I can tell you, they teach you very different things now than they used to teach, and it's because you need to know very different things. And nowhere is it more evident than when we saw the exponential curve of the graphics industry, computer graphics. Look at graphics today compared to 1992 when I was learning graphics in university, and I had to learn how to literally do the algorithm to figure out where the next pixel goes on a line so I can render it to eventually turn it into a triangle, which is a polygone. Meanwhile, two years later, I took the same course and we were doing animation. I didn't even know what a polygon was. I mean, I did, but not at that level, right? The whole ladder just kept moving up, and the jobs changed.

Originally, they needed people that could write device drivers, and then they need people, and now they need people who can do game worlds and physics and all this stuff, right? It's just graphics showed us the way. This is what happens. And software engineering jobs have been very stable for, I don't know, since iOS, since mobile and cloud. Those are the last two big innovations, right? Yeah.

Steve just made the point that the industry goes through these massive maturity leaps, from raw pixels to game engines, from bare metal to cloud. And if you're building software today that needs to make that leap to enterprise grade, there's a tool that handles exactly that. This is our season sponsor, WorkOS. If you're building any SaaS, especially on AI product, authentication, permission, security, and enterprise identity can quietly turn into a long-term investment.

Sammel Edge cases, directory sync, audit logs, and all the things enterprise customers expect. It's a lot of work to build these mission critical parts and then some more to maintain them. But you don't have to. WorkOS provides these building blocks as infrastructure so your team can stay focused on what actually makes your product unique. That's why companies like Entrophic, Open AI, and Cursor already run on WorkOS.

Great engineers know what not to build. If identity is one of those things for you, visit Workerwas.com. With that, let's get back to the question of what the last real innovation is software engineering actually was. And it's been kind of dead since then, actually. Yeah. I don't want to say AI because we're not talking about it yet. But I think we went through a period where people stagnated a little bit, where the

courses didn't change pretty much. And we thought this is all we're ever going to need to know. I feel the last big innovation, correct me if I'm wrong, was distributed systems. That was the last kind of hard problem starting from like 2010s when you Uber brought microservices into there, how you scale services, how you store large amounts of data. I feel that was a, like, I mean, it was a big, it was a big slow. Yeah, but honestly, like, I feel there's a lot of migrations happening, new React versions coming up and developers struggling with that. Apple, every year throwing in a, you know,

like a screwdriver and in the wheels with a new breaking version, Android developers needing to retire an Android old version and deciding, like, where to cut it off. So I feel there was that, like, kind of like, migrations thing. And also, business was just good, right? like everyone was growing. We were like everyone was busy hiring. Like there's no tomorrow. There was a time in 2021, the market was so hot.

A lot of boot campers with three months experience were getting offers. It's a pretty good company because everyone was so desperate to hire. Yeah. And then came AI in 2022. One thing that always struck me about you, even in those like, you know, in 2020s and even before, you were always pretty pragmatic. You know, you were by trade. You were always into compilers, debugger tools.

That's where you started. You worked on hard problems at Amazon and Google, never shied away to getting into like hard technical problems and, you know, like all these things. And when AI came out, I don't remember you saying, oh, this is amazing. This is going to change the world. How did you feel? Were you kind of like observing, skeptical, like at the very beginning, right, when you first came across LLMs? How was that? I was pretty blown away that they could write fairly coherent Emacs LISP functions.

like chat GPT, the original one in December 2020. 2020? 2022? Okay, boy, time flies. Could already write code in a weird language, right? Not very much of it, and it was janky, but that was, for me, that was the beginning of, oh, right, you know, because I've had friends in AI for 20 years saying any minute now, any day now, right?

And they'd show us and they would complete better and better and better. And this was the first time it was like, oh, okay, I see now, right? But I was still skeptical like everybody else. And I can tell you because when the rumors came out about Claude Code in beginning of last year, right, that Anthropic had a tool internally that was writing code for them and it was a command line tool, I, along with everyone else, went, no, it's not, you know, we were just like just flat out rejection, just absolutely not happening, right? Until I used it.

And then I was like, oh, I get it. We're all doomed. Right? And then I wrote Death of the Junior Developer right after that, actually. think. Gosh, it might have even been after 4-0 came out, but I did death as junior developer. But things changed really fast once that came out. But was I a skeptic? Yes. But did I pay attention to the curves from the very beginning? I figured if chat GP3-5 can write a coherent Emacs list function, then in a year, let's see how they do. And in a year, 4-0 was writing

a thousand lines of code. A thousand lines. Dude, that's most of the world's code is in files of a thousand lines or less, which means that it can make credible edits. It wasn't able to up until 4-0 came out, right? And so, like, man, it was that point when I was like, okay, we're on a curve. This is a ride. It's not stopping. Let's get on the ride and see where it goes. And I dove in, right?

And I was like, I was behind. I didn't know AI. I didn't know, like, the fundamentals of the, I didn't know the lingo. You know, everybody knows this stuff now, right? Yeah. I spent a year doing nothing but reading papers and catching up, right? So in this book, Vibe coding, I remember last time you were on the podcast,

this book was about to come out and I was reading an early version of it or so. But the back cover, I just read the back cover, and I realized that you must have written this about a year ago. And it says the days of coding by hand are over. When did you realize this? Because I've realized this recently with Opus 4.5. But this was a lot before, well before that. Yeah, it was a year ago.

It was, let's see, what is it right now? January. So it was over a year ago. It was 12, 13 months ago when I first realized. And it wasn't, that wasn't even my quote. That was Dr. Eric Meyer, right? The inventor of many, many, many things in the programming world, one of the most important compiler people in the world. That dude, think about it. He spent his life building technology for developers to be able to write code. And he's saying developers aren't going to write code anymore. What would possess somebody to say, well, my life's work isn't really, right? And that's what caused actually Gene Kim and I both to go, huh, right? You know, if the inventor of, you know, he made huge contributions to Visual Basic and C-sharp and Link and Haskell and P and Ph.P with a pig, is that what it's called? Right? All him. And he's just like, no, we're done. We're done writing code. I mean, that's, that's, that's, that's, that's, that's, that's pretty big words from a languages person. One of the most famous in the world, right? What does he see that we didn't? And he sees the curves, man. It's, that simple. It's like exponential curves, they get real steep, real fast, and we're heading

into the steep part this year. So the inventor of C-sharp and Visual Basic is saying that we're done writing code. But even if the AI writes all the code, someone has to verify it. And that's where our season sponsor, Sonar, comes in. Sonar, the makers of Sonar Cube, has introduced the agent-centric development cycle framework, ACDC, a new software-developed methodology designed for the unique scale and speed of AI generated code. It's a move towards a more intentional, four-stage loop that gives agents a garterer as they actually need. The four pages being guide. First, agents need to understand the canvas on which they're being asked to create so that the output fits with what the developer and organization require. Generate. The LLM-based tool generates the code

it believes will achieve the desired outcome within the right context. Verify. Next, the agent is deliberately required to check its work, ensuring it actually achieves the desired outcomes and is reliable, maintainable, and secure. Solve. Finally, any issues identified or provided to a code repair agent to fix. To power this, Sonar has significantly strengthened this offering, introducing products and capabilities like Sonar Context Augmentation, Sonar Cubogenic Analysis, Sonar Cube Architecture, and Sonar Cube Remediation Agent. Head to SonarSource.com slash pragmatic to learn more about the latest with Sonar and how it's empowering organizations to embrace the agenic era. With this, let's get back to Steve's exponential curves of AI improvement.

Playing devil's advocate, you know, like one thing about being an engineer is like, you can draw up curves, but you know, like you never know when they end or if they flatten whatnot. We can see where it has come. What made you believe that this curve would keep going? And especially that with LMs, the fact that it even kind of works was a bit of a, I guess, surprise for a lot of people. And the fact that it kept scaling is a surprise and there's this question of like how long they will scale. Yeah. So the world is filled with unbelievers.

People who, I'm specifically who believe the curve looks like this. An S, it goes up and then it flattens. And they actually think we're at the hump right now. Yeah, and they have thought that ever since the GPD3-5 came out. They're like, yeah, it's not going to get any better. 4-0 comes out. We love 4-0. People love 4-0.

They still do. They can't get rid of it. But they still think that's as good as it gets. You know, Opus 4.5 is out, and most people haven't played with it. Most people don't realize what's there. And that thing is already two months old. The half-life between model drops, far as I can tell, has gone from about four months,

beginning of last year to two months from Anthropic at the beginning of this year. So any day, we're going to see another model from Anthropic. It'll probably be out by the time we have this podcast out, right? And that will be so much further up the curve that people are going to start to be really freaked out by it. It's going to worry people when they see the next model. Okay?

Because all of the bugs, all the mistakes that they're complaining about, right now get fed right back in his training and so that it doesn't make them the next time. And this is what people aren't understanding, right? And also, time continues. There will be three and five years from now. The sun's not going to stop, right? And it's coming. So this inevitable, the collision of these curves, man, there will be societal upheaval is what's going to happen. And it's already started. And people are justifiably mad. And I'm mad with them, Gary Gay. Okay. I'm mad at Amazon for laying off 16,000 people and playing an AI without an AI strategy for it. people are not going to be able to find jobs, my and large, and they're the first of many to come. And nobody has a plan for this.

Why do you think Amazon did that if they don't have an AI strategy? Because, unfortunately, and people are going to hate me for saying this, but me saying it doesn't make it true. It was true already. Everybody has a dial that they get to turn from zero to 100. And you can keep your hand off the dial, but it just has a default setting of what percentage of your engineers you need to get rid of in order to pay for the rest of them to have AI. because they're all starting to spend their own salaries in tokens. And so at least for a while, if you want your engineers to be as productive as possible, you're going to have to get rid of half of them to make the other half maximumly productive. And as it happens, half your engineers don't want to prompt anyway, and they're ready to quit.

And so what's happening is everybody, on average, is setting that out about 50%, and we're going to lose about half the engineers from big companies, which is scary. Yeah, that's wild. It's way, that's way bigger than, we've seen back at COVID. It's going to be way bigger.

It's going to be awful. But at the same time, something else is happening, which is AI is enabling non-programmers to write code. And it's also enabling engineers who have seen the light and believe the curves are going to continue to go up to actually get together in groups of two and five and 10 and 20 and 30 people and start to do things that rival the output of these big companies that are tripping

over themselves. And so we've got this mad rush of innovation coming up and bottom up. And we've got this mad knowledge workers. falling out of the sky as the big companies lay them off, because there's clearly the big company is not the right size anymore. Even Andy Jassy's saying it, we're going to do the same thing with fewer people, right? And so does this mean we're going to have a million times more companies? Is there going to be a massive explosion of software or people going to get out of software altogether and we're all going to go to other stuff? I mean, like, I'm very curious

where all this goes. Yeah. Small teams that have the right skill set or see the right business opportunity or have advantages can do way more. So there is something there. and that. There is. So there's this land rush starting. I think a lot of the people coming out of knowledge work are just anti-AI. And those people are going to struggle. I'm sorry. But if you're anti-AI at this point, it's like being anti-the-sun, you're going to have to go live underground, right? But the people who are like pro-AI, like I think we're going to see a big redistribution of who's doing the work and where you get your software from. And we may well wind up from, I could actually see a happy place where Amazon's not even a thing anymore. I really could because software becomes, we don't have the words for what's happening, right? You know, so many things happening this year that we don't have words for. Have you noticed that? But software becomes sort of like distributed. I don't know. I do see non-technical people getting into software. Could there be a job there for engineers to come and actually take over maintenance? Yeah. I mean, I think there's going to be plenty of opportunity for, there's going to be a lot of engineers doing software engineering.

I just think we're all going to be doing it with AI. right? No. But I think it'll be quite some time before companies are comfortable trusting their code to be written and deployed by AI without any human being involved at all. I think the point that people are missing, the important point that the naysayers and the skeptics are missing is not that AI is not coming to replace your job. It's not a replacement function. It's an augmentation function. It's here to make you better at your job. Right. And that's not a bad thing, actually. I don't know why people would. fight that. Speaking about the job as developers, you've said something that can be triggering for a lot of people. You've said that I think this is on the AI engineer summit, if you're still using an IDE now, you're a bad engineer. Yeah.

Well, you got to be a little prerocative. Yeah. You know, I let me put it this way. Okay, I'm not going to say you're a bad engineer because I know some very, very good engineers, better than I am, who are still at like level one or two in my chart, right? But I feel profoundly sorry for them. I feel pity for them like I've never felt in my life for these. grown people who are good engineers or used to be, and they're like, yeah, you know, I use

cursor and I ask it questions sometimes. And I'm really impressed with the answers. And then I review its code really carefully. And then I check it in and I'm like, dude, you're going to get fired. And you're one of the best engineers I know. Tell me about your chart. Tell me about your levels that you came up with. Yeah. So I was drawing us on the board in Australia for a big group of people trying to show them what happens because I saw them at all different phases. Some of them had their IDs open. Some of them have a big wide coding agent. Some of them, the coding agent was really narrow, right? You know, and so I was like, okay, we're going to put you all on a spectrum just to show what's going on, right? And level one, no AI, right? You know, and level two, it's the yes or no,

can I do this thing, you know, in your, in your IDE, right? And then level three, you're like, YOLO, just do your thing, right? Your trust is going up, right? Level four, you're like, the code, you're starting to squeeze the code out, right? Because you're like, you want to look at what the agent is doing and not so much at the diffs anymore, right? So you're not reviewing as much now? You're not removing as much. You're letting more of it through and you're really focused on the conversation with the agent. And then at level five, you're like, okay, I just want the agent.

And I'll look at the code in my IDE later, but I'm not coding with my ID. At level six, you're bored because you're like, okay, my agent's busy. I got to do something. I'm twiddling my thumbs. And so you fire up another agent. And now you're addicted because you'll very quickly get into an equilibrium where every agent is waiting. There's always an agent waiting for you because somebody's finished.

Right? As soon as you spend up enough of them mathematically, right? And so you find yourself just multiplexing between them going like this and you can't leave. Practical question. Assuming I'm working on the same code base, how do you spin up the multiple agents so that they don't get in conflict? Is it you're going to use like? Yeah. So that takes you to level seven, which is, oh my God, I've made a mess, right? I accidentally texted the wrong agent and didn't realize it. And they did a big project inside of this project because I asked them to and now I got to clean up this mess, et cetera, right? All that stuff. And now. was when I started going, okay, what if we were to like coordinate this? What if Claude Code could run Claude code? That's the question everybody wants to know. And everyone was trying all last year. It's going, Claude, run yourself. It would run for a while and it would stop, right? Yep. And so it was the whole stopping thing that. So yeah, I pushed on that really, really, really hard and wound up building some stuff to help with it. But yeah, boy, it's changed a lot.

me and it's changed so much. Going back to the ID, you had a really good live debate with Natanzobo from Z. And the title was the death of the ID. And both of you argued your view. What is your view about the ID and also what did you learn from Nathan on like his take of he was a bit more pro ID and you were a bit more like maybe this is not going to be around forever? Yeah. I mean, you know, I am where I am in my journey, which is I think that AI will do it all for us eventually. And so the way I see IDEs is what do they really do and what are they really for?

It's not really for writing code. It's for bringing tools together and for making a big tool, right? Yep. And now you have MCP for that or whatever, right? Yeah. And so I see IDEs returning and I think Claude Co-work is a return to the IDE form. It's Claude code going, oh, I need to be for real people, right? But I think Claude Co-Works form factor probably works better for the average developer than Cloud Code does.

Right? So I see IDE, I see it's coming back into a world where it's IDEs, except it's all conversations and, you know, monitoring. And this is a really good point. My brother built a thing called Kraft Agents, which is pretty similar to Cloud Co-Work, except they connected in their company, their own data sources. And he said that some developers start to prefer that because it's a visual that's easier to see parallel agents, for example. if you're not a power user, it's easier to scroll. It's just a nicer UI. So your point on maybe some developers should try out.

Like if you're not sold on Cloud Code, like try Cloud Co-work or any other similar, more visual thing, it might be your thing. But like, you know, Git. Some people love the command line. I actually just use the UI because I just don't like memorizing the commands as embarrassing it is to admit, or maybe these days not as embarrassing. Not, yeah. The key was try, as long as you're trying something.

Yeah. Probably the single most important proxy metric that you can have in a company today is token burn. Because what token burn says is your engineers are trying to do stuff or your non-engineers. And when they're trying, they're failing and they're learning. And so if you want to get those organizational bottlenecks discovered early on and you want to get your engineers leveled up on my eight-level spectrum early on and you want to solve your business processes ahead, you need to start now, which means try. It doesn't matter what you try. It doesn't matter which tool you use. As long as you're using AI and you're trying to get it to do the work, you're doing the right thing.

Yeah, and I think as professionals, like, we really ought to just at least try. Like, you get first-hand experience and then you can make your decision. Steve's point about token burn is really interesting. The companies that win are the ones that experiment the most. And if you want to bring that same experimental mindset to your product, not just your AI usage, that's exactly what our presenting sponsor, Static is built for. Static gives us. you the complete toolkit without building it yourself. You get feature flags, experimentation,

and product analytics all in one platform and tied to the same underlying user assignments and data. In practice, it looks like this. You roll out of change to 1% of users at first. You see how it moves the top-line metrics you care about, conversion, retention, whatever is relevant for that release. If something was wrong, instant rollback. If it's working, you can confidently scale it up. Companies like Notion 1 from single-digit experiments per quarter to over 300 experiments with Statsig. They shipped over 600 features behind feature flags, moving fast, while protecting against metric progression. Microsoft at Lashen and Brex used Statsk for the same reason. It's the infrastructure that enables both speed and reliability at scale. Statsic has a general's free tier to get

started and pro-pricing for teams starts at $150 per month. To learn more and get a 30-day enterprise trial, go to Statsick.com slash pragmatic. With that, let's get back to Steve's take on the state of gas town. Now there's a huge problem with people not knowing how to try. And they say, oh, let me do something. And then it does the wrong thing because they always do. And then they're like, well, this is garbage. So, you know, you have to teach them that it's a shovel and you don't go shovel, dig like in Fantasia, right? Like, make the brooms walk around.

No, you pick up a shovel and you dig with it. But it's a shovel that you didn't have before you were using your hands. Like, it's a really, really simple analogy, but people just don't get it. They don't get it. And I think, and I'm going to say something that's contentious, but it's just the reality of the world. Most people can't read. I've ruined much of my work in my life. I've just completely gone down wrong path by overestimating people's ability to read.

And I think that reading is, if anything, getting harder to come by as a skill these days. And this is the situation that we're in right now, is that cloud code makes you read a lot. So I think we're in a weird limbo for the rest of this year. Okay, where until the UIs arrive that are good enough for everybody who can't read, everybody who can't read is going to be a severe disadvantage. Tell me a little bit more about your observation. lot of people or a lot of developers cannot read. Because you were at Amazon, that place supposedly is running on six pages and people actual reading, does it?

I mean, dude, most people can't read. I don't know if you know this, man. Like, they read really slow. Okay. And the AI is, I mean, come on, to most people, five paragraphs as an essay. Remember five paragraphs in high school is a thing we have in America, I guess? Maybe years were 100 paragraphs in Amsterdam. But to us, five paragraphs is a lot.

lot. And that's like, that's the AI just clearing its throat, right? Yeah. You know, you've got to be able to read waterfalls of text. And so we're looking at a world where that won't work. And so you're going to need recursive summarization. You're going to need a factory. And it's funny because, like, this is why, I mean, trying UIs is so important. Because Gastown right now, the reason I say you can't use it is that it's a factory filled with workers and you're talking to it through a telephone. You can also go and look through the window and pound on it and talk to the workers, but it's not like you're in it, right? With a UI, you're in it. And you can, you can see what's going on. And right? It's all invisible in gas, by and large, right? You know, hard to see. And so I really do think,

and I'm just going to make a bold prediction. I think that by the end of this year, and we'll see demos of it, like right away. But by the end of this year, most people will be programming by talking to a face. A face as in on the screen. Your AI, like the Gastown mayor, will be a fox talking to you and you'll say, why doesn't it work? And they'll say, I'll go look at it. And it'll go spin off its workers just like it's doing, but you're talking to a face. And it will talk back. Yeah, I think that's the only thing that's going to work for most people.

Fascinating. Let's write this down to prediction. Why do you go build it? I'm not going to. Let's talk about Gastown. You mentioned Gastown. What, for those that a lot of people I've heard about, what is Gastown? Gas Town is an orchestrator.

So, 2023 was completions. code completion. Yeah, auto-complete, yeah. That's when we said it's a fact. Completion acceptance rate card. Do you remember that? Oh my, yeah. People were measuring it, yeah.

Stupid metric, by the way. The second one was, but it was close. It was a proxy for are they trying, right? Then there was chat. That was 2024, right? And then agents was 2025. We knew you could just look at that curve and go, okay, well, if chat is completions in a loop, basically,

and agents are basically chat in a loop, well, then we're going to put agents in a loop. And that'll be an orchestrator. right? And a bunch of them started coming out and I built one of my own. Yeah. My own vision. But that's all it is. It's agents running agents. And can you talk through a software engineer to us architecture? Like how is it organized? How can I imagine, you know, this setup?

Yeah, sure. I mean, look, GasTown is really complicated and it's been really broken all week because I'm migrating it to Dolt. And that's where I actually learned how complicated it was. It has a lot of features. You're migrating it to? To Dolt. It's a new database. Oh, okay. Yeah, Dolt is, Dalt is amazing. Dolt is a Git back to database.

It's a Git database. It's, ugh. Beads is just Git plus database crammed together badly. And there's actually a database that does this. So I'm migrating to it. But yeah, anyway, Gastown is, is what it should be is one, one mayor that you talk to, that's your, your person. And then whatever else needs to get done, they're just going to fire off workers. Okay.

It's a little, a little bit more complicated than that because there are a really, I think there are two kinds of work that people go back and forth on and people are arguing about whether they're the right one. Some people at Anthropics told me it's the minimaxing context argument, okay? There are people who believe that you should maximize your context window and fill it with rich, juicy context so that the AI is wise and all knowing when it's talking to you. They want to like, you know, just right at the edge of the context. And then there are others who are like, task, kill it. Task, kill it. I want the shortest window because of the quadratic, you know, increase in cost.

combined with the dramatic drop-off in cognition as the tokens go up, right? Yeah. Losing their track and stuff. So which one's right? And we've got people who are like full on in the minimizing and the maxers. And I looked at my workflow and I was like, well, Polkats are the men and crew are the max. I have two fundamental worker roles in GasTal. Do you have a really simple one, which is the small concept of the Polkat?

If you have a really well-specified task, all broken down into sub-taskes, then you can find, and it's like, it's self-contained. It says what to do. Then you can give it to a worker and have it go do it, right? Meanwhile, you have a really difficult design problem. You're going to have to have a series of conversations about this. I maximize context. I'm like, read all these docs and then we'll talk, right?

So it's just two workflows. And like I like J.D. I mean, it sounds like I think it's so easy to imagine. Like it's a little town, you know, like it's wild wild west. There's the mayor, like the crew, the workers. everyone's buzzing and going around and the house start being built. In practice, how does this work? Like, how has it

work for you? What are you hearing people get projects done versus not getting it done versus turning into absolute chaos? What have you learned with Gastown? It's been a great experiment. I mean, I've really enjoyed it. It's been an experiment, right? Well, yeah, I mean, right? I went

out and built something that doesn't, that deliberately doesn't work. It's too hard. It's too hard for the models. Even Opus 4.5 is barely enough. And it's funny because the folks at Anthropic told me they like it that they're kind of embarrassed some of them because it feels like I've got all these workarounds for bugs in their model, which it kind of is, right? But it's not a bug. It's their model was never trained to be a factory worker and it will be soon. So a lot of gas time is going to disappear. A lot of the complexity,

a lot of the roles that are monitoring, all they're trying to do is tell Opus 4 or 5 to be smarter, and that's being on the wrong side of the bitter lesson, right? So a lot, GasTown's going to simplify and flatten into just minimax rolls. Crew for your max and your pole cats for your ends and I think that's the natural shape and they'll just scale up. And could that be the Polkaz, they might just be sub-agents at top point, for example? Well, sub-agent, I mean, you know, Polkats are sub-agents. It's just that they're more, their first class. They have their own identity, inbox. You can talk to them. You can actually see how they performed over time by computing skill vectors on their work and things like that.

So a little bit more than that than sub-agents. I think sub-agents have the problem of being opaque. I'm going to fire off a bunch of sub-agents to go do this work. And then you're like, okay, let me know when you're done. Whereas with Gastown, you can go look at it and be like, dude, your Polkatz not working. I'm going to poke it. Right. So Gas Town gives you a lot of hands-on, I don't know, steering, right? It doesn't try to be, it doesn't try to get out of your way. It's in your way, Gastown. It's really fun, though. I miss it. It's been down for a few days for me, and I tell you, man, working with regular Claude just stinks by comparison. Because it's like an idea factory. Once it's actually running and all booted up and everything, you can have so many

things going on at once and actually track them reasonably well. Now, it can suck you into a mode where you don't sleep, you don't eat, and you start, it's not good for you. And I actually wanted to talk to you a little bit about what's happening in the industry at some point. But Gastown itself, I mean, like it was all calculated, all the characters, you know, the naming. Why did I even do Gas Town? Right? Why is it? Why? Because I wanted to move the over to the window. Right? Because people last year, when I would say orchestrations coming, they'd say, no, agents aren't, no swarms, no orchestration, whatever, everything you're saying is just not true. And now what they're saying is, bro, you're being pretty aggressive, right? Which is a different conversation.

They're like, now they're like, well, your swarm, I don't know, maybe your swarm can't do, blah, but it's just completely shifted the conversation from the realm of impossibility or the realm possibility. So is it fair to say that you took on more than you you reasonably thought you could chew, you took on this more ambitious ones because you wanted to both stress tests what these models can do and find out what's next. See, find out and honestly just have some fun. Have some fun. Find out what's next. And I'm continuing to do that. So my next thing is I'm going to string a hundred gas towns together. We have a community, a discord. And if Mold Book can get people to pitch in tokens for fun. Like they're paying, they're paying, you're paying for the inference of your,

your agent on Mold Book, right? So if I string a hundred Gas Towns together and we decide to build something together, we will learn the mechanics of Federation. We're probably retracing Ethereum steps, but we will. And, uh, and we're going to come up with something remarkable. It's like the people version of Mold Hub, uh, right? Maltbook, whatever it is. And what, what are misconceptions about Gastown or what is trying to do that you feel it's kind of, you know, gone off a little bit of rails and it's good to clean up. Well, I mean, for starters, I don't think people should be using it and they are.

And I really mean it. Well, I'm always say people should not be using it, like, should not be using it except if you're doing research or if you're like actually understand that this is just a proof of concept. So some very, very clever people that I've been talking to have, have been searching their problem spaces for subsets, categories that Gastown could productively use today at a big company, a big, Fortune 50 companies say. Wow. And they've, they've identified some problem spaces that you could put Gastown on today. And I was like, oh, that's pretty clever thinking. One of them was this company I talked to that sets up bespoke data centers for you, okay, in any region you want, which is something AWS has never been able to do. Google's always tried. And they say it's just three months of miserable button presses to try to install the software and check that it all works. And the acceptance criteria are very clear. It's, you know, it's almost a Ralph loop. But they think Gastown could swarm it and eventually converge on a data center that, works and save all the people the trouble. You know what I mean? And I was like, oh, I, and this could potentially meaningful move the needle on their ability to open up more of these data centers for people, right? Oh. Yeah, go figure. And the same guy was telling me that he's been looking at production incidents, and he's realized their system is already in an indeterminate, unknown, broken state when they're down.

So how much worse can AI actually make it? Now, I cautioned him and said, actually, it can make a lot worse. But he's thinking on the long lines, if there are certain categories of outages where you could have them in investigation mode or whatever, right, where they could speed things up. So people are looking for the fuzzy problems. There was a third one that came along. I forget what it was. But there's a classes of problems emerging for which you can swarm them because you don't care that the results are messy.

It's the cumulative work that, right? But that's actually how I code now. I mean, right? I mean, like I code myself. I mean, I bid off more than I could chew. There's no question about it, man. Gastown is a huge mess right now. And everybody's going, he's going to vibe code himself into a corner and come crying out, you

know, they're pretty close to true. although I did manage just before we got on the plane to get it back on track and it's working again, right? So one interesting about Gastown is you said you don't look at the code, you have the agents, write the code, which is very unlike what your career has been, right? You cared about craft code elegance. Why did you decide to do it on what are the results? I mean, are the results as bad as I would think they would because this is right? Like if you imagine we're going to put like a thousand interns on a project, like we've kind of seen that.

in the past and the result has been, well, eventually a senior injury comes in and cleans up a mess. And I'm just curious, like, how is it better or worse? Well, so the ceiling of what it can actually build productively before it just dissolves into a mess is going up. But right now, I think it's sitting somewhere between a half million and five million lines of code, somewhere in there, probably more on the half million side right now. And with the next drop of an anthropic model, we're probably going to see it jump up to a few million lines, which is pretty good size, but it's nothing compared to what enterprises have. Right, nothing. Enterprises are very, very, very, very, very, very, they have hundreds of millions to billions of lines.

Yeah, but not in one code base. Like, having a few million lines of code is already a big code base and you'll typically have 50 plus people, sometimes 100 plus 200 plus working on it. Right. What it really comes down to, just to summarize this conversation and get to the end is how well you're going to be able to take advantage of AI totally depends on whether you're a monolith or not. If you're a monolith, which almost every company is a monolith, they have one monolith and then a bunch of microservices, right? If you're a monolith, you're kind of hosed because I told you the ceiling's going up for what they can do, but it ain't ever going to hit your monolith. That will never fit in the context window. And you're never going to be able to never in the next 18 months be able to tell a model, go fix my monolith. You have to break it up. Okay.

If you want to take advantage of AI or rewrite it from scratch, it's starting to get faster at this point to think about rewriting your stack. Yeah. One thing you mentioned even before we started that AI can really drain you. It can drain your energy. I can pull you and I can suck you. Can you tell me about this? Dude, there is something happening. that we need to start talking about as a community, as an industry.

Okay. There's a vampiric effect happening with AI where it gets you excited and you work really, really hard and you're capturing a ton of value. For me, I'm doing it all for myself and it's still kind of like pushing me to my ragged edge. I find myself napping during the day, but I'm talking to friends at startups and they're finding themselves napping during the day. It's funny.

They literally try to load each other up with enough context to force the other one into a nap, almost like a compraction event. It's so weird. And we're starting to get tired. And we're starting to get cranked. And I started talking to people in the industry, and they're starting to get tired and cranky. And what's happening is, see, companies are set up

to extract value from you and then pay you for it, right? But the way all companies have always been set up is that they will give you more work until you break. If you can do it, they'll just happily just say, give you more, give you more until you, until your plate flows over and you die. And people have to learn the art of pushing back, right? And that's been a thing for a long time.

But it's changed the equation. The way you push back, the reasons to push back and all that have changed very dramatically and are changing right now because you've got all these people now who can be super productive. And it's like, let's say an engineer can be 100 times as productive, just for sake of argument, all right? Who captures that value? If the engineer goes to work and works for eight hours a day and produces 100 times as much,

the company captured all of that value. And that is not a fair capture exchange. I think we can argue unless if they have early stage startup and they have a meaningful equity, that's a bit different. Yes, yes. But for all the rest of you. But that's not the majority of people, right? It's a minority.

Yeah. Yeah. We're probably getting there pretty quickly. I didn't, you know, we did notice one thing. And you probably saw this as well about six months ago we talked about a lot, the 996 problem at AI startups. And we were like, oh, it's interesting. AI starters, people are working really friggin' long hours and they're posting that they're in the office at 3 a.m. And you could tell.

I'll share with people what 996 is who don't know. 9.96 is 9 a.m. to 9 p.m. 6 days a week, if I'm not mistaken. Which is 9.96 is it's the standard you're expected to work in most of Southeast Asia, as far as I know. I haven't been to China or India, but I assume it's pretty much similar there too, right? there's another group of people who are capturing all of the value for themselves. They go in and they work for 10 minutes a day and they get 100 times as much done and they don't tell anyone and they've captured all the value. And that's not really ideal either, right? So at least in terms, if you're thinking in terms of how can groups of people be successful, it's best if they're all contributing, right?

So what do you do? And I think that the answer is each and every one of us has to learn how to say no real fast and get to. real good at it. And we need to learn how to start capturing. And the correct, this is the new work life balance. Okay. It's how much of the value are you going to capture from being 100 times it's productive and how much of it are you going to pass along to your employer? And this is a really difficult place to be because we don't have any cultural. All our cultural expectations are pointed in the wrong way for us to work harder and they want us to, right? Everyone wants to extract, extract, extract. And so I seriously think founders and company leaders and engineering leaders at all

levels all the way down to line managers, you're going to have to be aware of this and realize that getting your engineers onto this treadmill is pulling them into a, they're using much, much more of their system two. You know, they're doing much, much more of that hard thinking now. The easy stuff is getting automated by, so you're actually draining them at a higher rate. Their batteries are draining at a higher rate. You might only get three productive hours out of a person at max vibe coding speed. And yet they're still a hundred times as productive as they would have been without AI. So do you let them work for three hours a day? And the answer is, yeah, you better, or your company's going to break.

It's very interesting because also like the value extraction, I think, I can see it speeding up. And we see it with a few prominent people, Peter Steinberger single-handedly pushes out with so much more value output, you name it, commit. In any way, that would have been a team of 10 pretty good engineers before. And he, you know, like in all fairs, he is capturing it in the sense that he's, it's his project,

it's his baby. He does not sleep much. So that's definitely sure. going, but the value capture there is kind of okay. But I agree with you that this could be something like in the past, whenever there was a technology shift where people were more, more efficient in your lifetime. Have you seen this where injuries became more efficient and suddenly you could do a lot more with a lot less? And what happened at that time? People got mad.

Yeah. I'll give you an example. Pearl, the Pearl programming language was a massive accelerator. Amazon's website was built in Pearl. Probably still is. I think Facebook technically is too. PHP is a fake pearl. And you can quote me on that.

And both of them were incredible productivity accelerators. And everybody just could see it. You don't want to build websites and see. You just don't. Amazon tried it and they gave up, right? So that caused a huge rift, a huge schism. There were second-class citizens. All kinds of cultural dynamics happened there, right?

I'm curious about how some AI companies deal with this. Can we talk about how entropic works? Yeah. From what I know. from what you know from the outside. I know that you talk with people across the industry, but Antrophic is a very interesting place. One interesting thing that Dario recently said is he thinks compensation specifically

for their staff, the people who are building all these things and they're actually using the models and doing. He said something interesting that maybe we should have compensation where people are compensated even after they leave the company for the value that they created, which is just something completely unheard. but it's clear that he's thinking about this thing that is changing where individuals can create massive value in a relatively short amount of time.

Google, you can send me a check for all that stuff you never paid me for. Okay, just got to get that out of the way. I like that idea. Anthropic is unlike any company on Earth right now. They're operating in a space that is really fragile and they're very protective of it and they need to be because they've created a hive mind.

They're running the company, as far as I can tell, like a pure functional data structure. Remember Crystal Kosaki's book that was such a mind-blowing. You can make data structures that never mutate, then how do you mutate them? Right? And the answer is you just keep adding. It's improv. Yes, and, yes, and.

Right? And that's how they operate. And when you say hive mind, what, what do you mean by that? It's a lot of, it's like the markets today. Vibes, everything's vibes. It just shifts. It's just, right? It's, it's, it's, it's, it's, it's, it's kind of hard to explain.

But you see, here's a thing, right? We used to build products by like making spec and then implementing it and then complaining about it and then shipping it. Oh, and having a roadmap and planning for it. Waterfall. And timing it for the company annual event. Right. But the way. The way you work with like systems like Gastown and they've got their own internal orchestrators is you create it.

And your founders, the one that's the co-founder that was non-technical. You create the prototype and that's your product. And you start building it and you just make it the product until it's, right? So everybody just gathers around the prototype like a can't fire. and builds it. And that is what Anthropics doing at scale with thousands of people. So you're saying that the playbook of a successful tech product might have changed because the traditional wisdom, since the lean startup in like 2010 or so was you use your

prototype to get signaled, that you throw it away and then you build a lot more Polish stuff, right? And we used to, I think every software engine who's been around, you don't ship a prototype, you tell people it's a throw away, you start again, you make it production really scalable, that kind of stuff because you don't want to give a bad experience to people. Yeah. What changed, though? Just the ability to do infinite number of prototypes.

So instead, you make prototypes until you get a great one. And you're like, let's launch this. And so apparently, Claude Co-work happened in 10 days. Somebody went, hey, I did a prototype. And they were like, we're going to launch this. And 10 days later, they launched it. So, I mean, it works. But I guess one important context there, when I talk with Boris Charney about a feature that they did about how they did the tasks in Cloud code, the task list of how it completes.

He told me that in two days, he built 20 different. prototypes that are all working thanks to AI. I didn't know that, but he's doing what I'm talking about. They call it slot machine programming, right? You do 20 implementations and is that what he's doing? Something like that. I don't want to put words in his mouth, but I was just floor because building 20 working prototypes, that would have been two weeks.

And you would have stopped at three, right? That's in our book, actually, if I can pitch the book for a moment. Fafo, FAAAFO is the dimensions of value that you get from vibe coding. O is optionality, which is the ability to create lots of prototypes. What it lets you do is defer your decision until you know what the right answer is, which is cheating. So, of course, everybody does it, right? And it's going to fundamentally change the way that companies are run.

It's going to change the way that people are organized to create software, and it's going to happen this year. It's just fascinating how these changes are coming. But what enables these changes? Is it the fact that we can iterate faster with these things? Look, I saw a phenomenon happen at Google. This is kind of a big company question. There's a big company and a small company answer to your question, right?

Something happened at Google. I went through the golden age of Google where it was like anthropic. It was a hive mind. Nobody was mean. Everybody was innovating and it was wonderful. Yeah, this was the time where the founders were pretty close. You'd go to the chafitia and Larry and Sarah gave you sitting there and you'd hang out with him and just chat. And it was like golden age, right?

And then it changed rather abruptly. We made a few pivots and it became not that company anymore. And in fact, innovation died on the vine like altogether. And since, I don't know, 2008, there has been no innovation from Google. It's all been acquisitions. They have, they've created nothing new. I mean, they did Gemini a few years later, right? Yeah, okay, sure.

They created LLMs and then did nothing with them. That's a perfect example of why innovation dies there. For five years. Right? Five years. They did nothing. So I don't count Gemini. That's a different Google.

Yeah. We're talking about the Google that screwed up. Yeah. I don't want Anthropic to screw up this way again, the way that Google did. Google put safeguards in place to try to keep them from turning into the company that they turned into, which was ossified, you know, territorial. Nobody could. I hired a brilliant dude from Microsoft, brought him into Google and said, figure out what you're going to do. Take as long as you need.

It took him six months to find something that nobody else had claimed already. People claim work and then never do it at Google. So I'm going to tell you. something I've never said before. This is a brand new take. I think what happened to Google was when Larry Page became CEO and he said, we're going to put more wood behind fewer arrows. That was a motto. And he put a halt to innovation. Before then, there was more work than people. And after that, there were more people than work. And so people started to fight over the work. And that's where people started to do land grabs and backstabbing and territoriality and empire building and all the bad stuff you see, all the politics

that you see is about fighting over work. And going back to Anthropic, they're at a frontier and there's infinite work and like literally all of them have too much to do. And a friend of mine, a friend of mine in Amazon once told me that we don't have a lot of the problems that Google has because everyone at Amazon is always slightly oversubscribed. They have too much work. I've heard similar with Apple as well. That's kind of deliberate. But interesting thing, I mean, if we assume I am seeing productivity gains for myself, so I'm not disputing that agents actually make you more productive. And I think we can agree on by how much.

But for me, it's a lot. But if this happens in a lot of companies, people can actually do a lot more work. Do you think a lot of companies that are larger will see politics show up, which typically happens when? Right. If like the catalyst for the bad stuff beginning is more people than work. And all of a sudden, people can do all the work. then the company's biggest problem is going to be finding more work

or they're going to have to get rid of people, which is kind of bad, right? But it's not unlike Gastown in the small. My biggest problem with Gastown is feeding it because it works so fast. I have to work really hard to come up with good designs for it, right? That's what I spend on my, which is why I'm taking naps all day long, because I'm trying to come up with difficult work for it, right? Other people have said this too. This is the problem with gas.

And this is the problem with everybody who's going to use any orchestrator. It doesn't have to be Gastown. That thing will be dead in four months probably, right? I mean, it's the shape that worked in. December 2025. That's not going to be the shape that works in four months, right? One thing that I think, you know, where it might sound that we're talking really abstract, especially for people who have not done this type of work in this self, is like, well, we're talking about orchestrators. They're like all productive. Can you point to something that

has been built with an orchestrator or with this higher productivity that is a production software, either you built it or you observed someone built it, that could show like actually this is way more productive and we can actually see the output or turning it the other way around. Like we're still not seeing that much more output from companies, teams that you would expect. Okay, like a lot of them are having more productivity. But like from the outside, it's easy to be skeptical when we're seeing not much has changed in terms of our data live, the apps. So, you know, we're seeing signals here and there, but nothing major. Like, why might that be?

Yeah, that's fair. my feeling is that probably people have a low tolerance for nondeterminism and these things are fundamentally nondeterministic. So they can't just go replace customer calls on their software because they could be wrong. And it doesn't seem to matter that humans are also wrong very often. And AIs can, these days, can very easily get to the same level as a human as an average human in the job. But I think there's still a lot of risk aversion, right? So I think that the companies that are actually running with this are actually starting to see the results.

And it gets going to be reflected in the quarterly earnings invisibly in another ways at first. Could it be that we're focusing on building new tools? I'll turn it around and I'll say, what if what we're actually observing is that innovation at large companies is now dead. And we are only going to see innovation from small places, which is kind of what happened when cloud came out. And Facebook was a college kid at one point. Facebook feels like the biggest company in the world right now, but it was one dude. Okay. And so when a new enabling platform technology substrate appears, you're going to see innovation

that the fringe is because of the innovator's dilemma. Big companies can't innovate. They're all running into this problem. They may have hyperproductive engineers who are producing at a very, very high rate, but the company itself can't absorb that work downstream. They're just hitting bottlenecks and these engineers are getting shut down and they're quitting, right? So I think what's happening is we're all looking at the big companies going, are you going to give us something? And the answer is we're looking at the big dead

company. So we just don't know they're dead yet. Do you think they're dead because, for example, it can now be cheaper to do something. Like we can just say the internal punching back Zendes customer support. They have been the de facto place to do your customer support because your agent can sign up. They get this UI, they get this workflow, et cetera. And for AI native companies that are using MCPs webnot, it makes no sense for them because they just want an API, which Zendes does not want you to give to you because they want to charge extraordinary amounts for you to come to their platform and buy their AI for, you know, 10 times a cost. That model is going to struggle a lot in coming years because people will build their own stuff bespoke with APIs.

This is, this is my platform rant in real life, right? If Sendesk doesn't make themselves a platform, then they're going to, they'll have product themselves out of existence, I think. And the platform for the for looking ahead, is it APIs? Is it the, I think so? I mean, as far as we can, no, maybe not MCP, right? I mean, what had Anthropic found that what works better than MCP is having the AI write its own API to call the MCP? Because they're so good at writing code. But then nothing really changes because platforms always APIs from the beginning, right? Yeah, so why do we need an MCP?

Well, we needed some way to declare what the tool does in an AI way. But I mean, like, I just, it's so loose and so flexible. Integration's going to be really easy. I don't know. I'm not following that space well enough to know if MCP is going to continue to be an important, dominant player, or if the AIs just use stuff directly, like, via command line tool? right or APIs. But either way,

we're moving into this world where the innovation is coming out of new shops who have adopted and adapted. And I see big companies struggling really bad right now with this. I wonder if we will see a lot more of these building blocks

that we didn't know we needed. I think we're going to see a huge ecosystem of building blocks for people who are not non-technical who want to build stuff and they need those APIs. And right, you know what I mean? Like for storage or for matching or for whatever it is, they need to do. So I guess if you're in tech and if you're looking for an idea,

either because, you know, like your job is looking a bit shaky or you actually just want to do something like now could be a great time to start building some of these building blocks that work. And like reliable building blocks will probably be in need that are that have states that have SLAs, whatever, have some, some importance, right? That's not trivial to do. That's right. Because AIs are lazy. With good reason, they don't want to burn tokens if they don't have to. So if you provide a service that's going to make something convenient for them, they'll absolutely use it.

Yeah, especially if it's a service that you need to maintain, for example, like you need to keep up with, may that be regulation or changes or logging or whatever. Yeah, that's kind of a lot of work to do, even to prompt, like, to, and go back every day to prompt again to, like, update and all that. Also, as humans, we're also lazy. Yeah, I mean, well, Larry Law call it, right? That's one of the virtues of a program. Yeah. I want to go back to another one of your essays from 2012, which was called the Borderlands Gun Collector Club. You're the one that read that one. I got recommended on Blue Sky and a lot of people liked it and I read it and I realized I didn't read it.

And this was a really interesting essay because seemingly it has nothing to do what we're talking about, but you talked about gamification and you talked about how this Borderlands game, which you played apparently right? Back in a day, yeah. back in a day. You mentioned how after you completed the game, there was this weird thing that the game developers probably accidentally put in there. People kept coming back to have custom guns. And these were like a meta goal that the designers probably never thought of, but it actually made the game pretty kind of addictive. And you called this as a, I think it was like some sort of elder game or something like that. And you were kind of saying that, hey, this was pretty smart. There was an accident from the game designers, but maybe more game

designers should do this because it just makes the game addictive. and, you know, like not saying that. But since that, it was in 2012, we've seen so many games just have, like, deliberate gamification and not just games, but a lot of other things. Yeah, a lot of them found that mechanic eventually. Who is it? Did the Borderlands take two or I forget.

Anyway, they figured it out early. Then they didn't capitalize on it. But, yeah. So interestingly, I think, yeah, gamification, gamification's kind of rearing its head. People have pointed out, like, people are making game finance to Gastown, right? I mean, why don't make it,

game. Like, come on, man. I mean, like, look, we have literally, we have games for running factories. Imagine you're running an actual factory. How cool is that? Right? That's what, guess what Gastown is? That's why it's so fun, actually. Do you think that one of the reasons that some of the A.A. agents are more successful than others looking at specifically Cloud Code is they also did some gamification where there's always something showing there, right? There's a tinkering. There's the, there's the different things that keeps talking to you. There's always is some of maybe accidentally or maybe deliberately? Oh, they have the best product managers in the world and they have,

they have done absolute magic with command line UIs and stuff that they've done. It's wild. But look, I mean, come on, right? That's not going to work for most devs. So that's why Claude Co-work is so cool, right? Because it's showing us the direction that things are going to evolve, I think. Yeah. So I think developers will use cloud co-work or something more like it. With traditional software, we have tech depth, and we know how to deal with it, and we've talked so much of this. In fact, if we think

about what we spent, we're very busy with the 2010's, tech depth, collecting it, paying it off, migrations, yada, yada, yada. Now that we're doing, you know, a lot of vibe coding, or you call it vip coding, but agenic engineering just turning out a lot of code, how do you think we will recognize or deal with or do we need

to deal with this like vibe coding depth or agentic depth? You do. You do. You do. do. One of my upcoming blog posts is about this actually. I've discovered that there's a thing. I've given it the name of, it's called a heresy, okay, that happens in vibe coded code basis that you're not looking at, where an idea can take root among the agents that's incorrect. It's, there's a wrong architecture or wrong data flow or whatever that's causing an impedance mismatch for the rest of your code. And what happens is I call it a heresy because they have the, they have a tendency to grow and to come back, and they're really hard to weed out.

Okay. I had a bunch of them in Gastown. There was a Polkat heresy that kept coming back. And so what would happen was it's invisible, and your product stops working properly along the edges, and you don't know why, and you start having the agents dig into it, and you realize you've got a fracture, you've got a fault line. You have, like, say, two complete databases

that are both live and operational, and you're randomly choosing between the two of them, right? And you didn't realize this until just now, right? You find terrible, you know, things in your code, right? And you try to get them all out, but there will be one reference to it in some doc somewhere that an agent picks up on and goes, oh, that makes sense. It's the heresy and it returns. And the agent does the wrong thing and goes off and rebuild the heresy and it starts to spread again. It comes back, right?

It's like the agents want a system to work this certain way. And you're telling them, no, I want it to work this other way. And you're fighting with them. And what you have to do is you have to actually document the heresy. in the beginning of your prompting and say, this is one of the ways that you can go wrong on my project. Don't do that, right? And then you have to remind it periodically

or even put in tooling to keep it from doing that. Another heresy is that my agents all think they should be doing PRs. It's like, I'm the maintainer of this code, man. Just push to Maine, right? Or a branch or something. Don't make a PR. It's just polluting the PR space.

That's for contributors. They can't get this today. Now, I could put a bunch of hacks in, but that's fighting the bitter lesson. Opus 5 will be fine. Opus 5 will be like, oh, you don't want PRs, I won't do PRs. What is the bitter lesson? Oh, the bitter lesson, yes.

Richard Sutton wrote a very, very short essay. It's like 800 words. It's one of the best essays ever called The Bitter Lesson where he's like, yeah, we're AI researchers and we learned a bitter lesson, and you need to learn this lesson. The bitter lesson is don't try to be smarter than the AI, okay? You think that you've got special knowledge, the humans bring special domain knowledge to this problem, and we're going to teach it so that the AI will be smarter. What we found was bigger is smarter.

always. So it's like more data, right? Yeah. And so like when they're going into Australia right now, you know, you've seen the drawings, you know, how big Open AI's training center was, how big Anthropics Training Center was, and now the training centers that are, you know, 10 times larger. They're massive. They're in Australia because they have all the energy in the land and everything.

But they are going to make models that are 10 times or more smarter than the ones we have today, right? We talked about the vibe that, but does it not pain you? I mean, as someone who has built software, you know how to build good software, you you went in there to clean up the mess of junior teams or like messes, you were, you could clean it up and with your eyes closed or maybe you had to keep it open. Does it not pain you that when you describe, oh, the AI going off trial and doing it? If you scaled it back and said like, hang on, like, let me step in, let me make these decisions. Let me be the architect.

It would not happen. Yeah. Well, see, the thing is, I've also been a vice president at big companies of engineering. True. And so when I'm working with a team of 80 agents, it's not very different from working with theme of 80 engineers. Any one of them can screw up too, engineers. Oh, so you've done that, right? I have, and I'm telling you, they are isomorphic. So what is the bitter lesson? The bitter lesson is, don't try to be smart. Just try to be large. Okay. Now, that's not the only way to make

the AI smarter. They can also make them smarter in a couple of other important frontiers that are also getting developed. And so to tie it full circle to a beginning of our conversation, everyone who believes right now that the curve is S-shaped, they're 100% correct. They are 100% correct. It is S-shaped. Eventually, we will run out of resources. The world will be out of resources and it will flat, right?

But I can tell you that there are at least two more cycles left in this, and that means they will be at least 16 times smarter than they are today, and that is going to cause all of knowledge work to be subsumed by this stuff. Before we go all the way there, let's talk about, how all this better models, more productive, could impact personal software, things that people can build themselves. This is what I thought you were asking about earlier when you said you wanted an API from Zendesk.

Think about it. Everyone's going to want to build their own software. Oh, I was talking about a business for a personal. Oh, business is name. But yeah, but also personal software. Like what would the future look like when everyone could have like open claw running in their closet or gas town or they can just, they don't have to run it. on their thing, but they can turn to this agent.

Yeah. How could that change, like both personal software, but also the software industry as a whole? Because for a long time, personal software was the privilege of us engineers who could build it and we built our tools and we had open source and we had some billion-dollar companies grow out of some of the cool things. But what do you think could happen now that this will be democratized to some extent? How do you think open source could change?

Open source? How would open source change? Could it could have changed. Because one interesting thing that I'm seeing is a lot of remixing happening. So people, you know, now a lot of open source projects don't really take poor requests because there's a lot of not great ones. But a lot of people are just remixing. They're just taking the open source project. They're telling the AI make this change. And they publish it as open source as well. Often no one looks at it. But now they don't need to ask for permission. A lot of

people are like weaving things together. They say take this project, take this thing. Right. And it's actually so they'll make a lot more open source. I see what you're saying. In the old days, the F word, fork you used to be like kind of a declaration of war. Yeah. If you forked somebody's project, it meant you had had enough of them. Like, RooCode forked Klein, and then somebody else forked RooCode. And it's just like, I think it's now going to be an everyday occurrence, right? Because it used to be that to fork, it would be a lot of time and effort to maintain a fork to merge back the thing. The cursor is a fork, isn't it?

It is. Yeah. That's a lot of work. That's a lot of work. Yeah. A lot less work now, right? So, yeah, everyone's going to be forking. So, yeah, no, I think that that's a natural, yeah,

consequence of everybody writing code. Yeah. Just like everyone can take a picture now. That didn't used to be true. Yeah. What are some of your beliefs from early on in your career that held really, really well until recently, and now we've just abandoned because of AI? Engineers are special.

There's one. Come on. We are special. I think we're so special. Yeah, sure. We learned how to do something by hand that computers can do now. Kind of cool, I guess. What about the engineers?

mindset. We have that. It's not just coding that with you, right? Well, for one thing is, I believe that our thirst for new software will never, ever, ever diminish. It will only grow. And so we're at the beginning of software. All the software we have right now is garbage. That's right there, OBS especially. And we're going to see a new world over the next 10 years where software is commonplace and good. And you'll have your choice. And it won't be, I have to pick and choose between three really bad OOAS solutions. or or company HR systems or whatever stupid ass thing, right? Like today the selection is terrible.

SaaS is awful. The whole, the whole, right? Airline apps. Airline apps, right? I mean, we ran a vibe coding workshop in Sydney where a dude actually wrote an airline checking app for himself and got it into the Android queue before Southwest realized and shut him down because he was a bot. But that's what people want.

They want personal bespoke software and they're going to get it. And so, yeah, I think you're going to see. That's why when Jeffrey Manuel forked, beads. I was like, you go, you go. He's, I feel so bad about it. I'm like, dude, this is the new world, man. Fork, fork, fork, fork. Let's have beads in every language. I don't care, right? I mean, in all fairness, like, just looking at it from the positive side, like, I wouldn't mind just having good software for the stuff that I use day today. My utility provider is, someone is getting better. The government websites that I have to access, my, my, paying my

parking fine. The other day, I tried to send a package to Canada from the Netherlands and the post, Like the official post has been broken They cannot send anything for a week And I see the exception they cannot fix it So I had to go DHS and pay a bunch more money That's right And like there's a lot of bad software out there And your agent will be dealing with it

Not you Yeah But I think people who write software That agents like and prefer and choose And then they find a way to market it And get the agents aware of it They're going to win big Because everyone will use agents

Will I'll be dependent on it Well plus also I guess software or ways of making agents right quality software? Because I have a feeling like you will want to do better stuff that if you do the same, you're not going to have a business, right? Yeah. So, I mean, look, I think businesses will compete on more and more complex software. The ceiling will just keep going.

We're building, like, we're going to, until we build the Death Star or whatever, right? I mean, like, we're building bigger and bigger things. Oddly enough, Gerge, I am an optimist through all of this. That's my first belief, I think, first and foremost, is that it's all going to work out. So asking the optimist, now I got this question of, I think, thing was on blue sky. This person asked like, how do you think the software industry will continue to exist if

we get to the point that any software could be trivially cloned? Yeah. Where will that leave us? What cannot be cloned? What is the moat? Just, we just jump ahead. We assume that these things actually can do it. Human connections are probably the biggest one. As

as, you know, kind of almost counterintuitively, as software does more and more automated for you, people are going to be like, oh, well, yeah, but that's that's just automated. I want a human to do it. And they will literally want a human to bring their thing instead of a drone. You know, they'll want humans to curate things for them.

And I think that's going to be humans will be a moat. Do you think if you look back at some history like from the history of the rest history, like have we seen some changes that felt a bit like this? And then we saw some professions thrive because of either more automation or, you know, like stack overflow. I don't know. I mean, like that one jumped to mind at Mechanical Turk. I mean, like we've seen a bunch of. bunch of big step functions. It's just that we're, we're about to see a whole bunch of them at

once, right? I mean, look at the news lately. I mean, like, you're like, this is the funny thing is around like, where's all the innovation? And then in the news all day long, they're seeing all this innovation in AI. It's just not coming from, you know, the Walmarts and Microsofts. It's coming from random individuals, right? But the innovation's there. And from the startups that I've been talking to, you know, I've been talking to anywhere from two, five to 20 person startups. I think we're going to see some really impressive stuff launching in the next couple of months. Are you seeing these small startups change how they work? Oh, God, it's so different, dude.

Tell me how. It's so different. Okay, for starters, for starters, I think in the new world, I'm convinced of this, okay? Everything that you do will either have to be fully transparent or you're hiding it for a reason. Tell me more. In other words, if you don't want people to see what you're doing, just don't show it to them and they will never see it. And if you do want, if you do want them to see what you're doing, then you had better get it out in front of them as you do it instantly or else the train will pass you by.

So like what they're saying is like, so I told the story of my blog. People have heard it, but they like yelled at a teammate. They were mad because he implemented a feature that they'd asked for two hours before. And they were like, two hours ago, it's changed too much since then, right? And he's like, well, what do I do? You know, what's happening is they're getting into this mode where they're realized that stuff moves so fast that everything is invisible. effectively from the volume. And so you have to be extremely loud and transparent and intentional about saying everything that you're doing.

So that if anybody else is doing it, they can stop you right then. And if they need to integrate with you, they can start right then. And we're talking about startups that are looking for product fit, for customers. They actually just want to get what we call product market fit, where the traditional wisdom was built something amazing and then release it to the world. That's right. That's right.

Try to find product market fit in secret as much as you can and then launch it. and then tune, right? That's the formula. And many people feel at it. It used to be. Now, like you're saying, with Gastown, I realized I'm not going to find product market fit by myself. So I launched it as soon as it kind of worked and was like, help me. And that's how I found out about the adult database, which was a big change.

And people fixed a bunch of bugs. I got 100 plus PR the first couple days. And right? And so it found its way closer to product market fit just by me getting it out there. And would you say that is brought to. Like on one end, people look at you, well, yeah, it's just one other open source project. But is it bringing actually opportunity? If you wanted to, could you turn this into a business?

Has it brought you the things where I'm getting at is these things that take off either's open source projects. Like, can they actually turn into actual businesses? Are we at that stage? I promise you. If you had made Gastown, you would be, you would be shaking venture capitalists off you like ticks right now. I am. They're finding me everywhere.

Okay. And I tell you, it's because there's a lot of money out there right now, sniffing, wanting to find its way into, I didn't know something big's going to happen, right? And it's looking, and you can see it in all these different micro economies that are springing up. But nowhere can you see it more clearly than when you launch something cool like Jeff Huntley did Ralph Wiggum, VCs, right? You know, everyone want to talk to. You just got to be real careful because anything you build probably has a real short shelf life at this point, right? A real short one. I don't know. I'm not attached to Gastown anywhere. way because I think it'll be supplanted by something better within six months, if not sooner, right? So, so. Too attached. So let's assume that staff engineer is listening to this podcast or watching it on their commute, and they're at the type of company where they have co-pilot still. There's people like this, and they're using it. And they're, they want to believe you, but they're not sure they can.

What would you tell them? What is the, the thing that they can do to get proof that you're actually right? And this thing is, is working. We're not at 100%. We're not even 50% for. for people. Like a lot of people who are in this field have tried it out, but there's, there's a lot of people who are. Oh, yeah. I would say probably still 70% aren't, aren't doing it. Yeah. Um, so like, what would I say? I had a really good message for them.

Oh yeah. Get out. Get out. Um, so here's the thing, right? Co-pilot is, uh, if you were to line up all the tools, you know, from best to worse, right? Co-pilot is like, you're a line, right? Right. It doesn't even know about the line, right? But it used to be the best four years ago in 2021, right? Yeah. It was here. It was a personal competition. Even maybe two and a half years ago, I was quite stunned that somebody asked, does anybody

use co-pilot at an AI Tinkers meeting? And somebody raised their hand and he goes, do you have to? And everyone laughed. And I was like, what happened, right? The brand just tanked. But I'm serious. If you're working at a company that gave you co-pilot, they think that they're starting to move faster.

And there's a barbarian horde of people using Opus 4.5 that are, you know, destroy your company. sooner or later. So what you need to do is go into the crazy part of crazy town and figure the stuff out and start building. And because we are moving into a world very quickly this year where proof of work is so important. And I mean proof of work, not the Bitcoin sense, but your proof of what you have done, your resume. And I don't mean your resume because nobody's going to believe that. I mean the actual work that you did, which has to be visible back to our transparency, right? I think everyone's going to be bringing their work with them. I mean, the notion of proprietary work is starting to

like be threatened, I think, because it's so easy to fork, it's so easy to clone, it's so easy to route around. If you have anything proprietary, you become this thing that everybody just wants to run around you. And so big, big changes are aflit. But man, if you're working with co-pilot right now, you are going to get left behind. And so what you need to do is get yourself, find it a half an hour a day to go play with, with Cloud Code, right? And it's like I said, or if you're a company, make your token burn as high as your investors will let you go, right?

Because that token burn is your practice. It's your, it's your sorting things out. So I want to ask you the other way around. Let's assume you're just wrong in terms of the curve and we're at the peak and it will not be 10x. It will plateau at 3x. Or let's just say the next model is inexplicably dumber than Opus 45 and we've peaked. What would happen to the person who takes your advice? and they go all and then they learn things,

what's the worst thing that could happen to them? If these things take off, it's a great investment, right? But what would happen to them if they followed your advice and the models didn't follow? Where would that lead them? Exactly where they need to go, because the damage is done. Opus 4.5 made this officially an engineering problem.

We don't need you AI researchers anymore, thank you. You can make smarter models, I guess, but we don't need them. Because we have something that can take a bite-sized chunk out of a mountain, and it's a bite size about town size now, and so we can eat mountains, okay? It's purely an engineering problem at this point.

It's like fire or steam. It's a force, it's a power. And we wrap layer, layer, layer, layer. I worked on a nuclear reactor. I was in the Navy. I know how these things work, okay? We are going to put layers around Opus 4.5, if that's the smartest model ever,

and that will do all of the engineering from now on. So it's done. So it's okay to jump into the pool now. Your first job was about debuggers, or not debuggers, but you worked at this amazing company. You told me they had the best debugger tools. What was the name? It was Geowworks and the debugger was called SWAT and it was amazing,

time machine and all that. And on the first pragmatic engineer interview when we talked, this is in the newsletter, you are actually saying that you, to this date, you've not seen as good of a debugger, but you're kind of determined to build at some point and help build that. I did build a debugger enclosure for the JVM called Ganja.

It was actually pretty cool, but then I got an argument with Rich Hickey about how well he wanted to support the JBM, and he doesn't. But anyway, you're a guy who is passionate about about a story somewhere, though. You're passionate about debugging. What will happen with debugging? What will happen when debugging tooling? What do you think the future of debugging is?

With agents. When I see agents say, I'm going to debug this, they all use prenefs. So, you know, I'm curious. It could very well be that they just haven't been trained on debuggers yet and that they'll I'll wake up in six months and go, oh, I should have been using this. But it could also be that we don't need them anymore. I don't know.

And another step further, what do you think the future of the developer workstation, like our rigs, our machines will be, right? Like, do you think it'll be phone? I want gas down on my phone. I almost have, I have it, but I just haven't worked on it.

Peter Sandberger told me that he had Vipe Tunnel where you could do it from a phone. He said he stopped it because it became too addictive. Oh, yeah. No, tail scale. And yeah, actually, the only thing that's keeping me from just being addicted to do it all day long is it's too hard to enter control characters in.

But that's going to get fixed at some point. Programming on your phone will be a thing. But so do you think that developer workstations can be just like with Chromebook whatnot, or we actually want beefy ones which can run our local agents, whatnot? Like where do you think it'll be headed on the short term and then maybe on the longer term? Yeah. See what I mean? Local models.

Yeah. No, I, um, look, I love my laptop. I've been programming 40 years. I get the local thing. But, uh, I've been saying for at least 15 years that we don't need this stuff locally, right? Google had an amazing client in the cloud, high-speed network connection. And what you can do with it. CITZE was the base and then Cider was built way up on a higher layer. But when you get something like that and you're not restrained by that, especially in the world where you can run kind of unlimited agents based on your pocketbook, yeah, people are not going to be one of working on their laptops.

And I've already, Gastown has already completely stressed out my laptop to the wire, you know, because Cloud Code actually takes quite a bit of memory. So yeah, I think we're moving to a world where people will work on servers and on mobile devices, probably less on iPads, not on laptops as much. In the past, you've said that one of the most important kind of predictors of the bulk productivity is language design, well-designed languages are easier to work with. Do you think this has completely erased or do you think it might come back at some point, either purpose-built languages? I think there will probably be purpose-built languages by AIs, for AI's maybe. But right now we're in a funny place where some languages work better than others still because they have better training data. But in the fullness of time, all the languages will work equally well. I push back on that.

Like if a new language never has training data, how would it work? No, I mean, I'm sorry, all the existing ones. Oh, yeah. TypeScript, it struggles with TypeScript today. Yeah. It does. But it's not going to in one or two model, really. So could we see a stagnation?

Just fewer languages or no languages launching because they just get the job done. And launching a new language seems a bit suicidal unless you, like, bring a bunch of, like, training data with it, right? Man, that's a loaded question. I mean, I didn't mean to make it a load of it. No, it's a good question, right? Part of me says, like, languages just don't matter anymore, right? Any more than assembly languages matter except for a few people who are trying to optimize really important things. And then everybody else, it just doesn't matter, right?

But then part of me says, well, energy is the most constrained and important resource on this planet, and it's only going to get worse. So finding better algorithms, finding better ways to solve problems is often a language problem, finding a DSL, you know. So I think from an optimization perspective, an efficiency perspective, the search for new languages will probably continue. But for pragmatic, for every day, I don't think it doesn't matter what you pick. Now you even ask your agent what language it's using. So as a software professional who loves the crafts is into, you know, languages, debuggers, tooling, etc. a lot of what we talked about is pretty, pretty sad because, you know, like a lot of the beauty, the challenges that we worked, it seems they might be going away if we continue and if this continues as well. How did you work through this yourself? And also what is what is the thing that actually excites you looking ahead? Right. So I had the benefit of going through 30 years of graphics evolution. And so I saw the sadness and I saw the resulting much better games we got after all that. happy stuff we were doing by a hand moved into the hardware.

We're sad because we're used to it. Change is part of life, okay? And at one point, I had to say goodbye to assembly language, right? I was like, most compiler writers. They finally caught up. And then we were mad. But then we were happier because compilers are obviously way better than writing an assembly language.

Anybody would be stupid to say, oh, God, yeah, no, you're not a good engineer if you can't write an assembly language today. But that was actually what we were saying in 1992. Yeah, and then you had the blog post out in 2020. as well. Yeah. No, I'm just saying stuff changes. What you need to know as an engineer will change and you can't rest on your laurels and

we're going through a period of faster change now. But you have helpers called agents that can actually help you through this change. So stop complaining and just go do it. Yeah. And I think just recognize we're in this industry where change is a thing. That's right. Now with that said, I did go through the five phases of grief, right? Five stages of great.

I mean, like I went through, I don't know if I, I don't know about anger. I was angry, really angry for a lot of reasons two years ago. But no, I mean, like, if you've ever truly grieved, if you've, like, lost someone, you know that it hits you in a lot of weird ways where you feel realities disconnected. You feel sick. You feel stunned. You feel all day long. The world goes monochrome. All color disappears. All kind of weird stuff, right? And I went through that for about, I don't know, six or seven days. It didn't take me that long to get through it, fortunately. Or maybe it was that was the peak. And I was surrounded by a few months of it on either side. But there was a period that I went through it where I, was checking off things that no longer mattered that I had really cared about, like my ability to memorize or my ability to write or my ability to compute or whatever, all those things, anything computing related, I was very sad, right? Because those things made me special somehow, right? But then to your question, what makes me excited?

Like, as soon as I got through that, I was like, but wait, I'm writing 10 times more code than I ever was, and I'm having fun and why should I be sad? Right? And so I realized it's just, it's just me holding on to the old. just like I did in graphics. And there's no point because the future is actually more fun than the present. It's going to be. You're known for your predictions, and I'd like to put it to a test.

Let's give some specific predictions for next year in 2027, things that you think will happen either with how we develop or how the industry works. I think that my wife is going to be the top contributor to our video game. Ooh, bold claim. By the summer of next year. And she is not a developer, I'm guessing? No, oh, no, no, no. but she loves our game and she has lots of ideas, right?

Amazing. Yeah. In fact, I think my whole family might be in on it. I'm serious, man. Programming is going to be for everybody and it's going to be the most amazing thing because you know how much fun we've been having all those years and we've been telling people it's really fun, but now they're going to get to experience it, right?

I look at my kids and how they look at AI. They're having so much fun with it, creating, they're just prompting Gemini or any of these with their imagination. And they actually have, they don't think it's weird. I think it's weird, so I never would think of it, but they just enhance our photos with, like, squirrels on my head. And it just made me laugh and fun. And you realize, like, there's just a lot of fun and new things with it when you let go or you never knew what was before. It's given the people the ability to do very sophisticated mashups of anything. And mashups are really where innovation happens, right? Innovation comes from taking things and putting them together and seeing where it goes, right? We're going to see everybody innovating, man. And it's going to be the most amazing thing ever.

And then we're going to need ecosystems of agents that can go find stuff that you like because there will be so much content. How are you going to find the stuff that's really like that you like? You're going to have an agent that knows you really well. I think any software engineer who wants to go make a big business right now should go start working on agents that know how to go and search the new world, everything that's coming on, I don't even what we call it, right, the work pile for software that you like, for experiences that you like. if everybody's creating it, think about it. When the internet came out and everybody can make a web page and upload shit, we needed aggregators, we needed, you know, we needed search engines, we needed ways to organize and find and surface the good stuff, right?

None of that exists right now, but everybody's about to start coding. Like, right? You know, and so like you can get ahead of this. This is why I keep saying, just believe the curves, pick a point on the curve and aim for it, and you will land there, and you'll be first when the AIs are ready for your thing. I think as N-years, we already can build. We don't need permission.

We can use this whole super efficiently. Right now. And we are ahead of the rest of the world right now. Right now. Well, it's exciting times. Well, Steve, we'll have to check back on how, if that prediction will come through with your wife contributing more. But this has been, I think, really eye-opening. And it's, you know, sometimes I think it's good to go through the has-be and the can-be.

Yeah. Well, thanks. I hope you enjoy this conversation as much as I did. An interesting thought from Steve is his parallel between the graphics industry and what's happening in software engineering right now. In 1992, Steve was learned to calculate where individual pixels go on the line. Two years later, the same course was teaching animation. The work in graphics went from writing device drivers to build the game world and physics engines. It all just moved up the abstraction layer.

Steve's argument is that software engineering is going through exactly that same shift right now, except it's faster. Instead of asking, will engineers have jobs at all, A better question might be, what will the new jobs we do as software engineers look like? Another thing was the grief of this change. Steve is someone who spent 40 years building his identity around compilers, debuggers, elegant code, and then one day he sat down and started checking off one by one the things that made him special that no longer mattered. His world went monochrome, as he said. Within a week or so, he came out from the other side and realized he was writing 10 times more code

and that he was having more fun doing it. Still, I think a lot of engineers are quietly going through to something similar right now, and it's usually taking longer than a week to digest all of this. Finally, one thing I found really honest from Steve was his point about value capture. If you become 100 times more productive with AI, who benefits? If you work 8 hours and produce 100 times the output, the company captured all of that. But if you just work 10 minutes in a day and produce the same value as before, you technically capture it all of it, and your company captured none of it.

Now, neither extreme is sustainable. Steve is saying that this new work-life balance is a question that we'll need to figure out. We don't have the cultural norms for any of this, and it's going to be messy as we figure it out. If you've enjoyed this podcast, please just subscribe on your favorite podcast platform and on YouTube. A special thank you if you also leave a rating for the show. Thanks, and see you in the next one.