The Pragmatic Engineer · 1:21:01 · https://www.youtube.com/watch?v=1VqKUrxR2C8
1. Intro
0:00 Objectively, stuff has become easier, but then why am I thinking as hard as I ever have? None of our competitors are crushing us either. And we're in the coding agent space. All our competitors are super into AI. So, you would think in our space there would be a huge gap, but there just isn't. The 24 to 29year-old engineer will soon become the most valuable asset in technology because they have prei principles and post AI speed. >> Person like me has all the advantages.
0:20 Person not like me has all the disadvantages. Everyone is just saying mantras to themselves. A defense mechanism is to confidently assert a future in which you're a winner. And that's almost what every single prediction that you see is happening. >> That past 10ish years of building dev tools and understanding dynamics is really helping. The strategy that we know how to play really well is to pick one temporary bad guy and then galvanize all their competitors, push something forward against them.
0:41 There is a world where the net result of all these AI coding tools is the same amount of work gets done, but all the engineers are happier cuz their job is easier. That's not good enough for a lot of companies. So they're just going to say [music] Doc Rod is a co-founder of Open Code, the most popular open source coding [music] harness.
1:00 He's also a very downsource when it comes to AI, which can be a bit surprising when you consider [music] that he built such a widely used AI tool. Today we talk about the rapid growth of open code to closer to 10 million active users [music] in less than a year. The memo Dak sent to his team admitting they were shipping too many features, taking on too many hacks, and AI usage not helping them move faster. [music] why inference is one of the most profitable businesses in tech right now and why even open code is bottlenecked by GPU supply and many more.
1:26 If you'd like to ignore the hype on social media around AI and instead talk about where it helps or hinders productive engineering teams, this episode [music] is for you. This episode is presented by antithesis. Verify your systems correctness without human review or traditional integration tests and avoid bugs or outages. I'd also like to mention our season sponsor, Turbop Buffer. You probably heard someone say rag is dead these days, but it's not. It just doesn't mean what it meant in 2023.
1:52 Back then, retrieval was pretty straightforward. The human asks a question, your code embeds it, you hit a vector database, top K results come back, those get stuffed into context, and the LLM answers. Now, look at what's actually happening inside something like Open Code or any serious agent product. In 2026, a human sends one prompt to an orchestrator agent. That agent fans out to sub agents. Each sub agent is hitting separate systems. A vector index, a full text index, grabbing the file system,
2:17 running CLI commands and SQL against OLTP and OLAP stores, reading and writing a memory system, reranking results, looping, and calling more tools. One human prompt turns into dozens or even hundreds of searches across totally different shapes of data. In practice, this means a lot more complexity, a lot more cost, and a lot more potential performance issues, especially when you need to scale up the system. This is exactly what Turbo Buffer is built for. It's a ridiculously scalable, fast, and cheap search engine.
2:42 It's built on top of object storage for reliability and scale with smart caching on MVME SSDs, so it's very fast. It's priced so you can let agents loose with proper in 2026 without seeing your bill explode. Check it out at turbopuffer.com/pragmatic. Dax, welcome to the podcast.
2:58 >> Yeah, thanks for having me and thanks for coming all the way to Miami. >> I wanted to jump in something really interesting about you. You're building one of the most popular AI engineering harnesses, open code, which is speeding up how people write code and and just like turn out software. And yet you're claiming that this itself is not enough. Like this itself will not get us to better software. I've always said the easiest products to build are ones that you can use yourself.
3:23 And obviously we built Open Code so that our team can use it and it's like we are the customers of the product. Uh so we use it aggressively as much as anyone else can. And of course it is like we build it so we think it's useful and we use it every day and it's a critical part of our workflows but all the old problems that I've always struggled with are still there. I'm working as hard as I ever have.
3:46 I'm struggling as much as as I ever have. So a lot of the job has become easier. But yeah, it's it's a weird feeling because objectively stuff has become easier. But then why am I like thinking as hard as I ever have? You know, it's a a weird feeling to have both those things be true. And it's interesting because the like a lot of the people who are decision makers, CEOs, often hands-on people like hands-on CEOs, CTO's, founders at companies, they kind of think, oh, look, we've got these tools.
4:13 Coding used to be the hard part, right? Like like objectively, it took us so much time. It it still takes, you know, to get into the zone if if you're going back to coding by hand. So if that's faster, cuz that's where we used to spend most of our time. Like it should be faster. Like everything should be faster. But why do you think this is not the case? Or or like what is getting in the way of like just like shipping high quality software faster, better, right?
4:37 >> Yeah. I mean, there's different there's different life cycles, different companies. There's like pre-product market fit, there's achieve product market fit, which is kind of where we are. Uh, and there's companies that have like have had product market fit for like a decade. Uh, and I imagine that things look very different across these three. For us, pre-product market fit, it to me it doesn't really help that much cuz you're trying to figure out what you should be doing.
4:56 Um, and yeah, like maybe it helps you swing a lot. But I've always thought it's better to think a lot instead of swinging a lot. I think you could you can eliminate a lot of ideas or directions just by, you know, spending a lot of time in your head and with your team talking. Um, obviously AI doesn't speed that part up. We're at the phase where we're we've achieved product market fit. Now our task is to kind of hit the potential that we have.
5:18 Um, and the issue for us is there's a million different directions we can go in. There's uh all the obvious stuff we can do. There's all the stuff that our users are telling us that we have to do. There's stuff that our competitors are doing. And it's very easy to just one to one do each one of those things because we have a problem, prompt the agent. Competitor has a feature, prompt the agent. User has a problem, prompt the agent.
5:41 If you add that up, you think, "Oh, we shipped a thousand features. Now that adds it to a good product."It actually adds it to a horrible product. >> Like a Frankenstein. >> Yeah. Nothing's cohesive. You look in there, you're like, "We shouldn't have shipped this."The moment you ship something, you're stuck supporting it forever. And by supporting, it means any future feature you build is going to like interact with it. So you still have to be very conservative with what you put out there.
6:04 It's hard to undo anything. Just cuz we can ship 10 times more doesn't mean we have 10 times as many good ideas to ship out there. So, uh, in a lot of ways, my struggle has now been how do I like slow everyone down? Um, and like understanding that yes, our process can look very different, but should it look very different? Like we, you know, we we've done uh in the past 6 months, we've kind of operated very differently than we ever have.
6:28 A lot of stuff went wrong because of that. So now we're pulling back and figuring out, okay, what from the old world still makes sense. So yeah, we're like figuring out what we should be doing. And I I definitely don't feel like, oh yeah, we're like killing all our competitors. We're using AI so much better than everyone else. Um, and by the way, none of our competitors are crushing us either. Like no one out there is using AI so well that they just like we can't even compete, right?
6:52 Um, and we're in the coding agent space. All our competitors are super into AI. So you would think in our space there would be like uh a huge gap, but there there just isn't. Yeah. So I want to rewind back to to the very
2. Dax’s path into tech
7:04 beginning of how you know before AI before a lot of these things. How did you get into tech and software engineering? >> Yeah. Uh so I uh I grew up I kind of cliche story I grew up programming as a kid. Uh my dad was a software engineer so a little bit easier for me to get into than for other people. Then just started working out of high school. Uh founded a company. Thought it was cool.
7:25 Thought I knew what I was doing. Looking back in hindsight like wow I didn't know what I was doing at all. Um that eventually got aqua hired as a small aqua hireer. Uh and I ended up in like the real tech industry. bounced around as a consultant, founded a few companies, uh, and then ended up doing open source pretty much the past six years full-time. >> But going back to the very beginning, I found or saw some references to you working on Minecraft, Minecraft servers.
7:52 >> Yeah. Yeah. >> Back in the beginning, can can you take us back a little bit? >> Yeah. So, uh, so Minecraft obviously everyone knows what Minecraft is. Um, and again, this is another cliche story. You talk to a bunch of people in tech, they have a similar similar backstory. There was a modding framework for uh Minecraft that came out. I ended up working on the framework itself. I ended up making a bunch of mods with it.
8:09 I found that I liked creating like interesting sandboxes. I never like play like I played the game a little bit, but I didn't play the game that much. I like had a server that like a 100 people would play on and I would just use these mods to create like interesting situations to try to like understand like how people would behave under certain scenarios. And I found that like fascinating. Um but yeah, that required a lot of like programming Java stuff.
8:31 What's interesting is that community obviously I was like very new to programming. Uh it was all done over IRC or the community existed on IRC but there were some like very senior very good programmers in there. The people there I felt like were people that weren't particularly career motivated. They were probably in a comfortable enough situation where they worked like two hours a day. Uh and they were talented but they just didn't have any like desire to like breer chase at all.
8:55 So they funneled it into the Minecraft stuff and I got to talk to them and learn from them. So uh I feel like in like the couple months I was doing that I learned I learned a lot.
3. Early startup experience
9:04 >> And then you you went to the startups you founded a startup and then after being the founder at uh Iron Bay I saw looking back your history you became a head of engineering at Wright Health. >> Yeah. >> Can you tell me a little bit about what was that like? That was in 2017 or so like pre-COVID. >> Yeah. Yeah.
9:22 So that was a company in the transportation and healthcare space. Uh it was just me and the co-founder originally. Um, and that that company grew to like 20 people or so. That was my second swing at doing a startup, I would say. And it got further than my previous attempts. Um, but all but like it kind of ended up in a disaster. Uh, I did end up meeting my wife there. She was a head of product.
9:44 I was a head of engineering. We got together after a year. So, better than a startup exit, I would say. Definitely learned a lot. But, uh, yeah, it was one of the situations where everyone was super young in their 20s. And I think there's this uh stereotype of startups that oh yeah, it's a bunch of like super young people, you know, building stuff. After that experience, if I ever end up investing in companies, I'm not going to invest in companies that with a bunch of young people cuz we were all just like our brains weren't fully developed.
10:08 We're all insecure about various things still and that like played out with like company politics and and dramatics and stuff. So, uh yeah, that cliche of like, oh yeah, just a bunch of young people. I think that's like the exception, I would say, [laughter] looking back. >> So, so like a bunch of young people succeeding is probably the exception. >> Yeah. Yeah. And of course we have like famous stories of that. Um but you know like on average I like for me I felt like my brain didn't finish developing until I was like 26 I think.
10:31 So prior to that you know I don't know if I really should have been uh running a startup. >> And when you say like stop developing is it just kind of like getting enough experience to like understand how like a business actually works or like professional relationships. What in what sense? Yeah, I think for me it's like startups are so intimate. Uh because it's just you and a few people and it's very intense like you are this is the thing you're doing like you're not really this is your hobby, it's your job, it's kind of everything.
10:56 If you're not like fully developed as a person, if you're just trying to prove something to the world, if you're still insecure about certain things, all of that shows up at work. Um especially when such an intimate situation like that. So fighting, conflict, all that stuff. uh the way I perceived the situation even my own understanding of what was going on just basic like how to be a person and live in the world. Uh I think at least for I think I think for guys like takes a while for their brain to fully settle and when it did it felt like day and night like I was a different person but uh it definitely took a bit and now you can look back at that time and just kind of be like oh gosh like what was I doing? What was I thinking?
11:34 >> Yeah. Everything was just so magnified and way more intense and way more emotional than it than it needed to be I think. Okay. So the people who knew the DAX back then might be a little bit surprised. >> Yeah. Yeah. I think so. But again, that's when my wife met me. So something something was right there. >> Did you in your first few years, so you you founded a startup, then you went you kept going at like very early stage startups either as a founder or an early founding engineer or so.
11:56 Did you ever consider larger companies at that time? >> Yeah, I think um that was always there because uh you know this so for me this era was like the early 2010s or mid2010s. Um the big tech companies were very prestigious at that point. Like there was a lot like everyone you met was trying to get a job at uh either one of the big top tech companies or one of the hot like unicorn startups at the time.
12:20 That was like the thing to try to do. If you weren't doing that, you basically were going to like fail in tech. So I felt like some kind of pull from that point of view. But I also just couldn't get my together to like do that. Like I knew what it what it takes to there's like a thing there's a set of things you have to do to to kind of be successful there. I just couldn't even do that.
12:38 So, uh, yeah, I could say like, oh, yeah, I chose not to do it, but really I I I just don't think I was >> What do you think the things were back then? >> I mean, you know, there was a very structured interview process for these things. Uh, you know, you have to do certain like programming problems, whatever. And I think I was a good programmer. And I think I'd done some interviews that were like that.
12:57 And I some of them I even did well in. But the level of competition and like people study for it, people focus on it, like just randomly swinging at it, I don't think I would have uh landed anything. So yeah, I I was into building stuff. I was into like p more practical things. Um and I just struggled to do anything
4. Getting involved with open source
13:16 outside of that. And then how did you transition into open source? Well, I serverless stack was big project of of yours. was it was a a toolkit for building a uh building full stack a applications I think. >> Yeah, that that was kind of where our initial focus was. Um yeah, and how we got into open source. So after ride health kind of ended up in in disaster, I took a job at a like a series B stage startup at that time for me was like the biggest company I'd ever worked at.
13:40 Uh and I eventually got put in like a in a director role. First time being like a full-time manager with no other like uh like no no like active programming tasks. Uh and I still wanted to program a lot. So I ended up exploring a bunch of open source things at the time. You know I had like three or four hours of manager meetings every day. But then outside of that uh you know I had time to explore open source things like that.
14:02 And I started to build my own kind of crappy stuff and I came across um SST which had just launched. It was a was like maybe like a couple months old. That was Frank and Jay. They both uh had created this thing originally started contributing to it. They were raising a series like a they were raising around. when they were kind of getting out of YC raising a round. I invested in the in that round and then a month later I ended up joining the team and they gave me the money back as salary but then now I had to pay taxes on it.
14:29 So it's a if you're going to invest in a company make sure you're not going to join them. It's a bad use of money. Yeah. >> And then you did SST and then you did some other stuff as well on the side, right? Open next. >> So Openext I think was probably a thing that blew us up initially. Um this wasn't even a thing that we wanted to build. we were uh survey serving people in the AWS space.
14:46 Every single day someone would come to us and be like we like what you guys are doing but we really need help deploying NexJS AWS and over and over like for a year people were just nagging us about this and we didn't want to do it cuz we weren't next.js s users very tedious. You actually has a very complex framework trying to recreate the right infrastructure for all that in AWS is a lot of work. Digging into like JavaScript bundling like NexJS internals like not very fun, not very exciting work. Uh so we made Frank do all of it.
15:15 So he basically slogged through through that and figured out how to uh get it all working AWS. Our goal from the beginning was this project shouldn't exist. It's just a weird gap because uh the NexJS team is focused more on Purcell and it wasn't like a malicious thing or anything. it's just where the attention would naturally go. Uh so we're like let's fill this gap. The end ideal state should be that you know Versella eventually just manages all this and there's no need for this.
15:38 So we built that. Uh it annoyed Verscell a bunch. Um uh but yeah it was very useful for the people that you know were trying to deploy on in other places. Eventually uh we kind of rallied some other providers that had problems with Nex.js as well. also cloudflare netifi I think Microsoft got in there eventually too Google got in there eventually uh and they kind of built stuff adapters for open next and eventually the nextjs team had time to kind of like okay let's make an official adapters API and and in the past like year or two it became a much more like collaborative thing uh and I think the need for open next is slowly going away and then how did open code
5. OpenCode
16:14 come about because that that's a pretty recent story it started sometime in summer of last year summer 2025 >> in less than a year yeah back in February very uh our company we were basically doing a push to hit to hit profitability. Um so with SST we had a monetization path for that basically for like 3 or 4 months we're like running out of money and then but then our revenue was going up and then in February we had like one month of money left but then we also broke even at the same at the same time.
16:41 Weirdly though we were all like really calm about it. It just felt like I know it felt like something would would work out and it and it did. Uh so that gave us time to kind of take a step back and think about okay we can technically do whatever we want now like what do we want to be doing and for a while we're like obviously AI is a thing to work on this decade especially if you're working in dev tools we've been through waves before where like there's just a thing that happens and whenever a thing that's happening it seems like it's not making a lot of sense because whenever
17:09 something that is has a lot of potential it attracts a lot of investment by its innate nature most that investment doesn't make sense so it's very easy to look at anything exciting that's happening and think none of that makes sense. I'm not going to participate in it. But usually what happens is a few things in there make a lot of sense. And if you just completely sit out, you just miss out on that. I think we've been through a few waves of kind of doing that.
17:31 Uh where we saw the AI thing and we're like, okay, a lot of this stuff is stupid, but there's definitely a real value here. We need to be doing something in it. Uh and we took a few swings at a few ideas and like a lot of them we didn't even fully launch. Uh cuz it did we just discovered they didn't make sense while we were working on it. And then eventually we started to use cloud code as a team.
17:48 It was the first AI coding tool that stuck for us. It like directly solved some of the the workflow annoyances that we had. Um this is great obviously uh this should exist. At some point I asked why weren't we the ones that built this? Like we should feel bad about that. And then we realized okay maybe there is like still an opportunity to do something given our experience in open source. Uh we kind of saw I think so we were saying earlier like you don't have to just ship a million products to figure out something that works.
18:15 If you sit and think you can figure something out and we kind of looked at it from a positioning point of view like there's a market there's a bunch of coding agents out there. For some reason no one has grabbed the open source territory. There was no coding agent that was like we are the open source option and that obviously is a super valuable territory. every single dev tool we use whether it's databases, compilers, whatever eventually the open source option becomes a default option, right?
18:40 That combined with the fact there's heavy heavy competition uh for models like sure claude was and was like popular but there's billions and billions and billions of dollars invested like they're not just going to let anthropic win there's going to be push from open AI there's going to be push from the open source side so given that we saw that chaos we saw that it's really valuable to have the open source positioning that tries to work with uh all the models so the initial push for us was to kind of ignore whatever was going in the market and just make sure that we claimed that open source spot which we were able to do and then yeah like our numbers have been pretty crazy since then.
19:13 >> Can you tell me about the the growth like you launched in June 2025 how the growth was both for usage but but also for the team like when you started how how big was even the team was was it most of the the existing smelly labs working on this or just a small >> Yeah. No, so we were just three people at the time. So it was just the co-founders. Yeah. And then um uh we hired uh one of my friends who was also interested in working as and he helped us build like the initial thing.
19:38 So he joined uh so that was four and then we convinced one of our uh like a really good designer that we had always wanted to work with to join us as well. Uh but that was after we launched. So that was more like in the fall. But yeah, so we we launched and the growth was really good like immediately. It was better than anything that we'd ever done. But by December we hit uh 650,000 monthly activives.
19:59 And at that point we're like wow this is great. We uh back in the fall we kind were kind of telling people our goal was to hit 1 million by uh next early next year. Everyone thought we were crazy. Like that was like they oh okay sure. Then in January we did 2.5 million monthly activives. Uh so like went from 650 to 2.5. Uh last month we're at 6.5 I think this month. We're still halfway into the month so I'm not sure. Maybe close to eight.
20:23 Our next goal milestone was 10. There was a massive jump. So we went to 650 in December and 2.5 in January. What was that jump? Is is that the the winter break jump where everyone started to realize that these models are really great? >> Yeah. So, having been at DevTools for a while, we knew that in January there's always a bump cuz like I think people take time to learn new things in December with the time off and they have time to try new stuff.
20:47 So, we what we typically see is we see a dip into the holidays and like a giant spike in the first week back. For this, we saw growth into the holidays which we've never seen with any other product before. So like despite the fact that people were off, it was higher usage than ever. And then January came around and Anthropic helped us helped us a lot by uh you know they they like wanted to ban anthropic subscriptions in open code.
21:08 Uh that blew up into like a huge thing like we barely even commented on that but like just the user base was so upset. Anthropic accidentally put us and them in like the same sentence which we don't deserve cuz they're a much you know bigger more successful company. But that week that kind of happened by accident and that like spiked our numbers like crazy. >> So So I guess in in hindsight cuz what happened is Entrophic silently banned
21:34 being able to use cloth code subscriptions inside of Open Code which which was every tool including Open Code did that cuz it was a bunch of other third parties but they didn't allow Open Code to do this and then this led to this like outrage. >> The thing with them is I think that they're kind of new to working with developers. Um, it's okay to do things like like of course you need to do what you need to do to make your business sustainable. It's totally fine.
21:57 But randomly dropping a block at at like 9:00 p.m. at night, that just sets you up for like people to hate you. Uh, doing like a phase communicated roll out over a month, I think they would have >> giving a heads up. >> Yeah. Yeah. Yeah. I think people would have someone upset. Of course, everyone's going to be upset no matter what, but it wouldn't have been this concentrated moment of like everyone being being really uh really annoyed.
22:19 This reminds me what we were talking about how AI allows you to do things really quickly and fast. Do you think in this case An entropic might be you know stepping in this trap of of they can do things really fast and they do things really fast but for example in this case they can just implement a block like this you know like it it the PR probably took like what like a few seconds or a few minutes whoever did that might have not thought through the implications I think it's just a consequence of any kind of fast growing company uh you forget the amount of leverage you now suddenly have like you do one small action and it ripples through millions of people like we're dealing with this ourselves like we've never worked at this scale before.
22:54 We put out a bug the other day where um almost everyone has a terminal in dark mode and we open code it opened up in light mode. So we like flashbanged a bunch of people and I'm like in the past that would have been like a 100 people we hit but like I did this like a million people this week. So uh yeah but but in inside this block obviously we know it worked out well in in hindsight but when it happened I mean at the time Opus 4.5 or 4.6 six was the
6. Anthropic banning OpenCode
23:20 most powerful model out there best for coding and you saw that entropic just blocked you know like clos before you knew that this press would happen like was the scene's reaction was it just like stay calm keep going yeah what's weird is we knew this day would happen at some point and for some reason when it happened we all just felt excited because I think we were kind of like thinking about this for a while and we knew this would happen we also knew that like we live in this crazy bubble like especially on Twitter where everyone has a a $200 Cloud Max subscription.
23:48 At that point, we were at 650,000 uh monthly activives. There's no way 650,000 of them have Cloud Max subscriptions. Like, it's crazy for the average person to spend $200 a month on anything. So, we knew it's it was like a smaller subset. Um,
24:05 >> and also at the time, we had been working on deals with pretty much every other company to officially support their their subscription in Open Code. So the previous weeks leading up to that, we got Microsoft agree for uh GitHub copod to be officially blessed by Open Code. We got a bunch of different companies in the works. We had announced any of them yet. And the big one we hadn't gotten or we haven't even approached was OpenAI.
24:25 So when this happened that night, forget what it was Thursday night. I don't remember exactly when. I got like a hundred tags on on X being like, "Oh, they they banned it. They banned it."And I was like, "All right, it's go time."So, I messaged OpenAI being like, "Hey, tomorrow, uh, everyone's going to wake up. Everyone's going to be really angry at Anthropic. You guys have a chance to score like a PR win by taking the opposite stance and officially supporting Open Code."
24:52 The next morning, they confirmed like, "Yeah, let's do it."So, in the morning, everybody was like, "Oh, Anthropic blocked Open Code. They're screwed."I saw a bunch of people being like, "They're worth nothing now. Like, they're they're going to go to zero, whatever."I was like laughing to myself. I'm like, "Okay, just wait till the end of the day."And then we figured out the integration, we implemented it and the end of the day we announced like open AI is officially supported in open code.
25:14 We knew what was going to happen and like I going all the way back to the open next thing, right? Uh the strategy that we know how to play really well is to pick one temporary bad guy and then galvanize all their competitors to push something forward against them. Um so Anthropic was unfortunately in that position. Uh so we kind of got the rest of the industry to you know support open code support like access to these models in different places because they were all competing with with Enthropic.
25:38 So these are like nice strategies that you can run in these situations even as a small company. I'm starting to get a sense that that past 10ish years of building dev tools or like at least like five of open source and understanding dynamics is really helping you because even even when you told me about how you were thinking of open code you're talking about strategy about how there was this gap and there's all these competing model providers and with an open alternative over time in a lot of ecosystems the open one wins and the vendors compete for example with Linux you know Linux is open source but the distributions are are for-profit companies Red Hat had Ubuntu or Canonicle and so on and they all compete and and they make it better.
26:17 So even in this case it sounds like you you know like it all goes back to you actually had a strategy that you expected that if the players play the vendors play as they play it will make sense. >> Yeah, exactly. If you get your positioning right, the world just keeps handing you wins that you didn't even expect. So like we never predicted this exact scenario but like our fundamental understanding of the position was right. like if if there is a neutral party, all these companies with billions of dollars will kind of use a neutral party to advance their own like company's interests.
26:46 So, it's beneficial to be that thing in the middle. >> Yeah. And then right now, COEX came forward. They saw it as a way to increase brand awareness, usage, et how much is growing. And I'm sure logically at some point they might turn around at some point say let's say they win the market or they become market leaders, they might do the same saying, "Okay, we no longer want to support this thing."But at that point there might be other uh players as as long as there's multiple uh interested parties.
27:12 >> Yeah, exactly. So at some point maybe open AI becomes a bad guy that we have to like kind of galvanize everyone around. So it's it's uh I mean it's why competition is good. This is kind of exactly how competition plays out. I think the thing that people maybe underestimate is like we're a small company. We're not like a huge company at all. You can apply if you apply pressure in the right places, you can actually make things happen.
27:30 We get a lot of criticism and and like anger from people being like, "Oh, you guys are being so mean to Anthropic."They criticize like the way we approach things, but these are billion-dollar, you know, huge companies, you know, like us being able to apply any amount of pressure to get something to happen. It's very difficult. And this is what it looks like. People might think that it's, you know, they're above it or whatever, but uh having more access to these things, having more people be able to use the tools they want is a good thing that you can love cloud code, be like, I'm never switching off cloud code.
27:58 That's great. you should probably still be into the fact that people can use other other tools that they like, right? And going going back to why open code is so successful and that there was a gap using what you've learned about dev tools in general, like why was there a gap?
28:13 What do you think was a difference that you did outside of just you know like writing the writing the tool to start with? The the biggest advantage to in DevTools is the fact that everyone working at DevTools is a programmer and programmers are horrible at B2C products. They don't realize DevTools are B2C products. You basically treat >> B2C as a business of consumer. >> Yeah. Exactly. So like you treat them like the most extreme mindset to have is like you treat them as though you're launching Instagram or social media app, something like that. Yeah.
28:41 Yeah, you can do a top down process and there's plenty of companies that do like an intense top- down enterprise process and that works and that's great, but the dev tool products that are like massively adopted to the point where they're basically a standard, they're all bottom up. Like they're individual developers start to use them, start to like them and they kind of creep into companies and they grow in that direction. And to do bottom up, you have to basically think like a consumer company.
29:05 Um, and programmers generally are very very bad at thinking this way. So we very much focused on the moment you open open code it should feel very different uh and better than some of the other options. And to do that we had to build like a groundup uh terminal rendering framework. That's not what cloud code did. That's not what any of these other coding terminal coding agents did. They just used ink or whatever and you know they made it work for they need.
29:28 But we invested on it upfront because from the moment you use it it feels like something different. It might not be for you like maybe you don't like the overwhelming experience. maybe it feels like too much, but you still walk away thinking the people that did this are competent probably. Um, so immediately getting people a good feeling and then immediately getting them prompting without any layers of friction. So we focus on just reducing that friction as much as possible and focusing on things like I'm on a lockdown enterprise laptop.
29:55 How do I can I use open code? Like optimizing for all of those things. And our harness wasn't very good for like the first like five months of open code. But it was good enough. It was good enough that most people couldn't really tell a difference. And once we won enough share, then we went back and like tried to make our harness like good and smart and optimize and all those things. But uh it was inverted from what everybody else was doing.
30:17 Everybody else was being like you have to build the smartest harness and that's how you win. We did. We have like a mid-level harness, but we are the most used. So uh and now we're able to like you know creep up and actually have the best harness and are also the most used. So I think it was like an inverted strategy that we did that uh other people didn't fully
7. From terminal to GUI
30:34 understand >> and to get into the inverse strategies the technical level like you you you launched with a framework called Tari right? >> Oh that was for a desktop app. So the desktop I would say I wouldn't even say that was that was mostly a mistake on our part. So I love terminal stuff. I do all my work on the terminal. So our numbers are said we're going to hit like 8 million monthly active users. I don't think 8 million people should be using the terminal.
30:56 I think it's a little over uh we have like too many users for what the product is. I think a lot of them would probably have a better experience on uh on on a guey and we understood that very early and so we were kind of experimenting with like a web app with a desktop app and uh so we're like this is probably going to be the direction things go. Unfortunately, we were right like that that is like where things are going, but we didn't like treat that project too like we should have treated it a lot more seriously and try to get it like uh out there way faster and thought a little bit harder on on the technical stuff.
31:25 So yeah, we just kind of picked stuff and we didn't like think too hard about it and uh it ultimately was a mistake and we're moving back to Electron now. But open code is is growing amazingly fast. Interesting enough, there's this growth hack that some harnesses are doing. I would say growth hack where in the PR on GitHub, they actually put which harness did it. Cloth code is is doing it. GitHub copilot is doing it. Some others are not doing it.
31:48 And in open code, you are not doing it even though this could be like almost like free marketing. Yeah. So, initially we had that cuz initially we're effectively a cloud code clone. If cloud code did it, we did it. So we had that like with the commit it would say you know committed with open code whatever in GitHub and then we got a bunch of people being like hey can I disable can I have an option to disable this and I thought about it and I was like this is so l it just felt lame to me.
32:12 I'm like you can be like a casino right casino just tries to trap you in there with every little trick trick to like get you to stay. Um that's like the extreme of doing a consumer product. I felt like we didn't have to go to that extreme. It felt like a little bit lame to like try to it's like too obvious of a of a growth hack, right? like everyone sees it, everyone knows why that's there. Yeah.
32:30 So, I just wasn't a big fan and so instead of having the option, we
8. OpenCode’s business model
32:34 just turned it off by by default. >> You know, you're still running a a company that is a for-profit company in the end or or you need some you need to make bankroll. What is the business model behind open code? >> So, uh we have two lines of business basically. Uh so, initially when we first launched open code, a big problem that people had was or that we had again thinking about reducing friction, they had to connect something.
32:54 They had to connect their anthropic account. They had to connect their OpenAI account at that time. When you sign up for Anthropic, you couldn't even get enough rate limits to even use something like open code. So, a lot of our users couldn't even use it. So, we're like, okay, we have to at least build some kind of inference service that like you can sign up for and get access to all the models with the rate limits you need.
33:14 Uh, so we built that and we called it open code Zen. And we initially just built it as like an onboarding thing to smooth out onboarding, but that grew like a ton. uh and with the amount of open source models are becoming popular. We also found there's a ton of difficulty in hosting open source models correctly. Uh so Zen has become a place to aggregate the best model. I mean of course frontier models are easy but then the best inference for all the open source models.
33:37 All that became really popular. Um that business is growing a ton. I think a couple months ago we announced like that hit 50 million uh run rate uh within like five or six months. >> Wow. Um, and the margins there can be pretty good because open source models you can host at a decent margin. That is growing like crazy. Uh, we didn't really expect that, but that that's like a big part of it. The other side of it is extremely boring.
34:00 If you are a company that's using Open Code and you have a thousand engineers, you can't just tell them all to go download Open Code and like add an open API key. You need some kind of control plane to like set up all the providers, permissions, budget controls, rate limits. So, we have a product there. Uh we're going to make that publicly available soon, but right now it's just been like enterprise deployed. Uh so just if you're a company that's using open code at scale, you need some administrative software to to run it.
34:25 You can't practically use open code at scale without something like that. That's also open source, but you know, most people just pay for our hosted version. Uh the other thing is I think uh it's finally the time has finally come where people are looking at how much they're spending on uh on LM and they're like, what are we doing?
34:42 Are we actually getting anything anymore done? like we so like companies are now looking at their cost and trying to figure out how to optimize it a little little bit. It's great timing because open source models are now very competitive. Uh they are 10x cheaper blending that in and having good inference for open source models is becoming a part of our business as well. So these big companies you know they need the control plane but then kind we kind of just give them inference access as well to the these other models and they end up just kind of naturally starting to use it.
35:09 If that ends up being a main part of our business, we might stop charging for uh the control plane itself and just charge for the inference. >> Dax was just talking about the boring but essential work to get enterprises on boarded. SSO, permissions, control planes, all the stuff every serious company eventually needs, which is where I need to mention our season sponsor, Work OS. Sooner rather than later, you'll need to get around building these enterprise features.
35:32 Not just control planes, but things like O for apps and agents. Work OS handles it. SSO, SKIM, fine- grained authorization built for how agents actually operate. The fastest growing AI companies, Entropic, OpenAI, Cursor, Perplexity. They already trust Work to solve these problems. Check it out at workwest.com.
35:52 I'd also like to talk about our presenting sponsor, and this is we just talked about slowing down to speed up, thinking hard about what to build so you're not sprinting to the wrong destination. But quality is part of the destination, too. You don't want your product to flashbang a million people like the team at Open Code did that one time. Antithesis is a property based testing platform that enables you to express the properties your system should have then verify that those properties will hold in the chaos of production.
36:20 With antithesis specification and thorough verification becomes a seamless workflow, giving you clarity so you can deliver quality. Check out antithesis.com/pragmatic to learn more. And with this, let's get back to DAX and open code. We had a
9. Why inference is profitable
36:35 recent tweet about how inference is actually really really profitable like you were quoting someone who was saying like oh you know like these these AI model providers are are you know like having might be having financial difficulties. Can you explain to those of us software engineers who you know we don't we don't do inference I mean we use these models and we we just assume that this this must be our our business. How can it be profitable?
36:57 Why is it profitable? What are you seeing? >> Yeah. So I think this is uh it's kind of there are different parts of a business. So if you look at the pure inference part of a business if you think about what's the floor on the cost the floor is the cost of electricity. Um there's a capital cost to acquire the hardware. Once you have it to deliver a token the cheapest it can get is the electricity to power it.
37:18 And obviously there's other infrastructure there's like operations staff. There's stuff like that. Um, but we have seen models that we look at the sticker price of it and we know like the uh uh cuz because we rent GPUs at scale to run the models and we still use middleman by the way. So we're not like going all the way down to the down to the floor. Even for us there are some models the sticker price and the cost to us there's like an 80% margin in there.
37:44 And I think the other thing that people don't notice is prices have gone up. It's confusing because it seems like they haven't. But they've gone up from the point of view as we used to all use sonnet as our default because opus was too expensive. Then they made opus cheaper so that we started to use opus as our default but it was still way more expensive than sonnet. So the prices have gone up and the cost to host these models haven't changed.
38:04 Um so that's one aspect of it being really profitable. And anthropic of course they have and openai crazy scale. They have the biggest GPU deals that they've done. Um, so I wouldn't be surprised if they're looking at like 90% margin at current prices. I don't think that's like a defensible margin long term. That's crazy to be able to make that much with this amount of money going through as well. It's interesting cuz when Brian Canrell was on the podcast, he used to work at building a cloud service that would compete with AWS and he said that back then this was the same thing.
38:34 AWS back then hid their financials. Everyone thought and they told everyone that cloud is a terrible business and it's like you red blood everywhere. And then he started to do it and he said like actually it's a really freaking profitable business to run a cloud but it's kind of a welcome secret because why would Amazon or any other provider advertise the business that it's it's printing money. >> There's always negative sentiment that exists for any business that's getting hyped.
38:58 They have no incentive to correct it. Um so again it's complicated because I know the training costs are a big part of it. Uh the R&D department is is hugely expensive but long-term inference makes sense as a business and I think it
10. GPU bottlenecks
39:11 it always will. Yeah. >> This being said, you also said something in in public about GPUs about you you I I'm quoting you. There are just enough GPUs. It's crazy that even a company our size is being bottlenecked by us. >> What does that mean? >> Yeah. So, across the whole stack of GPUs, so everything from like producing the GPU to supporting hardware to like labor, everything everything is like super tight right now. The demand for inference is growing.
39:35 So, like I don't think it's linearly growing. I think it might even be exponentially growing. But we haven't made our production of GPUs grow exponentially. That's like kind of a linear process. So as those lines intersect, there's going to be uh tightening. So for us like there's we have G GPUs that we need to reserve. We have to pay a lot up front. Um everyone is now hoarding because everyone's kind of expecting this crunch to kind of continue.
40:01 It's very hard to get capacity for inference. And uh the other thing that's crazy I think I posted about this you know we see things like oh a company has raised $2 billion or whatever to do something in AI and that feels like a crazy amount like wow that's that's a huge amount like you have to be like a crazy startup to do that the big tech companies are spending like tens of billions in a year like Amazon Meta whatever like they dwarf anything that's happening in the startup space so they are just vacuuming up like all the demand any company that is in the supply chain they don't want to talk to you because they're busy trying to get something with Amazon or Microsoft or or Google. So, yeah, it's very tight times.
40:39 I I think it'll get resolved. I think any my whole career, anytime I've seen any kind of shortage, there was a tense period and it was met with like crazy over supply. It might be different this time, but generally that's how how I see things go. But right now, it's tight. I I want to talk about the the hype of
11. AI hype
40:57 what productivity gains uh these you know AI tools spec specifically AI agents are giving to engineering teams and and the reality and and you wrote a now very heavily quoted tweet which which was I'll quote just some parts of it. Everyone's talking about their teams like they were at peak of efficiency and bottleneck by the ability to produce code but the way things actually look like is and you listed a few things like your team your your or has good ideas.
41:21 People are now using AI to be 10x more productive. They're using to turn out their tasks with less energy to spend and so on. So like this was a few months ago I think two or three months ago when you wrote it. >> Yeah. I think there there's so many dimensions to this. So the thing I was talking about in that post is the majority again we forget how big the software engineering industry is. Every company in the world employs software engineers to some degree, right?
41:40 Um, the majority of these environments aren't like the most motivating, exciting environments. Most people there are trying to do their job, go home to their kids, like have a have a a reasonable life. You give them a button that lets them do their work faster. The natural place for them to do is hit that button as much as possible, do the same amount of work, and just cash in that extra time, right? Which makes total sense.
42:05 It's like if you're not if you have no reason to be above and beyond motivated, you're not going to really use that to like, you know, push your organization harder. Yeah, these tools maybe make you more productive, but like be really realistic about your employees. Like where are they going to like cash in cash in those gains? Obviously, some companies are not like that. They're the employees are motivated. They have good reason to be. They're compensated in a way that that makes sense.
42:25 But most places aren't like that. Uh, and the problem with that is usually in those environments, it's like there will be a couple people that are irrationally motivated because, you know, they love the work they do, etc. Even though the rest of the company isn't as motivated,
42:41 they're usually the ones that are trying to make sure everything is good quality, make kind of push everyone to try harder. They're all now overwhelmed by like slot PRs. And we we've had a few people on our team that have joined and their previous company was like this, like they were the person that still cared. the rest of the organization just like hits the button and gets their task done and they're drowning in just garbage and they're getting burnt out and they're leaving.
43:03 So motivation and team and people and humans and like emotions all that stuff is still a big factor in in all this. How do you think companies like let's say a m midsize company or even a small company might have to rethink kind of motivation
43:20 compensation thinking about work now that you know like I was Steve was talking with Steve Yagi about this on how an engineer could if they're super motivated and they put in the task and energy they can produce a lot more output and if it's well directed that could be better business results but it does come at a a huge cost in energy And again, if you're if you're just being paid by the the same paycheck, it doesn't necessarily make as much sense to do so.
43:47 So, I'm I'm I'm wondering like uh what what kind of early thoughts you have so far. And of course, for you guys in a startup, I guess it might be a bit easier. I mean, obviously for us, you're right, it's easier for us. Um we are in a very exciting space. The people that join our company are very competitive. Uh they want to get in there and they want to win. So, that's like a big driver. everyone has equity that if we do our jobs right like it'll be pretty meaningful for them uh at some point I I even preai I feel like uh again I can only speak for startups as like that's where my experience is.
44:16 I'd always see startups post jobs where they're like we're hiring two engineers and they post two salaries and these are like okay salaries. I always thought like why just hire one person and combine the salary you'll get someone that'll like meaningfully change the direction of your whole life. Like people will start showing up at that at that level. Um, so we've always been willing to pay pay quite a lot. We don't need to hire a thousand people.
44:39 We need to hire like 20 good people. Um, so generally I think good salaries still go a long way. But yeah, at bigger scales like I think it's just hard like when when your company hits a certain size like there is just no good reason for someone to do much more than what their job strictly ask them ask them for. So I don't have any good ideas here. And I I wonder if it's a a thing where it is hard to retrofit
45:01 this this technology and and the way of working to existing structures which have been and I guess the question goes back to like how how much will like the AI native startup like yours or or ones that are starting today change like how will their workflows change the type of work even the roles right like what is a software engineer even do in terms of okay of course they prompt AI to write code but what about product what about all these other things.
45:23 >> Yeah. Yeah. I mean yeah I think the bottlenecks are still there. you're still figuring out what you should be doing. You can spend a year just figuring out the right thing to do. And then once you figure it out, maybe it's fast to actually build it. But yeah, like I I think the the joke I made was pre AI, I would spend 95% of my energy thinking about what to do and 5% of my energy doing it.
45:42 Now I spend 96% of my time thinking about what to do and 4% of my time actually doing it. So yeah, it's like a 20% improvement, but dayto-day it
12. AI spending
45:51 feels as hard as ever. Another observation you made is at a lot of companies and you will I guess see this secondhand from from open code being being used at companies that the CFO is now going what do you mean each engineer costs extra $2,000 per month. What are things you're hearing about in that area cuz this is happening. >> Yeah. So the with I think with every technology there's a phase of like flexing where there's so many uh companies now that want to be seen as like we're so future facing we're like
46:21 our process is ahead of everyone else's like you have no chance you're going to catch up and they're all bragging about how much they're spending. So there's like right now there's a push to be like each engineer is spending like 10,000 a month and that's like that's so worth it. like our business is so successful and and so useful and so efficient that any amount of money is worth it and and there's a lot of that narrative.
46:40 Then there's like and that that's fake that'll go away. Uh then there's a real narrative of like yeah these companies hire thousands of engineers if they literally cost $1,000 extra a month that like breaks your whole budget. Like that's not a a thing you can kind of casually do. We're in a temporary period of like we're experimenting to see what's possible and and and everyone's learning. I doubt this is going to be a sustainable thing. Like these companies were already pretty tight on what they could afford, especially if they can't directly point to clear results of here's the issue, right?
47:11 The net result of this, I'm not saying this is the case, but there is a world where the net result of all these AI coding tools is the same amount of work gets done, but all the engineers are happier because their job is easier. That's not good enough for a lot of companies. So, they're just going to say go back to typing out the code. It's also an interesting dynamic where there's also the pressure of well when everyone else is doing it e even if if we just stick with the happier analogy and again let's let's assume that the the quality of the output overall wouldn't change if everyone else is doing it and you're like okay well it's not worth it let's stop it then your best engineers will leave so I I'm also hearing some uh CTO
47:47 saying like well we're giving access to better better tools because we're one of the best companies like it would look silly if we said like oh you can only use I don't know GitHub copilot anymore we're not allowing you to get whatever open code or off code or whatever else that is cuz we like our best people would leave. >> Yeah. No, that that is a real thing. It's kind of like uh I mean again depends on if if you have someone that's really good that has infinite opportunities using Jura is a risk because they're going to be like I hate using Jura every day and they're going to leave.
48:12 And I know people that have literally have done that. So that that's like always a always a dynamic. So >> but but that will be at the top of the market right. Yeah. So it's again I think at the scale we're at we're just so exposed to like how big the world truly is and the world we typically play in it's so small compared to everything else that that exists and at most these companies it is just use copilot just plug copil into open code and that's all you get and like your limits your limit and then and that's what's there um and there's some narrative being pushed that these companies are going to die because
48:45 they're going to fall behind etc but uh
13. Dax’s memo
48:47 I don't know I just don't think it's that straightforward Another longer uh post that uh that I I paid a lot of attention to is the one that you sent out to your team to the open code team which was on on the topic of saying all right we should do three changes I'll quote you basically we have the following challenges none of them are new but I think they're turbocharged by LMS number one is shipping features not worth shipping number two when iterating on features sometimes the original design design is off and it forces you something hacky but the LM cannot not deal with the hacking.
49:19 And number three is we need to spend more time cleaning things up. How did you get to these observations and what's changed since you and how how did the team respond? So the first thing right features that we shouldn't have shipped so easy just to respond to a problem by shipping a feature. So having more restraint uh and like so we we try to like flesh that out a little bit more like here's the type of stuff that we want to ship.
49:40 Here's the type of stuff that like we'll wait on um until we have more clarity. There's having more restraint there. The thing about shipping hacky stuff, that one is I think the probably the biggest challenge because forever this has been a problem where you have a system that's doing a bunch of stuff. You need to add a feature to it. The system doesn't exactly support the feature. So your options are rethink the system from first principles, redesign it so it supports that feature or just absorb the hack for temporarily.
50:09 And you can make a judgment call on which one you do, depending on how bad the hack is, depending on how valuable to the company uh it is to get this feature out. You make the judgment call. That judgment, that ability to have that judgment is so distorted right now because the agent will just do the hacky thing for you. The agent will kind of deal with the hacky problems that come down the road. And it's way easier just to be like, "Oh yeah, it's a temporary fix."
50:34 So we're shipping way more hacks in places where we should have just rethought the whole system from ground up or like redesigned it to to and like refactor it to make it more flexible. So I think our judgment is just off. Does this have to do that when I as an engineer, you know, preAI like I'm making a hack, I know I'm making a hack, I'm thinking about it, I feel bad about it, I I feel bad.
50:56 >> Yeah, exactly. >> But I do it anyway. But you know, I I spend time thinking about it and there's kind of like a little bit of prickle there. And then when I do a second hack, I remember the first one and I I feel even worse about my and I can still justify, right? after a while like like there's feelings that especially
51:12 when you're someone who cares and the reason you care is you have an experience you've been burnt you know you're you're you're placing landmines for someone else maybe even for yourself and is is it just that the agents a I mean they just do it they don't have feelings and they also surprise the effort suppress the thinking they they don't even tell you I'm doing hack doesn't even know it's doing a hack it's just following whatever the training data is which is pretty lowquality code on the internet right >> yeah Exactly.
51:37 I I think way is exactly right. That prickle that feeling that you get, it's like muted now cuz someone else it's kind of like you've made someone else deal with the problem. The problem is still there and the the landmines are still going to blow up on you eventually, but like you're not you don't feel that bad feeling as much anymore. So your judgment is skewed. You're not getting that feedback loop. I I guess it's like, you know, like there's always this like very relatable
51:57 story of the CEO who just delegates stuff and then like doesn't understand why things are terrible on the the the floor and then like one day goes down and like you know gets into like doing the actual work and realize oh my gosh these conditions are are terrible. >> Exactly. versus the CEOs who were hands-on and they tried to stay in touch and do I don't know simple stuff like or CTO's doing coding in the environment like I think stripe CTO did this like once for a week every few months and then felt like oh this is painful let me do that
52:24 >> yeah exactly like you need to I mean just like you need to be using your own product you need to be also like you you need to feel the pain that the users are feeling same thing with your code base same thing everywhere so yeah I think all of life is about having the proper feedback loops in place and it's very easy for those to go away and then the third thing that you said in in this memo was related to this one is we need to spend more time cleaning things up. How do you deal with that?
52:46 And I mean because you're also a founder, how do you justify it? Because you know there's this thing of like especially when you're a startup, okay, you've just found product market fit, but there is this pressure to move move quickly and cleaning things up. It will not get you more customer love or revenue or any of the stuff that you care about as a business. Yeah, it's really hard because every single day we wake up, there is a thousand people yelling at us, telling us to do XYZ things.
53:10 There's a thousand people telling us we're doing everything wrong. Every single day, uh there is like a competitive new product that shows up. Uh very overstimulating. If we let ourselves just get pulled by those forces, I don't think it results in anything good. And I think what's also cool is cleaning stuff up is easier than ever. Like you think of a new way. In the past, I would realize, oh, there's like a new pattern that we should be using and we would just start to use that stuff for stuff going forward, but it was too much work to clean up all the old stuff.
53:40 But now, you can clean up all the old stuff. It's like you can ask the agent to go implement the new pattern everywhere. It's very easy to clean up tech debt. It's very easy to like find new patterns and implement them across a codebase. Very easy to clean up like dead old patterns. And yeah, you're right that there's no like direct uh result of of doing that. I think you can be a successful company without ever doing that.
54:01 The way I think about it is there's a million ways to be a successful company. There's all these different companies that are successful out there. If you had your pick of any company you could work for, you probably wouldn't pick 99% of them. So, I want to make sure we build a place that we're happy to work at 5 years from now. Our day-to-day is hap we feel good. We feel good working there every single day.
54:20 It's not this thing where it becomes miserable to work there. We can't get anyone good to join us cuz it's mostly about slogging through like legacy stuff. And in in this memo after you listed all of these things and you know you're basically saying all right we're we're shipping a bunch of stuff that we we don't need. We're not cleaning it up. We're not thinking you actually said something really interesting. The and I'm quoting you again.
54:39 The worst part about all of this is I don't think we're trading this off to move faster. I think we're moving at a normal pace. >> Right. Yeah. Yeah. It feels like we're going fast, but then I look back and I'm like like I don't know if we actually are going that fast. And I don't think we're going any slower than our competitors. We're certainly not going any faster than them. So if you're trying to look at productivity, it's so easy to trick yourself into thinking you're being more productive.
55:01 And when you sit down and really look at it, often times like it's not as crazy as you you expect. I guess what you're saying is, you know, don't be complacent and accept but but like just be critical and look at is this working? Like should we should we slow down to speed up? Should we focus on the invisible stuff? Those kind of things. I I really believe in just like preparing a lot and like setting the foundations, right?
55:22 And then then when you spring, you spring with like so much more force than you would if you just forced it earlier on. One thing I like about you is you you do call out BS when it it's a BS especially when it's really trending on social media. Again, you're you're a lot on X. This happens a lot specifically. And here's a tweet
14. Dax’s skepticism of predictions
55:41 that I'll I'll read to you that you you'll remember. It went very viral. Uh so many people, you know, VC folks all said like, "Yeah, this is the future."And this is what it said. The 24 to 29 year old engineer will soon become the most valuable asset in technology pre because they have preai principles and post AI speed and it's an undefeated combo and people are saying like yeah this is the future like this generation
56:04 who is not too old to have the old things they they will be killing it again they have no preconceptions of what used to be possible and you did call BS honest can you can you talk tell me like you're thinking >> well it's it's funny cuz like I'm just so tired every single Every single day I wake up and I open the feed and just prediction after prediction. The future's going to be like this. If you're just going to be like that, if you're just going to be that, everyone's just like making stuff up, right?
56:27 That one's funny because that that's a very classic post where it's like person like me has all the advantages. Person like not like me has all the disadvantages. It's like everyone is just saying mantras to themselves cuz the root thing that's going on here is we are experiencing a moment of great change. Everyone is very nervous about what that means for their own position in it. a defense mechanism is to confidently assert a future in which you're a winner.
56:51 And that's almost what every single prediction that you see is happening. You almost always trace it down to companies like mine will be successful, other companies will fail. My job won't be replaced by AI, but everyone else's job will be replaced by AI. And everyone has some like rationalizations for this, but the root thing that's happening here is everyone is scared and worried and not sure about where things are going. And we are just bombarded with predictions and protecting their own psyche. Um, yeah.
57:16 I'm just tired of predictions. Like, yes, we're going to have time of great change. I just focus on like the next day. Like, what can we do today? What can we do tomorrow? I didn't know I was going to be working on this a year ago. I don't know what I'm going to be working on a year from now. I'm just trying to do the thing that makes sense right away. Uh, this thing about like, oh, young people have that that's that's like always been a thing.
57:34 Young people have a lot of advantages. They have the classic disadvantage of not having a lot of experience, but having a lot of energy. Uh, I have a lot of experience, but not as much energy as a 20-year-old. So, it's just the same thing that's always been like, you know, it's And it's funny cuz he like that one's particularly funny cuz he said 24 to 29. Why not like 18 to 25? You know, it's just so it's clearly he falls in that age range, which is why he's saying that.
57:58 It's just like Yeah, just it just made up. And I think everyone's just like nervous and worried. >> I I think it's good to just be honest about it because it's true. Like I I mean I I'm nervous and worried as well just because it's >> the change is faster than before. And this is talking with like the great of the industry who have lived through the Ken Beck, Martin Fowler, Grady Buch, and they're all saying that they have seen change like this.
58:17 Like for example, when they went from mainframes to to microprocessors, but it was throughout more like a decade, not a matter of a year or so, or maybe we're now at this point two or three years. And they're they're all saying the same thing that the change is faster, but but yeah, like as as you say, like it's it's very easy to to rewrite history and say like it was always obvious, but it's just hard to tell.
58:38 >> No, it's not. Yeah, it's so unobvious. Everything that ends up happening is always counterintuitive. there. There's always people that like see it correctly and like line themselves up properly for it, but none of the obvious things ever happen. It's like it just the end say we're going to end up at it's going to be so weird from our point of view now. It's going to make total sense in hindsight. So yeah, predicting is a lot
15. Engineering culture at OpenCode
58:59 harder than people think it is. So far with with open code, especially with open code, you and the team have reached really good success. What are the things that comes to building products and your engineuring principles that have not really changed from from the early days or or the ones that you've learned and you've stuck to them and it it helped make Open Code successful as well? Yeah, I think for us on the product side, like I said, it's very simple.
59:23 You probably only have one good idea in your whole product. Get the user to experience that as fast as possible. Well, it sounds so easy, but if you go try every single product out there, you will see a million accidental steps they introduced from the user hearing about your product to like seeing the value in it. Very hard to keep that minimal. Very hard to like not let that creep back in. It's like a constant thing.
59:46 So, we do this I do this thing where um like I have a command that like runs up a new Docker Docker container and runs open code which lets me experience like the first time experience. I do that like once every two weeks and I'm always catching stuff that we've messed up in that process by accident. The job of product isn't to just receive a problem and ship the immediate solution. It's to absorb all the problems and understand that there's one solution you can ship to fix 50 different problems. Right?
1:00:11 That is hard. That is difficult. That takes experience. That takes thinking. That takes talking to users. That takes talking to your team. That takes understanding your codebase. A product is a way to abstract a solution for like many different issues, right? That's always going to be hard and that is a skill that you can infinitely get get better at. Um I used to be horrible at it. I'm okay at it now. I probably got another few decades of getting better at it.
1:00:35 Yeah, that that's what I'm focused on like how to build stuff that solve problems well and AI has not helped me even a little bit. What has helped you there? what what has helped you to get this like product sense better or or like you know figuring out cuz it it sounds like we we talked a lot about thinking about reflecting about having one elegant solution that can solve multiple seemingly or unrelated problems. I mean, it's just uh it's years of experience in in situations of right feedback loop, right?
1:01:01 When I mess something up, I get a literal human yelling at me and like saying horrible things about me. When I design something poorly, I have to slog through the codebase and like do something that should have been easy that's a lot harder now. Yeah. So, for us, it's all about making sure everyone on the team has those feedback loops. No one is insulated. Um, when you're in that type of environment, even for just like a couple months, you just get so much so much better.
1:01:26 And I think a lot of organizations, uh, it's hard to keep that type of situation as your company grows. I think it's probably impossible. Um, so if you mostly worked at larger companies, this is probably the thing that you've never fully experienced. Um, I've been at companies where the product team would want to like ship something faster, so they'll cut stuff to get it out sooner. The pain is not felt by them.
1:01:48 It's felt by their support team. The support team deals with the angry people, and the support team fixes things manually for them. and the engineering product team are like, you know, hey, we did it. We shipped the feature and they don't realize that there's like a a side effect that they created. So, yeah, like really being in that feedback loop just makes you makes you better. Uh, I think caring a lot about building something for a lot of people.
1:02:08 I think this is another thing that uh you don't have to try to build stuff for millions of people. I'm not saying you have to do that, but it is very interesting to have that perspective of hey, make something that works for the whole market. It's so hard to do that. There's so many different environments, people, workflows, preferences, constraints. If you adopt that mindset, the stuff you work on makes no sense to anyone else observing things.
1:02:32 They think that everything you're doing is wrong. They think you're focusing on the wrong stuff. But if you really are going for the whole market, like you just start to
16. How building works at OpenCode
1:02:39 think very differently. Can you let us in a little bit of of how the open code team today works? like tell us how many people there are, what kind of setup, and maybe we can walk a recent feature that you or or someone else launched or like was it even team and then how how you also get this like immediate feedback. >> Yeah. So, we're still figuring this out because we've grown a lot recently like we're at 20 something people now and it's happened in the last congrats.
1:03:02 >> Thank you. Yeah, it's happened the last like couple months, like 3 months or so. So, we're still very much in the phase of getting everyone settled. We're in that horrible feeling phase where we have more people than ever, but we're like going slower than ever because like everyone is still kind of getting getting situated and getting up to speed, etc. So, we're trying to make it through that phase as fast as possible. Uh, I think for us, um, we're very we're an open source company, so which means all of our code is already public, so we kind of build in public as much as we can.
1:03:28 Um, we uh we've been trying to figure out a good terminology for this, but if we have like a thing we're trying to ship or make happen, there's a phase where we're trying to like push it up the hill and that's like a painful phase cuz you're going from zero to making it exist. And there's a point where it's definitely not done. There's definitely a lot of work to do, but at that point, most of the stuff is figured out as most just like fleshing out the details.
1:03:47 Uh, so our team really tries to focus on getting it out of that first phase into the second phase as fast as possible. We kind of put a milestone of like this is a demo that we want to show people. Let's try to get it to there as fast as possible. And from there, again, because we're so public, because our users are so vocal, people tell us exactly what to do after then. Like once their foundation is there and people roughly get what they what what a feature is, they'll tell us what else they need.
1:04:13 They'll tell us like where else we need to make it work. They'll tell us what sucks about it. And it gets very easy from there on. And whoever worked on it, they do that full cycle. There's no one that's like receiving the feedback and summarizing it from the engineer. They're receiving the feedback. They're getting the GitHub issues. They're getting the replies on on on Twitter and they're figuring out the road map and the cycle for it.
1:04:31 Um so that first phase is the hardest. But from there again the feed lot feedback loop kicks in. Things get better over time. One of the things that we try to try to do is um like the founders, we try to make sure that the the whole team has perspective on everything that we care about, the market, our competitors, what we're trying to do, our position in it.
1:04:50 If they properly understand that, they naturally land on their own priorities. For us, motivation is a huge thing. I said it earlier. We know this is a long game. If it's a long game, your strategy should be how can I stay in it the longest. The only way to do that is to work on stuff that is exciting every single day. We kind of let the whole team grab stuff that they're excited about. What's the biggest problem they want that they think is the worst thing that's hurting us, they're just going to grab that and work on it.
1:05:14 They roughly end up having good judgment if we're doing a good job providing them like the right context about what's going on. So, typically people will just grab stuff. Uh there's been times where on our team really want to work on something and I like vocally disagree with it. I was like, I don't think we should work on that. And they've been right. Like I I think like a few weeks later I realized, oh, they were actually correct about it and I was wrong.
1:05:35 So, it's really
17. Taste and quality
1:05:36 exciting to see our team be able to start to do that kind of thing. >> One thing that comes up, we didn't mention it a single time in this conversation, but elsewhere it often comes up is taste. Uh there's this this notion or idea that one thing that AI is just very bad at and probably will stay bad at is having taste and and how as engineers taste taste, product sense, they're I think synonyms to some extent.
1:05:59 Uh, in fact, I even heard that Microsoft internally has a training for taste to get better at taste, which I I'd love to see that one. >> What What is your take on on on taste as a whole as as as a as a concept? So, I think fundamentally it's a it's a good idea. There's something that makes sense there. I think with good ideas, they're very simple and so everyone kind of repeats the idea, but good ideas are simple, but very very difficult to actually live.
1:06:23 So, it's very difficult to actually have good taste and it's like a lifelong Yeah. One, it can be learned. uh it's like a lifelong thing that you're going to work on forever. I think the root issue is a lot of people will say that the whole taste thing, but do you actually believe it? Like do you actually believe that your product has to be good? There's so much like there's so much out there now that's like the code doesn't have to be good.
1:06:45 The product doesn't have to be good. Like nothing has to be good. It's just this other thing. You can still be successful. when they point to companies that have crappy products, that have crappy engineering, but still make a lot of money, right? So, there's like a thing in the air about maybe all that stuff doesn't matter. The moment that gets in your head, like nothing like you're not going to have you're not you're just not going to ship good products cuz fundamentally you don't believe in it.
1:07:08 And I feel like the number of people that like vocally believe that craft is really important, making an irrationally good product is still something that you're going to do. Uh because most great products, they could probably be like 50% less good and have no material impact on it. But it shows up in other ways that are really hard to directly draw that line. It's if you start to be lazy in one place, you start to become lazy everywhere.
1:07:29 It's like an infection. So my thing with the whole taste thing is like, yeah, you're saying taste matters, but do you really believe it? It's like a very, very high bar to be someone that says I really care about good products. For me personally, I care a lot about it and I am nowhere near achieving my own bar. Like I'm like so missing my own bar and what I think what I believe. So when when you hear me talk about body and stuff and use my products, you're like, "Oh, it doesn't he's like kind of ahead of what he's saying."
1:07:56 That's cuz like I'm like still trying to get better at it, you know? So I look at products that are really good. I'm still very inspired by them. Um I still have like heroes that I think uh just kind of do a great job at certain things. Uh I know I have a long way to go to get there. Can we talk about the these heroes, the the products and the engineering teams that you look up to and why?
1:08:17 >> Yeah. Yeah. So, I think um in my space in dev tools, uh I think Mitchell Hashimoto is like an obvious one. Our company is very similar or trying to be similar to theirs in that all their products were open source. Uh they became mass adopted. Things like Terraform became the default. You know, it's very hard to do something like that. And it's well executed across the board in the microscopic, in the macro, the business model. uh you know his work with Ghosty has been really great.
1:08:42 The architecture of it cares about every little detail and it shows up uh when you use a product. So um and he's very good at product and I think he he he has a he made a clip that's very similar thing we were just talking about where
1:08:56 every feature you ship it's not about the features it's about how it interacts with every existing feature and his work as a product person is to make sense of all that. Um and he's very good at doing that. I think he's probably one of the best for being also a good programmer. So, I think he's someone that I admire a lot and I hope that we can kind of be as good as that one day. I sensed as we're talking about taste, we started to talk a lot about quality.
1:09:15 Could it be that quality is one of the last few things that these days a startup, a small company going up against golads has left to to hang on to. >> Yeah. Yeah. And I think the the flip side of it is uh it's easier than ever to rot your product. I think it's uh with these agents and everything. So you see with big companies, big company's products are rotting faster than ever. Even startups products, I was saying this the other day, like now if a product is a year old, it's probably already kind of going to And I think it's because of of like these agent workflows.
1:09:45 So yeah, I still believe quality is a huge differentiator. It's not just something you can decide to do. I think it needs to show up every single aspect of your company from like you have to do things that are irrational. I think that's kind of what quality comes from. like you do a bunch of things and like 50% of those things you you didn't have to do and I think very few people are willing to operate that way.
1:10:07 There's like a cold logic these days to programming and to software and to products. It's like I'm like a business guy and I care about business which means I only do things that are hyper hyperrational and a lot of people think that's what being good at business looks like. Um and of course that can work but yeah I think quality is like a huge differentiator. Um I mean even if you look at our story when we first launched open code uh cloud code was the only other real thing we were going going up against.
1:10:33 A big initial differentiator was that our terminal experience just felt better. We spent a lot more time on like we built our own terminal framework. Like building your own framework is like the first thing they tell you not to do, right? It's like the thing that no engineering team should do. >> It's irrational. >> Yeah. Exactly. It's irrational. But like it did. We looked at it and we're like we couldn't achieve the experience we wanted. Like we we're people that use terminal tools.
1:10:57 We look at tools like Neoim and enjoy them and know what is possible. Like uh I mean again going back to Mitchell like he worked on making terminal stuff as good as possible. Like he knows what's possible with it. Once we know what's possible, how are we going to ship something that's like not pushing those capabilities to the max, right? Uh and very initially a lot of the reason people were uh using us when people were talking about us compared to cloud code was how janky cloud code was or how much it flickered or how much it did whatever and it didn't matter like they're still a hugely successful product but we irrationally focused on some of the quality stuff that helped us go up
18. Dax’s work setup
1:11:32 against a much larger product company with much more funding. What's your work setup? >> A work setup I've now switched to a framework desktop. Uh >> nice the one where you can replace >> Yeah. Yeah. the the the little like tiles in the front and stuff. Yeah. So, uh that uh running Arch Linux on a not an ultra I guess it's a 5K display. Just one 5K display. Uh I use Italian window manager which I've been using for 10 years and that's roughly it. Yeah.
1:11:57 Got my SM7B as well, the mic. And I use my iPhone as my camera. That's about it. >> Yeah. And then you use mostly terminals of course. Open go terminal, right? >> Yeah. So I use uh Oh, I guess my setup is actually a little bit more complicated. So that is my physical machine but I do all my uh work on a remote machine. So I sh it to uh a much bigger beefier computer uh that has many team sessions going one for each project neoim as my editor and then open it's usually split half.
1:12:28 So like neovim on the left open code on the right um and I'm going between the two. So yeah arch
19. The role of engineers and EMs
1:12:37 uh neoven open code. I wanted to ask you how you think engineering leadership has changed with AI because you you've been an engineer founding engineer then you you've led teams before you're technically leading a team now as well and and also like when when you talk with other you know you're not talking with a lot more like CTOs and and and like-minded folks what's different is are people being more more hands-on uh is this is is that even a good thing?
1:13:02 Yeah, I think uh I'll tell you something that I've heard and I think and on one hand this makes sense on the other hand I'm not too sure about it. I think these teams are now looking themselves as okay, what's the role of an engineer now, right? If you're not going to write the code, what do you do? Your role maybe is to figure out how to make it easy to ship code that is to safely ship code, right?
1:13:22 Um, set up guard rails so that someone promps an agent to do something, it's not introducing a bug. Like, make sure make sure your testing story is good. Uh, make sure there's like proper conventions and patterns in your codebase that agents can follow so they're not like adding something that's really crazy. So your your role ends up being more like how do I set up the right guardrails to make it so someone that is using an agent can kind of blindly ship something that that works well.
1:13:47 Whether it's another engineer, it could be your marketing team that is uh trying to ship a change to your website. How do you make it safer to to make changes? And this is like the novel way that everyone is kind of looking at engineering teams. The thing that I find interesting is that's not novel. This has been the thing we've always been trying to do forever. How do we get a junior engineer to ship code safely without breaking stuff? Right?
1:14:07 How do we make patterns in the codebase? How do we make tests? Like it's it's all the old stuff that we've always wanted to do. Like I would love to be able to hire 100 junior engineers and have them be effective, but you know there's like limits to that. We were we never really figured that out and like some companies did to some degree, some companies kind of didn't. So it's kind of the same problem as always which is how do I make a less experienced person punch above their weight, right?
1:14:29 And now you know it's using co coding agents that's maybe like how do a designer ship stuff like that. Uh so in a lot of ways I think it's the same problem as always which is how do you make code bases that are easy to work in scalable flex to new requirements. Um I think a lot of like the old patterns for me are coming back.
1:14:47 We've always been like a big domain driven design company. Um we did it in a very light way. We're now doing it in a much heavier way because we find that these like kind of bory enterprisey uh patterns end up being pretty useful because you have a bunch of idiots on your team now. The coding agents are a bunch of idiots and they are going to work 24/7 and they're going to like ship a lot of stuff.
1:15:07 So you need way more guardrails than you used to. And I think what's nice is some of these old patterns we hated because they were very verbose. They produced reliable code that was like modular and safe, but they were very verbose and annoying to type out, but you're not typing it out anymore. So now you can kind of get the benefits of these patterns without the downsides. So we're starting to like explore that more and kind of enjoy that.
1:15:27 >> Yeah. I wonder if like design patterns might make their way back. Remember in the 2000s or like mid200s they were a huge thing of like again for structure it helped junior engineers not mess things up. >> Yeah. >> And it was very verbal. So like eventually people just like hated them and got rid of them. >> Yeah. And and if you're a good programmer you you didn't have to do those patterns. You can kind of like you didn't need the training wheels in a lot of ways.
1:15:49 Um, but now like you know the
20. Advice for engineers
1:15:51 agents don't have training wheels so you got to put them back on. >> Yeah. And what what advice would you have to more experienced engineers who again had been pretty good engineers until now and they're like all right I just want to like stay with it. Uh keep keep my game high and you know have the skills and and build up the experience. So like I I could work at a place like open code. I have a tough time giving advice to people because I feel like I work in such a weird place.
1:16:12 Like my company one it's a startup so it's innately uh automatically a little bit weird. two like we're we do open source which is like there's like five companies that are open source companies really. So everything we do and the type of people we try to bring in I don't know if it generally applies to everyone. I think the most I could say is and I've always believed is even even preai is uh software engineering is a skill that can be applied to an industry and you can just be a great software engineer and that's that's totally fine.
1:16:42 make a probably good good career doing that. But you if you also become an expert in a specific industry, that's like a deadly combo. Um if you are like just pick any industry, let's say let's say farming, let's say you understand that farming industry really well and you're also a decent software engineer, you're probably like the top 10 people in the world for that combination that the whole industry will want to hire.
1:17:05 But like and I guess what's great about being a software engineer is you don't have to pick an industry. like everyone else has to be like I'm going to be in medicine for the rest of my life. You can choose to do medicine for 10 years of your life and like do tech in in the medical field and become an expert in that and realize you don't like that industry and pick a completely different industry and just go become an expert in that. That's so exciting.
1:17:23 I think software engineers are curious people and uh it's just so fun to be able to like deeply learn an industry in that way. Um and eventually you'll find something that that clicks that you can stick with and being a good engineer and also being an industry expert like it's very easy to become a unicorn of a person in that way. >> And when we started we were talking about how software is everywhere. Software engineers are everywhere.
1:17:42 And I guess every industry will lack software engineers who are really curious about their industry. >> Yeah. It doesn't take long, right? You spend like a year in in any industry like you now know it more than like 99% of people. So, uh, I think it's but I think the trick here is it's very easy to turn your brain off to that side of things and just focus on I'm given a task to like add something to the UI and like not your opportunity as a software engineer is you get to be in any company in the world and learn about anything and you should kind of like take
21. Book recommendation
1:18:12 advantage of that and I think it there's a rational career reason to do that as well. As a cos do you have any book recommendations things that you've enjoyed or change how you think? >> Yeah, it's funny cuz uh I do not read books at all like >> or or reading recommendations. Well, so I mean, can I expand on that? My wife is a avid reader and I get to benefit from that cuz she reads all the books and then she tells me like all the good ideas in it and I restate them like they're on my own idea like I've read the book.
1:18:37 I did have like a reading phase earlier on. I think kind of helped uh help me understand like a lot of how the world works. Uh I'm a big fan, these are like boring recommendations, but I'm a big fan of uh a bunch of TB's work. I think he's basically got like a couple good ideas and it's maybe hard to read a whole book cuz a book is just one good idea inflated into a book, but these are just fundamental true things about the universe that you can just see play out everywhere.
1:19:00 Um, so huge fan of like stuff like skin in the game. Uh, obviously Black Swan is super popular. A lot of the stuff that I found to be very influential on myself is the idea of uh emergent properties. So almost everything great in the world is came not through like top down design. It came through a bunch of smaller entities operating together randomly and then something kind of great comes out of that and that you see that whether it's in like robust software or like what makes a city great, what makes a neighborhood walkable, what makes like an organism like uh capable of surviving disease.
1:19:36 So this whole like bottom up versus top down uh in terms of designing systems, there's a few books that talk about that. TBS is one of them. Uh, and I feel like I see that everywhere. Like once you kind of understand his ideas, you realize like they kind of underpin the whole world. Dax, thanks so much for this conversation. This was fun. >> Yeah, it was good. Thanks for having me. >> I hope you enjoyed this conversation with Dax as much as I did.
1:19:56 Dax is in a rare position. He's building one of the fastest growing AI coding [music] tools out there, going from 650,000 to nearly 8 million monthly active users in [music] just a few months. And yet, he's the one telling us to slow down. One thing I really liked is what Dax called the muted prickle. PreI, when you wrote a hack, you knew you were writing a hack. You felt a little bad about it. You'd remember it the next time.
1:20:18 And that feeling kept your judgment sharp. With AI [music] agents, that feeling is gone. Now someone else is dealing with the consequences. The landmines are still there. They just won't blow up on you today. [music] And we don't even pay attention to a lot of these landmines being placed by AI agents. Finally, I really appreciated Dax's memo to his team. He basically admitted, "We're shipping features we shouldn't. We're absorbing too many hacks and the worst part is we're not even moving faster.
1:20:40 We just feel like we are. That's a pretty brave thing for a founder of a hot AI native startup to say out loud and I think it's a reality check that a lot of engineering teams need right now. If you enjoyed the episode, be sure to subscribe on your favorite podcast platform or on YouTube. And if you'd like to support the show, leaving a rating or review really helps. >> [music] >> Thanks for listening and see you in the next