Inventing the Ralph Wiggum Loop | Creator Geoffrey Huntley

Hey there, and welcome back to Devin Terrupted. I'm your host, Andrew Ziegler. And I'm your host, Ben Lloyd Pearson, and I'm excited to announce that we're doing something a little different this week and starting this week actually and moving forward. First of all, all these long form interviews that we publish every Tuesday that are not going anywhere. We have a really wonderful guest, multiple guests lined up for upcoming episodes, and we've got another really fantastic one today that we'll get into in just a moment. However, we are going to split off our normal news segment into its own show every week. Little come out on Fridays, so this Friday will be the very first iteration of this new show. So tune in this Friday to get news updates from us. We'll even try to bring in some experts from the field to share really cool things about what's happening in the world of AI and engineering productivity. Those are the changes. Andrew, what are we have coming up today? If you're an engineer, and you've been online at some point in the last week, there's a good chance you've seen Ralph Wiggum take the industry by storm. And what is Ralph? And it's creator's own words, Ralph is a bash loop. And that creator is Jeffrey Hauntley. Jeffrey has been pushing one of the simplest most provocative ideas and autonomous AI-assisted coding. And Ralph, it turned any iterative work into something that keeps fixing, refining, and evaluating until tests pass or succeed. And really the brute force effort of this can't be understated. The amount of work that Hauntley can do with this type of loop is truly profound. And this work, it sits at the intersection of practical workflows, philosophical insights, a little bit of contrarianism, and a very bright glimpse about how the future is going to be built with simple loops, clear goals, and letting feedback drive the convergence towards done. And we've been covering Jeffrey's work here on Devon Turrupted for the past year. Today he's joining us, to dive into Ralph's origin story, and what that means for you, now that the cat is out of the bag. Yeah, and we've discussed quite a few deep topics. We'll have links to all of this stuff in the show notes because there's a lot of reading that I think goes along with this episode. And one of the concepts we'll talk about is this new article from Steve Yegey called The Gas Town, which just describes a very complex system of effectively applying the Ralph concept to much larger challenges. So I think this is one of the most interesting discussions we've ever had at Devon Turrupted, and there's a lot of things for our audience to dig into on this one. And of course, all of this content will be our newsletter and sub-stacken LinkedIn. So be sure to find it, join the conversation, as well as your fellow developers, as we figure out what all of this means for us. Now let's dive into the interview. This is so exciting. I'm actually kind of excited that we also have those lost tapes because that was some really good shit that you were putting out there, so I can go about a lot more. These are our secrets now. Yeah, and now those are like, wow, those are, now, not only I only heard that, it was a closed room. That was great. But so this is just like overwhelmingly cool, Jeffrey, like, that have you here, they give you some context. We've been talking about you a lot on Devon Turrupted for the past year. I would attribute really what I know about starting to work with these tools and even using cursor to you, all of what I've learned in the last year started with reading your articles as like the nucleus of that thought. And so to be here and be able to kind of chat about your ideas and how they've evolved is really exciting for me, and because I watched you bring the, and now very well-known Ralph into the world. And that's what we want to talk about today and what it means for developers that are maybe using their own Ralph's because I think there's a huge revolution happening right now at the top of the year with all the engineers coming back from the break with new ideas, Opus 4.5 under their belt, and just a lot of insight from folks like you out in the field that are experimenting. So we're really stoked to have you here. But I want to just also frame the bash loop itself and kind of take a step back because I want to start there and just ask you, when you brought Ralph into the world and you named it Ralph, why give it that name? Yeah, so it's February last year, almost a year ago, and I was doing spec based development. I made a mind at GitHubNix, published some research there about two years prior to that. And I remembered that on spec based workflows or LLMs generating apps, this is like the Jupiter T3 days. So I started applying it, and then I started realizing that I could probably, this could be quite mechanical, like if I take specs and how I'm doing things. And then I got to the point where I was really like, wow, there's some pure first principles thinking here of like, I could deterministically allocate the array. And the first thing I was like, okay, what can I do with this? And this was the Z80 long post, and I started the path of essentially using LLMs to essentially clone product features and all existing companies. And like, taking source code that was like, BSL, license source code, and like, clean rooming it into specs, very similar to how the Intel and AMD CPU came into. And I re-implemented like Hashikop Nomad, I cloned the company Tilescale. I did all these random things. I remember Rovo, we read Rovo, Rovo, you did several of them. It was really interesting to watch how you use the LLMs to do this like a binary analysis, and then you would pull out this information and rebuild what they had put in it, and it really kind of took away, like it drained any mode that you could find. Like you could go to any mode and drain it with that and be like, I can build this in a day or with this loop and figure out how this works. Nothing can stop me if it's on my computer. Pretty much. So, for developers, you go speak about the founders and how they're feeling about this. Because it's pretty gloom out there for founders. Like we can focus on the developers and developers side of things. But go speak to your founders. Now, to answer your question, when I discovered this in February, it literally made me want a Ralph. Ralph is a term for vomiting. And it wasn't named. It wasn't named. It wasn't a technique was not named, but it made me want to vomit because I could actually see where we're going. I could see where we were going. I was building software in my sleep, and then I started publishing a lot more. I focused heavily in on, like, do you, do you use your screwed? If you don't pay attention, got that distributed to Prime Gen, so the Gen Z popped off in that area. And that was like real guidance explaining the cycles of our industry. And I really focused on some of you not going to make it. You need to be curious. There was reasons behind the order of my publishing. Because I was spooked. I was feeling like really sick in the stomach, knowing what I had essentially discovered. That if you drove it in the right way, allocated the context window to terministically in a loop, and it was also simple, that I could see where I could go. In the future belongs to everything talk I do, and I say, like, I walk around. I see dead people, like the sixth sense. Like it's not like they're literally dead, is they just don't know that they don't have a job yet. And I'm like, wake up, wake up, please wake up, please be curious, like play the LLM, like they're good enough now, play, please play, please play. And then I went across to San Fran, went to a meetup, I ran into Dex Houghty, and we had a very similar moment. So I had that moment in February with myself, and then in July, I just rocked up to a meetup in San Fran, two hours late, presented late, presented last, and we just kept going all night. And it was like 15 people in there, and we spent an hour afterwards going, oh my god, they could see it, they could see it. And because it's San Fran, I decided, hey, look, the word's going to get out about this thing, because I just essentially showed the technique for the first time. And I decided, well, it needs a day, it's kind of dumb, it's kind of lovable, and it never gives it up. And it made me want a Ralph, so I called it Ralph, I was in Ralph Wiggum, and thus, if forever is now stuck in meme folklore. But it also has an alternative meaning, it also has an alternative meaning, which comes into the future of software engineering. What Dex and I have calculated is the software development, as profession, is dead. But software engineering is very much alive, okay? If your value to a business is that you type things on the keyboard, would you believe Open, sorry, Sonnet 4.5 on a loop with a bash loop Ralph, it costs $10.42 US an hour. Now what's the minimum wage law, what's the minimum wage law is in your state? I'm pretty sure that's why the discussion in San Fran was going on so long, was we realized that a fast-food worker will get paid more than a software developer. Now I don't need to be inflammatory in saying that, but the unit economics changed. It changed six months ago. There's been a batch of Y-combinator companies roughing, you folks were early, you're reading, you're growing, like that. There now exists people who are year in, or six months or a year in, or been applying it, and that the rift on this is becoming huge, huge, huge, so unfathomable, huge. It is unbelievable the difference, someone who's been curious for the last year and invested in themselves has as an advantage because all the frontier labs were giving away infrancing for almost free, now we've got these quotas and caps, so we were able to burn tokens into absolutely crazy stuff with this space dust. Now, software engineering, however, is a life, software engineering is a life. If you're just doing development or typing the keyboard, yeah, it's predictable, what's better transpire. Autonomous worker can do your job, a PM can drive a autonomous worker to do your job. Now, software engineering is a different discipline, this is the, like actually, engineering. If the idea of autonomous loop within your code base makes you want to Ralph, listen to that feeling, right? Autonomous loops, it's like the shipping container, like you look at the cost of freight per ton before the shipping container was invented and there was sky high, and then it was like sense to the ton after the shipping container. The rough loop is that same type of equivalence of the change in the unit economics. It's not going back, so if you're the software dev or all the sailor carrying cargo on and off the ship manually, please understand the container, the box just got invented. Now, engineering is different to software development and engineering is now the game because let's say running an autonomous loop, you're like, oh, what happens when it drops a database? Sweet. You're an engineer, right? What are you going to do to stop it from dropping the database? Don't provision right secrets. Maybe you would do some tests and enable a change data capture and then you have to expect the audit log, like engineer your way out of the failure scenarios and the more you do that, the more you capture the back pressure, which allows a more autonomy for the new unit economics. That's the game now, like pre-commit hooks, property-based tests, snapshot tests, and eventually you'll come to where I am where I don't even use CI and my agents run full with pseudo auto machine, bare metal box running Nick's OS, and I don't review the code. The agents autonomously push to master, no branches, and the deployment happens in under 30 seconds. And then if something goes wrong, I've got feedback loops which feed back into the active session and then it just self-repairs. So, we're starting to get into, when you start to get into some what I'm researching, I call this loom, and Steve Yager calls this gas town, we're exploring what it means to be self-evolutionary software. Now, you don't have to yolo commit into production. There's no reason why agents can't be in control of feature-flag experiments and add in the branch, and then they connect us to some other data source, and then they make the cut over, and they roll it all out again. So this is engineering now, folks. It's all an engineering game now. You're talking early on about the importance of that curiosity, and I agree with you. And I feel like it's, right now, feels like the best time in my career to be curious. Like, there's so much opportunity when you know where to look. And I feel like a lot of people, their perception of this technology is a little bit tarnished by what may have been early experiences with it. We've all been using these tools since the days of GPT 3.5 or whatever it was. And I know that the things that it failed on back then were obvious often, they often felt like it really did not seem like a very effective tool. But here we are. We've had multiple generations of models come out. The models have gotten substantially better in the last year, in particular, I think. And I feel like there's, because the reputation of AI has been tarnished so much by the early phases of it, that people are struggling a little bit to see what the next version of this all looks like. I'm sure kind of curious, if you felt something similar, even with these autonomous loops that you're building, that you're ralphing, are you seeing the changes to the models even resonate into improvements for that method of doing things as well? Absolutely. So the start of, when I really started publishing, like from my OFUCK moment, was boxing day, I guess two years ago now, or 12 months ago, really, that was like Sonnet 3.5, and I was able to generate like a Haskell audio library, it was so stupid, it wasn't like regurgitating Stack Overflow, that was my mindset and my frame, I'll just regurgitate Stack Overflow. I tried this in 2.3, it's not anything, and I came back because I ran in a loop by hand in cursor. I wasn't quite yet at the very, like, novel idea of just running in a bash loop. It was just very mechanical, like I was just doing the motions of specs and everything else. And that just shook me, and then when I got to February, this was at GPT-3. So that shook me, my previous frame of reference was like GPT-3-ish. So that was like, it took a call with a founder to say, Jeff, you need to get on the tools. Like, you need to start writing. Do you see what I say? I'm going to hang up now, and you go play, and you call me back. 24 hours later, I was just boxing day, I was just completely shook, because I could see the slope, right? It's slope on slope here, folks. It's a derivative of the slope. And then February, I kind of really made a very mechanical, and that was the Z80, cloning, and realizing what was going on. That was like Sonnet-3.5. The way I described Sonnet-3.5 was, it's weird. When you start really playing with the models, you start atomorphizing the models, and this is how I came up for the idea of quadrants of behavior, like high FX, low FX, an Oracle, a deep thinker that doesn't take action, and then highly, highly agentic. So I called Sonnet-3.5 a squirrel on cocaine with a chef's knife. You did. I remember that. Yeah, I called it that because it could cook you a meal, and it was so highly agentic, but it had a squirrel brain. If you took your eyes off it, it would murder your code base. And it would do it all the time. It could touch. It was tall, hungry, tall, happy. It was a trigger friendly. It was a different kind of model. It was a different type. It really was this hyperactive squirrel that would stab you if you took your eye off it. So you had different techniques to really control it, et cetera. And now, like, all, if you look at, like, cursed and all those things, or like, why it looks like chaos, it's because of the damn squirrel. It's because of the damn squirrel. And now you don't need to do all that stuff because, like, Opus didn't suddenly get better over Christmas, just people played. Right. And now, it's good, but the way I describe Opus is, it's highly agentic. It produces great outcomes, but it's a little bit forgetful. So you have to nudge it in a reminder on, like, if you give it too many goals, it might forget the goal. So Ralph and the idea of one loop, just doing one thing means it's going to be less forgetful. When GPT-5 first came out, I was in San Fran, and we couldn't figure out what was going on, because we were just in the office, and we were, like, maturing a harness. And we're like, this thing feels like it's low testosterone. Because there's this big webcast, et cetera, what's going on? And we're like, this thing feels low T. And we could have figured out why. So went down Crosser Road, spoke with essentially a competitor that's playing with this. And we're like, why is it like, why is it low testosterone? And they go, oh, this is San Fran. You can't say low testosterone, Jeff. We prefer that words timid. And then, and then you start riffing, like, what's going with the model? Like, the harness community is really small. They might seem like enemies, but we're all trying to figure this out. And we add a morphize these behaviors. And then we see what we can do to get rid, once we've identified a commonality of behavior, what can we do to get rid of it? Now, it turns that GPT-5 doesn't like you using uppercase. If it, it can say, is it yelling at it? And it gets timid. This is in the open AI model cards. Like, if you yell at it, it, it, it, it it won't do its task. It actually does. So we stop yelling at it in our harness prompts and all our tooling. But this is where it gets really weird. Because if you've got a code base, we have cursor rules. And you've got a model selector drop down in and out. And you've signed all your cursor rules around anthropic models, which encourage yelling at the model, so that you want, they want you to hurl abuse at the model. But if you do it at, you do the model selector, all of a sudden, is it really GPT-5 that's bad? Or are you yelling at the model? Because all these cursor rules now are yelling at the model. Harness is now yelling at the model. And the official published guide on how to tune GPT-5 by open AI says, don't yell at the model. Isn't it funny to think that they're not compatible on an API level? But then also on a behavioral level, the types of things you'd put in the prompts on the, like the human created parts that go into it or the text base parts that go into it. Like it's, even those, they're, they're not compatible. They're not compatible. Like, my understanding is the MCP specification still doesn't have a user agent sniff topic. So it could switch out the prompts based on what the consumer is to take this type of nuance. And all the MCP servers you download and run, they're the same story here, they've been built around anthropic, and then you use them in a different model. And it's not so good. It's not that model's no good. Like it just hasn't been tuned. That's right. And how do you know if you're tuning is because you start animal fires in the models and you start noticing these weird things and you're going around other people who start thinking along these lines and you just try things. It's a very different skill to building software with the tools. Like tuning is a very different skill. Yeah, it was definitely times that I've taken the same problem and taken it to a different model and gotten the result I wanted when I didn't get it from the first model. And I'm kind of, I'm curious, you know, because so Ralph is like, there's two sorts of sides to this. There's this like brilliant simplicity that just takes a very simple concept and uses it to iteratively improve on on an output. But it's also like incredibly inefficient, isn't it? Like it is. Is this how we're going to like tune these models or make them better? Or are we making up for a failure of the capabilities that will get addressed at some point in the future? The game is always changing. Like the prompts are used for curse and from February and all that stuff to try to keep the squirrel on rails. No, no, for apply. The game always changes. Like I still see people doing like GPT-3, big UR first UR, UR, a QA developer persona and all that stuff. That stuff's dead folks. Gone. Gone. It doesn't matter. Like you'd stop treating it like it's GPT-3. Persona-based is dead. Now to your question, that doesn't mean you shouldn't adopt and start playing now. Just because the knowledge is disposable, like you'd need to actually learn what it is and is not possible. It's the capabilities and knowing on how you do loopbacks and all this and you learn all these tricks, the tricks. For me, in the last year, I haven't lost. But the approaches how I get them have changed. The approaches how I get them have changed. So Ralph is incredibly inefficient. Because what you're doing is essentially mallicking and array every loop and then telling you to only do one thing and then you have to re-mallick this big thing at the top again, the specifications each time, each time. So there is waste there. But if you think about that Ralph of enables a path for founders to get software development of $10.42 an hour, any types of talks of efficiencies is just going to drive that price down. So I mentioned the word array and this is maybe some advice to for developers in this space. Context windows are tokens of these weird MLE terms. I want people to think about this as an array and memory management, mallicking and array. Because that's all a context window is. There's no memory on the server API. There's none. What you're doing is when you do a prompt, you're allicking or mallicking, you're prompt to that array, it literally gets sent off as a standard rest request and it gets churned on some GPUs. And it might go, you advertise the capability that you could run a program. So that response comes back. Your harness says the LLM wants to run a program. Okay, I'm going to run LS and then it auto-allocates the LS to the array and then it sends it back for more infrasing. You're just mallicking arrays here, folks. So and that's one of the biggest turn of inventions that the cause from my oh god moment was I used to copy and paste code from GPT-3 into like an editor, press compile, and back forward copy and paste manually. Or tool calling is the automation of that. Okay. All Ralph is is the automation of tool calling for a system, and treating the entire thing as a system and taking a system space approach from first principles. So if you got this array that you're mallicking, and then there's some hints in the name of a context window, software engineers should know what a sliding window is. So you got an array, you got a sliding window, the window is only so big, the array is much bigger. So the less that you allocate, then the more the window is going to be out of C. So thus the thought that you should only pick one in the loop. And this is really wild because a lot of engineers right now are using a multi-stage planning and they're they're treating it like a child. They're breaking it down to the steps they should do and they're in this high control thing. Invert that thinking. LLM's a fantastic prioritization. If you building a brand new application up from specs, it will do the logging module first, it will do the telemetry next, it will do repository patterns for databases, it will do the right things in the right order. So by just telling it to just pick the best, like the most important item and only do one, you're mallicking less into the context window because what happens with a context window is you got an advertised number of 200k. That's a marketing number folks the same way you get a hard drive and it says it's 20 terabytes but it's only 18 terabytes usable. The same thing here in thinking because there's a harness overhead. There's a harness overhead and then there's a model overhead. So a model overhead would be like the actual programming of Opus for example, you can't get rid of that. So all of a sudden you can crudely say that you lose 16k tokens to the model overhead and then when you're using cursor or any cloud code or what else have you, you also get a 16k overhead. So the real number is like in the 176 but if you put an MCP service in there all of a sudden the real number gets down to like 120 and then you throw in some cursor rules in there. I've seen people operating with like, this is like a Commodore 64 worth of memory and they've allocated over 80% of their memory before they even be able to get a loop going. And because this is a sliding window it's so easy for it to get forgetful and all these other things. The more you allocate the the more you're going to get bad outcomes. So Ralph is a deliberate attempt to minimize allocation. So I never get a compaction event. Compaction is the equivalent of, imagine you've got this beautiful context window, a beautiful ride getting you really good outcomes. And you, oh my god, this means you've seen them. And then it's like, oh, I'm so sad, yeah, and then it compacts. Or even if it doesn't compact it, it gets anxiety that it's going to have to compact it and then it starts making bad decisions as a result. So that is, Sonnet Fall had the, it was, we just, we actually described it as moment reading harnesses as it had context anxiety. I hope this doesn't really have some of those attributes, but what would happen when it had context anxiety, it would go in a simple implementation. I'm running out of time. I'm just going to like comment out this thing and cheat. Like there's all these little meta things. So, so the idea of I want people to think about compaction because there's a new term for folks is really simple. Imagine that you've got this array and this array says this is specifications, this is goal. Compaction is just literally, imagine a jenga tower, right? And if you pull at the wrong brick at the bottom, the tower falls over. Compaction is essentially the equivalence of it like a jenga tower visualization of outcomes, but also if you download a video on YouTube and upload it a thousand times, download upload, download upload, it's actually a loss, it's a lossy function folks. Right. So what happens if the, the compaction removes the thing that was giving you this juicy golden window, which could be your specifications and if the specifications get compacted out, next thing you know, the end result is it starts making stuff up. So avoiding compaction and then using that array with a singular goal to get stuff done. Now, if we go away from Ruff really quickly and let's just say someone as that Steve Yagi's one or two, what is a failure mode I see is software developers, they click new chart, they get, they, they like make a website pink and then they reuse the array and they set another goal that's completely nothing to do with the website being pink and then they say make me an API and all of a sudden they've got this backend API control with pink rest end points. Like you need to be thinking about a new chart is the new array, each array, tracking, track hygiene and before we go past that and just rewind a bit, there is proven scientific research of the notion of context rot and the existence of a dumb zone. So if you think that you've got like a 200 K and like once, once you go like 60, 70% over that, like the LLM starts getting dumber, actually dumber. So you want to like minimize the amount of time in your dumb zone is what DexHorty would say and it is true. And so Ruff deliberately is you don't want to get in the dumb zone and you don't want to compaction but you want to deterministically allocate. It's an orchestrator pattern for a gas town or for what is to come next or someone can use to build their own gas town. AI has changed how we build software but faster code doesn't always mean faster delivery. That's why linear B is launching the essentials plan, your toolkit for measuring and improving AI productivity. You get the new linear B mcp server, AI inside stashboard and developer surveys, all designed to reveal how AI tools impact delivery speed, code quality and developer experience. Stop guessing which AI tools work and start leading with data. Visit linearB.io to learn more and unlock the next chapter of AI productivity. You know, let's let's let's talk for a minute about about gas town. You bring up C.V.A. and and and maybe how gas town is something that's building on the idea of Ralph. Maybe it's something totally different from Ralph. I'm curious to know from your perspective, like what you're teaching all of us to do right now and embracing, you know, the slope on the slope. There's an exponential curve of learning and opportunity here for folks and I think the real takeaway from this is that the simplicity of this loop, the simplicity of all of these parts that you have to bring in to keep context small to be light white and to be interchangeable. I think all of that plays into people building their own types of rafts, their own loops and maybe gas town is an example of one of those coming into fruition. But, you know, I personally as someone who's building and using these tools too, I see it as an inspiration to go and maybe craft my own gas town. I've definitely borrowed a lot of concepts from it. So I'm curious like how you think about the evolutions of your concept like Ralph and how you see them out in the world. Yeah. I used to work with Yegi over at source graph. I spent a bit of time traveling around APEC, telling people, pay attention, pay attention because I was sitting on Ralph and Yegi was out doing much more worldwide, big tours because he used Yegi and he's just saying folks pay attention, the orchestrator's coming and he'd already done like he's rant saying this is going to happen and I don't think people took him seriously. So on years eve, he dropped the blog post and said, welcome to gas town. Do not use gas town. Gas town is not for you, but by the way, he's this beautiful chart that allows you to measure where you are on skill level. And in the figure five is the notion where you start deterministically allocating an agent and roughing and when you get to like six and seven, six and seven, six is when you're starting to like learn to run model these at the same time and then you experience failure domains when you're running two at the same time and then you realize it's you've got to do some engineering. So like the two spinning plates you got going to fail in the same way. By the time you get to like figure seven, you got like 10 plates spinning at the same time. It's just different windows on a widescreen monitor. It starts feeling really chaotic. It feels like a spaghetti base in factorial. It feels like spaghetti base in factorial. Where did I put my on? What do I put my all? Where is it? Where is it? Where is it? Where the hell is it? Right. And the reason you shouldn't go to gas town is it's like use gas town is you need to go for the motions of a put yourself development as a developer to learn why gas town needs to exist and why it's coming and that's from like learning to allocate the array and figure five and then also changing your software engineering practices because by the time you're doing figure five, which is Ralph, like a singular Ralph, what happens is you start questioning things like code review. Why do we do code review? I think that what you get that you start thinking like why do we have agile? Why do we do daily standups? It's our job as engineers to potentially falsify the last 40 years of software engineering practices and engineering magnet management practices for our new power tools that now exist. Everything is now different, but we're still an engineer. We don't want failures. We don't want people of like things getting hacked and all the rest. So like at figure five, like you're generating a 40,000 line pull request in a couple hours and your code work is doing the same and like it starts to be transparent in your face, like I think the industry is going to spend the next year going, how do we fix the code review dilemma? The answer is you don't for classes depending on the domain, especially in product. You just don't do the code review. Instead you work on safe release practices. You engineer, if you see valid domains such as you put them in pre-commit hooks, maybe you run other Ralph loops after the Ralph loop is done. That's when you start thinking into when you start getting the megabase in factorial and that's Gas Town. And that's for the lessons learned at five, six, seven, eight is the full application of all that learning that came before. You can't just skip the learning and just go straight to Gas Town. Like maybe you can, but you're not going to have any edge. Like we're meant to be curious as engineers, you go from earn your stripes. It's not that complicated. Now at seven is seven, you create eight because it's just too chaotic. It's so draining. Like trying to find resources in your base to be any town. It's just so damn ridiculous. You're like, stuff, I'm going to rebuild my base from all the knowledge. And then you whatever your domain is, wherever you're a software engineer, you're an accountant, you're like legal, whatever. You will build your own Gas Town. I've got my own Gas Town. It's called Loom. I've cloned GitHub, AMP code, Daytona. I have my own source code called JJ. I have the ability of a source code host. Like I'm basically on the idea. If I want to explore the space of invalidation, I essentially need to be able to control everything from source to be able to change what it is. And now it's so simple to clone product features and companies. The next thing I'll do is like launch darkly. I'll have feature flags in there so I can play around with safe engineering. You can literally clone platforms now folks. The models are getting so good. It's getting so simple. So I have my own Gas Town. But my Gas Town is like a hard fork from everything that's been done today. I want to build an autonomous evolutionary software, Loom. Yagi is within the realms of what exists today. That's a differentiator. Like I'm prepared to like fork, like source control. I've got my own file system that I've built for the agents. Like if you think it's unhinged, I'm doing it. Trying to find the answer of what the right thing to build and not build is and what do agents need. Like I don't think it's I'm inspired. Yeah. I'll give you something to think about. Unix is essentially 40 years of design for humans. Think about it. We have exactly. We have the TTY, which was on the idea of the humans interacting it. We got bash because it was for the humans. We've got a shell for humans. All programming languages. Just evolutions of a base language for the computer. But those were all for humans. All for humans. Environmental variables for humans. Why do we have humans for humans? Humans. Humans. Yeah. Humans. And then you start thinking, wow, what happens if I start cutting down the stack? Like I'm I'm familiar with like Unicorn, all domain, knowledge of research, etc. But I'm like, what if user space didn't exist anymore? That's where I'm going to explore. Like what is agent space? What if we took the last 40 years of Unix design and we figured out what agent space? What if it's just syscalls to a kernel? And that's all an agent needs. Like we need to rethink about what engineering is. We've got this magic like we've got this magic space dust machine that can do crazy things. And I guess when people first do their mouth loops, they're going to feel like I did you feel like you're robbing your future. But not in the sense that you're putting yourself out of a job. I've done all the things I wanted to do in retirement. It's it's idea to execution. Like I want to build a fascism. I built one last year. I want to build a program. Oh yeah, I built one last year. Like you start doing all it's it's like and then you realize this is mass like dopamine that you can just do anything now and you start just doing it. And then we're going to see this mass explosion of creativity of people just doing it. It's going to be like cheer city. It's going to be really pretty. It's going to be scary for founders. Go speak with founders. How they feel about this because you know, it is pretty unhinged that one person in three days just live streaming. Essentially, I don't know three, four companies of a thousand employees each over six years worth of work that they would have put in in those three companies and got the core features set in three days. This is what we're looking at here folks. But this is when I said the rift is getting massive. And if people are just still sitting there with cursing going, why know? Why know? Know that there are people out there doing laps. They're doing laps on laps right now. And something that Angie and I have actually talked about just on around it over the last year is how like it does feel like it's never been easier to get ahead of everything. If it's quickly as possible, like you can just go, you learn a new technology in this space and then suddenly you're operating a hundred times faster than anyone else around you. But it's also never been easier for everyone else then to catch up and figure it out and get right back to where you are. You know, I mean Ralph has been a thing for, for, you know, six, six months. Seven. Seven. Suddenly everyone wakes up and is like, oh my gosh, I should also be doing this thing. And now suddenly everyone like sort of is. And I hate this phrase because it gets way overplayed. But like a lot of people are saying like, AI won't replace you, someone using AI will replace you. And I'm almost kind of getting the sense out of this that like, you know, gas town isn't going to replace engineers, but engineers who are using gas town or who are building their own gas town. Those are the ones that are going to like replace the other engineers. And so in that, and when you frame it that way, it's like learning how to build a gas town and how to do this Ralph technique. This is actually just the new domain of fundamental skills that engineers need to have. And it's, you know, just like learning a programming language, it's something that you have to, you have to build that skill and refine it. This is the hard, this is the hardest send an agreement. We understand we've got a buff of a new discipline of comp side here. Like it was invented every day, every, every day. If you're not hanging around people who don't see this, then you need to plug yourself into people. Like there's some good communities on Blue Sky, but most of the AI activity for devs is happening on X. Like go plug yourself in and be really curious. So one of the first fundamentals every developer should learn is how to build your first coding agent because a coding agent is your tool. We spend hours and hours and days configuring the OVM and all our dot files, etc. If it's just 300 lines of code, why would you not want to have your own coding harness? Then you could exercise your taste, your discipline, all that high control you used to do on like on code, you can now do it on your printing precip code. So go build your agent because like cursor, windsurf, and all these like harness companies are building coding agents. There's nothing different between them. There's pretty much nothing different between them. It's 300 lines of code allocating array with some tools like read file, read file, edit file, bash tool, and a search tool. The search tool is just executing the bash tool and executing the command ripgrap. That's all they're doing. And they're trying to differentiate themselves as being like like the Gucci or the Louis Vuitton and we do very much or we make software to use her. I'm a wind surf user like correct putting everyone into camps, but you don't have to be in a camp. You don't have to be in a camp. Like honestly, I trust a car mechanic that's rebuild a few carburetors a whole lot more than someone just orders the new partner slaps it on. I want software software engineers that are curious that are being mechanics. They've re-build the carburetor. They understand exactly because once you understand what cursor is doing, you go, you understand the prestige. You realize it's not magic. It's not scary. It's like I'm scared of a wild true loop that we've arrest API. Yeah, you are. And you realize just how dumb that is. And then you go build your own and then you start thinking, well, okay, I'm going to automate workflows in my life. I'm going to automate like a producing of software and then you eventually end up a gas town. So I spent the last year really encouraging people to go build your own agent. I've got a workshop. It's on GitHub. It's free. It takes you 30 minutes. It's unlocking people's brains. Now where that gets interesting is because once you realize the magic trick of AI and why every company is doing AI is because it's just those 300 lines of code with like a prompt on top, QPT wrapper stuff. You realize there's no moats. So this is something that dev should have a conversation with founders and business leaders. What is a moat now? If some person in Sydney is able to basically rip a fart into a voice prompt and like clone huge product features, in companies that would have taken 1,000, 2,000 over 10 years and just not do it at one and do it at many. And if I come into the market, type topics or someone comes into the market, if there's like 10,000 employees or heads to be fed like outgoing expenses and at a single company. And then it's just three children, dudes and barley, like living like kings. And they coming in at a different unit economics. Guess what's going to happen? So we started on this story arc of like AI is going to take your job as a section. No, this is one of my things like some software developers not going to make it. And I framed it really around the idea of employee performance bell curves. Some companies do performance reviews as six months. Some are doing 12 months, high performance, six months. It's very aggressive, fang, etc. And what's happening is you're going to come across fang, etc. And let's say that you're a high performer at fang like last year. This year would you do performance reviews? The high performance is now low performance because the high performance is a gas towning or they built their own gas town. And that's why you won't make it. It's not AI. You just, you won't curious. You didn't invest in yourself. You're asleep at the wheel and the inevitable happened. And business leaders need to actually make adjustments because there's a couple people having a couple people having the time of their lives coming into their market at a cheaper price point. And they're never going to raise money. They've had to raise money. They've got valuations, got stakeholders and investors. This is Clayton, Chrissson, disruptive innovation, textbook. So if you want to be a developer, don't be a waiter, don't be a juror ticket monkey. Be a doctor that diagnoses the problem. So like you want to get yourself as close as possible to a PM or in front of customers and you don't want to be downstream because when you're at figure five agile fractures, at figure eight, you're like, yeah, I'm just going to be on Bali and I've got my loom that's automating software development and I can do anything I like. I just got to like throw some tokens on the care file. And this is the evolution of where software is. We're still engineering. We're still software engineers, but it's critically important to be around people who get it. And I'd like to add the following note. Just because AI is not working in a company does not mean AI does not work. It means the company has a problem with AI because they've got a whole bunch of corporate Dongba. Maybe they're doing have to do a lot of context engineering to try and get it to the right coding standards and patterns. But the reason we had coding standards and patterns was for legibility for humans getting back to the fall humans thing. So I've seen people try into like inward working. There's a notion of working with the grain or against the grain. I see a lot of corporates working against the grain. And then the employees using AI there, they're not using it home and experiencing working with the grain. And my biggest concern is those people don't when someone says, hi, I'm a software developer. If they say AI doesn't work for me, I guess sweet. What identity are coming from? Are you coming from as a software developer where your identity is that you, your dot net developer? Well, because that doesn't matter anymore. Are you coming from that you're coming from like door to your bank? Well, that really doesn't matter anymore. Like if AI is not working at door to bank, that's a door to bank problem. I'm speaking to the developers. Like, are you playing with it at home? Are you engineering and learning the way? Because we've got a year now, we've got model first companies like working with the wood, where they've captured the back pressure. They've engineered ways so Raf can keep on working. Understand there's a completely different mental model on how software should be built now, different unit economics. And if your company doesn't get it, you have a choice. You can either go to a company that gets it. They're plenty out there now. You can go after the opportunity and live like a king in Bali and build your own gas town and just like smash your previous employer. Or you can suffer through a probably three or four year AI transformation program. If any developer remembers when all the essential consultants will run through and we got agile coaches, that's coming, baby. I think it's already here for a lot of people. Yeah, I'm pretty sure that's already like more or less happening a lot of places. Like, I'm just, I have so much I want to follow up on but at the same time we've been chatting out for a bit. So I want to be mindful of time. Jeffrey and this conversation, we've taken a wild tour through loops and into towns, way out in the distance and you're really kind of painted a picture about where this is all going. And that's why we were really excited to tune in today because you know, on Dev Interrupted, we've constantly been following the stuff that you've been talking about, how the moats are gone, how the walls are gone, how people need to be running, hill climbing and building their own routes. And it's just been an amazing opportunity to kind of dig deeper into where you're thinking about all this, especially capitalizing on this amazing zeitgeist of activity happening right now. Post holiday break where everyone's emerging freshly experimented with these tools. Maybe they had put it down years ago and then pick it back up and now they did. Like, there's an elucidation in the air and you can smell it when you talk to people about how they're talking about how they're working and engineering right now. And so we're going to keep having these conversations. You know, you're a friend of the show. We want to continue understanding where this is all going. And I think you're the perfect person to guide us in our audience. And so just, and you know, keep that in mind that we're going to be having you back here in the hot seat very soon. But before we do start the clothes out here, I just want to turn it back to you because everything, all good things are a loop, Jeff. So I'm going to turn it back to you one last time and say, where do you want to leave this on? Where should folks go to go learn more about you and what you're building and where this is, how they can start getting advantage of this themselves. Yeah, sure. My website, ghuntly.com, you'll link it in the show notes. It's all there, it's all free. Just an email address. That's my ask. If you want to pay, you'll get access to some of my ideas, maybe 48 hours early, San Fran crowd likes the notion of alpha. They like to front run and like have the ideas first. So if they want to pay for that, you can pay for it, but you don't have to. You just like put your email and you can see it all. Been publishing for the last year. It's all about the loops now. When I say engineering, you should be engineering feedback loops. So that's all Ralph is, is like forcing the feedback loop back on itself to actually get something to done. And that's all that tool calling was. And it's your job now to actually start looking at data sources that you can engineer to feedback into the loop. So to get the outcomes. Now, if this is all new to you and it's really startling, like that there's people a year ahead and they're doing absurd things. You're like, I can never catch up. That's bullshit. Would you believe if you're watching this year early? Only 10,000 people have installed the Claude code plugin. You're early. There's still time. You're still time. Strap yourself in. Just know that the official Claude code plugin takes you on a path where you where you get compaction, etc. They did really good job with accessibility, but you need to approach this like an engineer. Just go do it. Like build it up step by step, like Kubernetes is a hard way, but like context engineering. I have another video where I, with DexHorti on my YouTube that says why the anthropic plugin isn't it. And maybe if you go look at that as well, it gets into really a detail of context engineering and some other tips. Go check it out and I can't wait to come back. Amazing. Well, thank you again, Jeff. I'm so happy we made it to the end of the call before a compaction event occurred. Even though I think that between our conversation, we definitely filled the whole window with a lot of ideas for people to be digesting. So folks, you know, definitely be processing that we're all going to be coming back in this hot seat and talking about this more soon. 2026 is going to be a fascinating year. We're orchestrators emerge and in you and your team, they're already full of them. So let's take advantage of that opportunity. Jeff, thank you again for coming and we'll see y'all at the next one. (upbeat music)