Steve Yegge's Vibe Coding Manifesto: Why Claude Code Isn't It & What Comes After the IDE

[MUSIC] We are here live at AI Engineers Summit with Steve Yagi, the legendary Steve Yagi of Steve's Tech Talks, Steve's platform's brands, and most recently, Source Graph and App, welcome. And most recently, Vibecoating. >> Yeah, that's right, the Vibecoating book. >> So this is the big Vibecoating discussion. In the pre-chat, we're discussing the intersection of Vibecoating and AI engineering. So we got the kind of movement leaders of both sides here. How do you see it? >> It's absolutely a movement, right? You got to get people behind it. I mean, I said at the end of my talk today that there's a huge backlash, and the backlash is only just brewing now. So you and I are pushing forward on these waves of, AI engineering is about building AI enabled applications and being in AI. And Vibecoating is about abandoning the old ways of producing software and embracing the new ways, right? And both of these are making people pretty mad, right? >> I don't, I think they're mad if their identity is tied to the way that they work today with no changes, no room for changes. >> Yeah, so I'll start with my first hot take. >> Okay, let's go. >> There is a demographic that is the most affected by that. Their identity is the most tied up with the way that they work. >> Okay. >> It's not junior engineers. It's not non-engineers. They're all Vibecoating. It's senior engineers, senior leaders, people who have, so basically you can narrow it down to 12 to 15 years of experience. They hate Vibecoating and they hate AI and they are online going, my 15 years is better than that AI, okay? Now you saw, I don't know if you saw Jordan Hubbard's post from Nvidia where he just laid out some really nice advice on how to get the most out of agents as you're coding. And this guy posted and he's like, yeah, you know, no. You stick with your junior director stuff and leave the programming to programmers, right? When you have 15 years of experience like me, then you're qualified to talk, right? >> Right, so I said something to him like, I think you need to learn to read a clock. And he's like, and until you have 15 years of experience and I'm like, well, you got more experience than him. >> More, I have 45. >> So should I go to 60 before I can talk to you or should I cut out 30 years of experience so I can be as dumb as you, right? Those are my options. And so I don't know, I guess I'll see them in 15 years. >> So, okay, I think there is one element that I'm trying to figure out of, while these people have to coexist, right? And most companies are gonna have a mix. Even OpenAI, by the way, we've talked about this last night at dinner. Guys, OpenAI has people who don't use AI to code. >> They have people who don't use codex, they probably are using cursor or something. >> Okay. >> But they're not using the agentic loops, right? >> Yeah, yeah. >> And yeah, so we talked to Andrew Glover there, the director of DevProd and from what he was saying, they've been planning on going public with this once they have more data about it. And it totally, they're sharing that-- >> Performance. >> The performance difference is like 10X by any way that you measure it. So lines of code, commits, business impact, whatever. And it's so stark and pronounced that the people who aren't adopting it are now 10 times less productive at performance review time. Two people, same title, same job and all of a sudden, one of them is 10 times as productive in the other one. What do you do? And the answer is you panic. You actually go to HR and you go to legal and you're like, what are our options here? Because the time is coming, okay? Here's another hot take, all right? If you're still using an IDE to develop code by January 1st, you're a bad engineer. There's a hot take for you, all right? Now, you still have like five, six weeks to still be an okay engineer while you're using your IDE, but this is the time that you need to drop it and learn how agents code, okay? Because it's a skill set. I mean, it's so complicated, we wrote this book about it. Me and Jean Kim, 'cause we were, you know, we were playing with it ourselves last year and we're blogging about it and talking about it. And every blog post was 30 pages. And it's like, what do you do with 30 page blog posts? That's long even for me, right? >> Yeah. >> And at some point, I was just, man, like the skills that you got to learn in order to get the AI to do the things that everyone's mad because it's doing them, right? Because everybody's like, well, I tried it. I spent two hours with it and all it produced was garbage. And the answer is actually you have to spend 200 hours with it. You have to spend 2000 hours with it. And that's not actually an exaggeration. Jean just pulled up a study that showed that you actually have to spend a year or 2000 hours with AI before you trust it. And what does trust mean? Trust in this case specifically means before you, as a user, can predict what it's going to do. And if it's unpredictable, of course, you're going to be mad. But as soon as you've worked at it with it for a full year to where you fully understand its capabilities and its drawbacks, which haven't really fundamentally changed. It's gotten more capable. But the edges are always the same. It hallucinates, it gets lost, it gets amnesia, dementia, it lies to you, whatever, right? Those skills, we've been building them for years now. Everybody who's been trying to write code with AI. We've been trying. It hasn't really worked, but it's been working better and better and better and better. And now it's reached the point where it's working a lot better than all of the other options. And if you haven't tried it in two months, you're way out of date. The models are much better than two months ago. If you haven't tried it in a year, you're a dinosaur. It's just unbelievable how bad you are. And you may be, look, I have friends who are much better engineers than I am. I mean, world class, maybe some of the best in the whole world have built technologies that you've heard of. And they're not using AI yet, except the occasional, I'll ask Kerser a chat question like Wikipedia, whatever. Okay? Those people are going to be the interns in a year. - You really think so? - Yes. - With all their experience that I have-- - I've had this hypothesis that has not been really confirmed with any anecdotal evidence at all until today, when I met somebody at your conference, that told me about how he had been in this position 12 years of experience, didn't want anything to do with AI. And he met these two PhD students from somewhere in Europe, I forget where. And they were both just super hardcore or vibe coders with the agents, right? And he was watching them work, and they were super junior. And they kind of didn't know what they're doing, but they just had no fear and all the ambition. And all they did was they just kept hammering on the thing going, okay, well, why did you do it that way? Explain it to me. Okay, well, let's look at other options. And they would just be kind of the perfect engineer with no context. The perfect no context engineer, what questions are they going to ask? Have you thought about scaling? Have you thought about security? How is your test coverage, right? I mean, engineers are going to all ask the same questions, right? And he realized that engineer in a box is not too far off from knowing the right questions to ask an LLM. And that these two students were so productive with it, he was blown away, that he was like, oh no. Like that's when the right, the right, the right, but one of the reasons I have to learn this, and now he's been doing it ever since, right? But it ain't easy. I, you're not going to pick up cloud code and you're not going to just try it and be like, it's just going to work for, it might, you might get lucky, but eventually if you don't have the right mindset, if you don't have the right attitude going in, now even with the right attitude, how often do you swear it's worn at your agents in the last two days with the actual F word? Or like, right? - I'm pretty polite, I say thank you and please. - I say thank you and please. I'm like, what did you do that, right? And it's because it's because Jean and I realized this after we published the book. You have this helper, they're very human-like. They come in, you have to tell them a lot of stuff, and they, they, they need a lot of guidance, but over time, they need less guidance. Your prompts get shorter, things get streamlined. They seem to get it, they're working. Now, if this were a human being, you would draw the conclusion it's because they understand you and they get you and they're finally part of the freaking team. Do not make that mistake with LLM's. Never make the mistake of anthropomorphizing in LLM, like Larry Ellison, right? The LLM at any moment can stab you in the back, okay? It can just be like, yeah, we took care of that really hard problem. Now I'm going to delete your database, and you're just like, no, right? And it's because of that, it's weak, we call it the hot hand. You sort of like, you're like, it's going, man, I'm feeling good, this thing gets me. I'm going to make it do a production change. And that's how I found out about this. And it's like, I was like, my script can't access prod. And so it shows to do it in the worst imaginable way. What it did was lock out the entire rest of the universe and Google, including my live game, and everything else, and only allowed my script to access prod. And it was changing password, it changed the password. And I was like, why did you change my password? And it's like, oh, it's so sorry, I definitely shouldn't have done that. What, what, no shit? Okay, and I'm just like, right? This is what will happen to you if you just, you just try to do agent coding, okay? Bad things will happen. This is what our book is about, really, right? Well, I mean, that's not the best ad because then what, like, you learn, and then eventually you learn how the speed bumps and the corners and everything, it's like driving, right? It's like driving. Like, you want to become like a NASCAR driver. Like, this is high performance stuff. You're coding with 12 agents at a time, and you're more ambitious than you've ever been. I was talking to a guy today who's got, got way more projects going than I've got. I don't know where he gets all the time from, but he's probably doing 10 or 12, like, major projects at the same time right now. And he's just doing it all with the gentle coding, you know? So I mean, like, man, the ad here is that, you will turn into Batman, but you can't just grab the suit and put it on and be like, I'm Batman. You're just a cosplayer. You're cosplaying at vibe coding. You got to learn how the tool belt works. And that's going to be pain, suffering, and mistakes, and learnings. Now, you can get a lot of it by reading this and all of the other vibe coding books, read the O'Reilly one, watch the talk. I mean, seriously, like, you should like get all of the possible angles at it because it seems to land differently for different people. There'll be some analogy where you finally get it. You know, I get it. It's like this. And it's like a 3D printer. And nobody else thought it was like a 3D printer, but somehow that was the magic that made it for you, right? - Yeah. - I would say one of the biggest surprises from the dinner yesterday was how many people all have the experience where they no longer write single lines of code. Like, they're really just kind of prompting and doing-- - I-- - Going about that. - Single lines of code, you mean they were never writing any code at all? - They might edit. But like, I think when they're writing that new, they'll always start with the prompts. - No editing, no touch. - I know editing. - It is very expensive when you're like, that identifier is misspelled and it's a local, you know. You could just add it, but it's better for you to close your IDE and probably uninstall it. - No, actually that's not true. Somebody finally convinced me that IDE's are fantastic IntelliJ in particular. Keep it open, it's a great old build. And actually not for the LSP, although you can use it for that. Actually that's another good way to use the LLM if you get an MCP server. But no, it's that IntelliJ's auto indexing is so much faster in incremental rebuild, so much faster this way. - Yeah, from last night. - Yeah. So all you do is leave IntelliJ running, but you shouldn't look in it. It's a tool for the AI now, right? - Amazing. One other thing that is a big part of the Hotties you're saying is that Cloud Code is not it. - Cloud Code ain't it. - Explain yourself. - All right. - That's one here loves Cloud Code. - Everyone here loves Cloud Code. Or AMP if you use our product. Or it just is just recently leapfrogged Cloud Code again because of Gemini 3. AMP has this cool feature where it goes to another model. - Just a free warm you. I also want to talk about just Google in general and how this Gemini revolution has kind of changed Google's image. But let's talk about Cloud Code. - Sure. Cloud Code has been around since March. Cloud Code has been proven to work. And so, but yet probably 80% of the world's 90% of the world's programmers are not using it or anything like it. You get certain companies where it's really taken off, but most aren't. The world is stuck on cursor. The world is stuck in 2024. Last year we were trying to get people to write with chat, right? And they were like, "No, completions." They were like, "Oh God, no, but it can generate the code. You just got to piece it in and you just got to do all this stuff." And they were like, "That sounds kind of hard." And we're like, "But it's faster." And they wouldn't do it. And then nine months later, it finally percolated it. And now they're like, "I like cursor." And it's like, "That's so last year, dude." Right? Like, wake up. And yet, they haven't adopted it. And so you have to, at this point, look at it and say, "Why haven't they adopted it?" Let's go look at the reasons. And the answer is, it's too hard. It's too hard. You have to be able to read. Man, most engineers, honestly, to them, five paragraphs is an essay, okay? And with Cloud Code, you've got to read waterfalls of not just information, but also code and diffs, right? Because if you're going to put your IDE away, you actually do have to look at the diffs. Now, I'm going to tell you that once you get some expertise at this, you can actually tell from the shape of the diffs and the color of the diffs and the length of the diffs. - Survive. You can tell whether it needs a code review, whether they're doing the wrong thing, whether they seem to be rewarding suspiciously too much code for this problem, right? The diffs alone, just the shape of the diffs can tell you a lot about what's going on without actually reading the code. But you should pay attention to them. Otherwise, you'll have problems that will only crop up later, right? But yeah, I mean, like put the IDE away, okay, Cloud Code, and then get Cloud Code out and try to start using it, all right? And you're going to find that it's, look, I've been using Cloud Code, honestly, 10 to 12 hours a day, literally, for months and months and months and months, and I still curse it out all the time. I just lose my mind. I'm like, how could you have done that when you just set, right? And it's like, it's actually been shown. It's starting to be shown that sometimes when you put a little pressure on them, they perform better. You can break through your log jams that way. But anyway, look, you're going to run into problems, but the thing is, next year, the tools will be better, okay? If Cloud Code's not it, what is it? Well, we got to get back to something like an IDE, right? I mean, that's just going to be, it's got to be natural for people. You got to be able to look at it and see what's going on. Not have to read. It's got to have visual indicators, right? And yet, it's not going to be an IDE because an IDE is very much focused on helping you write code, and that's not what you do anymore, right? So what it's going to be is it's going to be your agent orchestration dashboard. It's going to walk in in the morning and be like, yo, so how's it going to do, right? I'm like, oh, that one's still running. That one's running a tool. That one needs my input. Okay, right? You just go through the list. And so I'm building one. You can go look, I'm supposed to be a private repo, but it's public. So I've got forks and shit happens, but whatever you can play with it, it's called VC VibeCoder. It's my V2 of the VibeCoder system. And what it does is it creates a set of canned workflows that run the agents for you, right? Yeah, I don't know if you saw an anti-gravity from Google the other day, which I saw two days ago. So it's so fun. How much stuff people are inventing that are all? For age of error, I call it a march. With Revenge of the Juner Developer, I did that chart and everything, and like Daria quotes it and all this custom advisory boards and everything, right? Really? Yeah, yeah. No, it was it was really pretty impactful. And I called that what's going to happen is the agents, I even back in March, I knew they were too hard. I was like, what's going to happen is they're, you can run them programmatically and 90% of the crap that you do with them could be handled by a model, often a cheaper model, right? If it's just like, if it's asking you which of these two things should I do next, three equally important, like just have Haiku say either one, right? So like I called the orchestrators are coming and it's taken close until like the end of the year to get there, which is roughly where I predicted them coming. Replet agent three, there's a bunch, there's there's conductor, there's a DMAD came out open source. They're all different, you know, takes on it, right? And but there will be more coming. I guess Google's as well, right? Yes. I like this analogy that they have, it's still pretty or so. Who knows what the eventual vision is, is that you just get notifications from your agents as they're working. Exactly. Yeah. So in mind in VC, there's an activity feed. That was one of the first features I added, which is like, I wanted to go work and I just want to get notifications periodically of interesting stuff. Interesting. I wonder if they'll have like social networks of agents. Well, so the agents do each other following each other. Well, so I just had three hour coffee with Jeffrey Emanuel, who's, he did the MCP agent mail. Just one of the smartest people I've ever met in my life. He's the one that wrote the article that crashed the stark market about Invidia. That Jeffrey Emanuel, the way an incredibly well written article that said, this is why it's a bubble and the whole market went from Carpati started following it's back up. He wrote what you just said, he said it is back up, but he wrote agent mail, which is he was just tired of having to copy stuff between his agents. Like, you tell me what to tell this agent. And so he made a little, little like, I don't know, HV server that's like an inbox for them, a messaging and they talk to each other now. And now he goes coordinate amongst yourselves to paralyze this task, this epic that I just put together, whatever, and they'll do it. Some people are coming at it top down and trying to build orchestrators that you do it all for you, but interestingly with beads, right, which the issue tracker session thing that I made. Plus his purely vibe coded by real, yes, purely vibe coded. Yes, so I mean, like I get PRs every day for horrible problems that I introduced, but nobody seems to mind because we've got stable versions now. So beads is like living proof that you never actually have to look at the code as long as you and other people are asking the right questions and having the AI look at the code. I get PRs from people all the time, where it's obvious that the AI did all of the analysis and all of the coding. And I look at it and sometimes I'll just be like, so my AI, what do you think of their AI is PR, right? And you saw summarization. I mean, isn't that bad though you want? It's bad if your code, if it look, it's all about the outcome. Vades is working and it's got tens of thousands of very happy people use it. So obviously it's not bad. I mean, one of the few things out there, yeah, if you do this to your company's production website and bring it down, then yeah, it's bad. But still, beads is kind of a database, you know, and database is one of the harder things to make. You know, beads is really weird. The architecture is really weird. And the only reason it works is because it wouldn't have worked in the old days. It would have been just too hard to manage and not programmatically. But what you do is you tell the AI, go fix it all up. And whenever it's corrupted or there's a merge conflict, or just fix it. And it's funny because Jeffrey manual who did the mail basically did the same thing. He has all his agents run in the same directory and they do file reservations. They're like, I need that file. I used to do that Accenture in the 90s, right? I'd run over to a dude's cubicle and be like, I need that file. Their revision control was so bad. So like he's got a file reservation system going. But what happened was as soon as he put it in place, his agents just started working. And now he's got this little village of agents, right? And that's where we're headed. So the orchestrators are going to be about not keeping the agent on the rails, but keeping all of your agents on the rails and communicating with each other. And then you hit the wall, boom, is anybody know what the wall is? Once you get past all this, merge, merging is the, it's the wall that everyone is hitting right now. Yeah. I think the company that's best poised to solve it is graphite. I was going to go talk to him about it. They'll be happy to talk to you. Yeah. I think everybody needs to solve it. And if you're at an enterprise, like what we hear, because Gene Kim and I talked, we talked to companies all of it. I'm a SaaS seller, so we're in a source graph. So we get to hear the inside story from all these big companies, right? And they're saying, yeah, as soon as you get to the point where like every developer is 10 times as productive, merging their code becomes this incredibly complicated problem. Because you and I work at the same time for two or three hours. We make, you know, 30,000 line change. Each mind makes it in first thought and it gets merged. And then you come along. And I have literally changed our logging system and our architecture here at APIs that you are using. Yeah. And so it's not going to be as simple. It's not as simple as let's fix a merge conflicts. It's like, you're going to have to re-envision and reimagine and re-implement your change on my change or a rip yours out or it might not make me do it. But ultimately, ours are just the AIs doing it, right? But the important thing is that they have to be serialized. It is a queue. And when they go in there, they have to actually like basically redo what they were doing on top of the new thing. This is already has solved this and it is a huge obstacle right now. So one company did, sorry, last thing. One company said, here's our solution, one engineer per repo. Not making that up. It's a solution. It's a solution for now. The classic solution for this is stack diffs, right? Merge queue stack diffs that- I don't know about stack diffs, so I guess I'm dumb. Well, it's like a Facebook concept that they're trying to bring into the white roles. GitHub is working at it. I just talked to Jared Palmer there. Basically, I'm hearing no solution yet, but you should be aware of it and design around it. Yeah. I mean, there's the old fashioned way of just hammering through it really hard and- Well, also, you know, you could just talk to the other guy and say, like, hey, I'm doing this, you know, pretty deep architectural change. Let me go first and let's agree on the overall pattern first. So yeah, I mean, I've run into this situation a few times where I've actually tried to give this agent the heads up that this one's making you change to the effects this one. With the male thing that Jeffrey did, I think once I get it wired up, because he doesn't use work trees and I'm going to this, but once they can actually talk to each other, I think it's going to be as simple as just keep in mind that that agent's working on something that affects you. You might want to go talk to them about it. Yeah. And agree on an overall, like, fundamental effort. And they're quite good at it, right? They just- Yeah. Well, it's because they have no ego. They're not like, oh, it's got to be me, right? So just whoever's first gets to be a leader. Great. What do you and him disagree on? Me and who? Jeffrey. Emmanuel, the guy that I just met. Yeah. So we foundationally, fundamentally disagree that having 12 agents work in a single repo clone is a good idea. Saying you're on the pro side. I'm on the pro lots of, like, either get work trees with lots of branches or separate repo clones. I would imagine. He eats them sandboxes. He's in favor. He's got them all in the same- They're all- They're literally- they're using the same get, the same build. So one of them will be like doing a build, like, need to re-intest- That's so much churn. Yeah, but he has a file reservation system. So the funny thing is, OK, I was like, this is insanity and he's talking me into at least acknowledging that it probably works pretty well if you're a solo dev and you're using no more than a dozen or 20 agents, because it is actually working for him and he uses the same principle that beads does, which is it wouldn't work in the old days. It doesn't make any sense to a real engineer. And yet, you tell the AI, if anything gets messed up, just fix it. And they will. And so that's right. That's why his thing works. Because every once in a while, the file reservation gets screwed up and they're like, hey, we need to resolve this and they figure it out. Interesting. Yeah. Yeah. Yeah. Some people have proposed that the theme of this conference next year is on multi-agents. Oh, yeah. I mean, yeah. Of course. Yeah, yeah. I mean, AI will be about multi-agent. Look, we're in this phase still where we're cutting down corn with sites with our hands. That's what a real programmer does these days. We're moving next year. It's very clear. We're moving to, you know, these machines that turn, you know, these giant, just like those ones that you see on the farms today, factory farms, we're going to be factory farming coat. Okay. And that absolutely like a lot of people are just so dead set against that philosophically morally, ethically, whatever. They're just like. They're so used to the subsistence agriculture that we're not, we're not used to like the big. They want to be John Gears. But we are, we are actually moving into the John Deere era of coding. That's amazing. Yeah, but that's funny. We didn't know as you actually. And I just thought of it too. We'll have to reuse it. Yeah. And then it's growing on me. It's the whole, it's this idea that cloud code and AMP and code X, you know, client, we love them all. Equally, they're all equally bad. I said in my talk today, they're like, they're like a power saw or a power drill, a skill craftsman can do a lot of good with them. And then you can also cut your foot off with them. The same thing is true of cloud code. But imagine a big machine, a big farming machine that knows how to run cloud code and scrub it. It's like, it's like, okay, you plan, you implement, you review, you test, right? He split it all up. And now you guys self factory farming, right? It works. People are building it. It's going to happen. And what it's going to do is it's already started to unlock programming for non programmers. And this is completely turning companies upside down. They're starting to realize that maybe the ideal time team size is like two or three. And I mean, like, right, the whole way that companies are run, the whole governance structure is going to change because now coding is no longer the bottleneck. The business needs to get immediately involved. The speed black back loops get faster and it's really exciting times. But it's too much for a lot of people and they just, they're like checking out or they're revolting online. And I predict that as this capabilities improve and as we get closer and closer to the factory farming of code, we will see a massive backlash from the leadites. You are the one a few people can ask this as a, I know a lot of people on our audience are critical of going for the full hog with this. Yes. So a lot of like, they're like fine for front end, fine for application code, but don't touch my cloud, infra, don't touch my back in my distributed microservices. They really don't touch anything production, only touch code, only use these things when Git is your backstop for starters. Okay. So keep proud out. It's going to be real tempting to write, but don't. If you have Git as your backstop, why should you be worried? People accept, I guess, people have the perception that it is less good at back end code. Oh, this is the problem where everybody's bad at math. Okay. So how good was ShadGPT 3.5 at systems code, pretty bad. How long ago was that? Okay. People think, people think the, honestly, I believe that the misunderstanding here is rooted in a fundamental belief that the models are done getting smarter. Right. And the funny thing is they could be done getting smarter. They're not, but they could be, and we would still be over the hump where we've discovered electricity, and now we need to harness it. We will still get to factory farming code with today's models capabilities, and we'll get there fast. We'll get there by summer. But the models are getting smarter so fast. It's really, there's this interesting tension of, you know, like, you're building tools for capabilities that the models will eventually have built into their brains. And so you won't need that capability in the tool anymore. And so this is constant arms race and decay of your tool, filling gaps with the model until the model's good enough to fill it itself, and then your tool moves on. Yeah, that's right. I mean, all the road is becoming, all code and all tools are becoming throwaway. Yeah. Which is great because they're easier to build too. Yeah. By the way, yes. So, I remember Joel Spolski, one of the greatest, you know, of our generation, our time on the greatest riders and thinkers. He gave the best tech talk I've ever seen, and I want to get him to come and revive it. He gave it it Amazon 20 years ago. He's still relevant today. He's invited here? Great. So Joel Spolski, a long time ago, wrote something that was timeless until today. So it was 20 years timeless, which was-- Never rewrite your code. Never rewrite your code. And now, we've discovered that it is for a larger and larger and larger class of piece of bodies of code, it is better to just start over and rewrite it from scratch than it is to try to fix it. The LLM will do a better job. I first noticed this when I was trying to port all of my unit tests from one architecture to another, and eventually I was just like, oh, just the iteration because they're trying to fix. So there's a lot to keep in. But instead, if you say, for all the tests out and make them again, it just goes, and you're done. And so it's like, hmm, hmm, well, what about this library? I got to refactor. And so it's creeping up, but we're moving into a world where the fastest thing to do is just build new code that does a better job of what the old code was trying to do. Yeah. I mean, it's like we're unlearning everything. I feel like an upside-down land. But this is-- but it's like we've entered quantum mechanics, but you have to embrace this new world. I love the energy and the credibility that you bring, because a young kid could say what you're saying and not be as believable. But you're coming from a perspective of you've been a huge-- I've been-- Systems, you've been a game programmer. You've been everything. Yeah. I've done assembly language for five years, you know? Yeah. Operating systems in assembly language. And it was 8080, 8086, not even if 80X86, kind of, eight-bit registers. I've done it all. And, you know, the game programming teaches you everything. Yeah. And then, of course, I've done platforms, Google, and ads, and this, man. And I know the agentsic loop and the game programming loops share a lot in common. They do. So sharing a job-reading system loop, I feel like I'm building the same systems over and over again now. Yeah. There's only-- we're cursed to reinvent the same designs in every new domain. It's a privilege, too, you know? One thing I wanted to get you to come in on is Google. Ah, Google. One of my favorite memories, which is just like just before you retired, was talking about how Google still doesn't get it at Google Cloud, in particular, how they shut down the deprecation policy. The deprecation policy. I was still mad about that. You got to get me pretty mad to write a blog. You seen? Have they turned it around? No. I talked to people there, and a lot of them were like, yeah, that's not a thing for Google. And it's funny, because Amazon, Amazon, not on the platform, not on the deprecation stuff, not on the important stuff. Google has turned it around on execution. Yeah. They finally did the thing that they should have done, you know, 15 years ago, which is whole people accountable, and it's not just engineers do whatever they want all the time, which is what it was for 20 years. It actually worked pretty well because they had amenoply on ads, and they get afforded to subsidize Google engineers doing whatever they wanted for. But, you know, ultimately they had to do the right thing and grow up and mature as an organization who was painful, and they lost some Google culture, and it's not as fun anymore, but they now execute well, and they did the right thing for the company. And now with Gemini, you can see now they've been shifting their focus gradually towards more AI/AI, and now it's starting to pay off for them. Yeah. And maybe they're going to be the big, big winners. Do you have observations of a similar kind with all the other labs, you know? I'm just kind of curious, and your takes on one of my favorite charts is that old chart where you had Microsoft, like all pointing guns at each other, Facebook, everyone's agreeing. The first person to ask me this, I remember that chart, that was funny. Yeah, it's just like someone could do that for OpenAI and-- They could, they could. You know, it's an interesting question. All three of those companies, Google, Anthropic, and OpenAI are an unbelievably chaotic internally right now. Yeah. Chaos. Okay? Anthropic hides it really well. They seem-- They seem like they've got their apps together, so what that means is their product managers formed a wall around that chaos and Bravo Anthropic product managers. But it is-- and it's not because Anthropic screwing up, it's because it's an inevitable function of growing that fast. They're hiring like 100 plus people for cloud code in the next, I don't know, month. I mean, like, they're going wild, and that's just cloud code. You're not going to-- I mean, I was at Google and Amazon when they were in the big fast phases, and you're just going to have chaos. You're going to have churn. Nobody knows who to talk to. What? And everything's crazy. Eventually, it starts to smooth out, settle out, and they'll get there, right? And AI is chaotic more like in a-- well, they had a lot of exits, right? You know? I don't know if there's chaotic as they GitHub, who lost most of their senior leadership and was just complete term oil for years, but they're pretty chaotic at OpenAI, right? And then Google, you know, we were just talking to somebody today that was saying it was still too hard to like get consensus across groups with the Jewels team. Yeah. They can't get it rolled out internally because Google is so siloed, it's a billion monoliths, right? There's a little little apps that don't talk to each other, it's hard to roll anything out across Google. So all three of them have execution problems right now. I think Anthropics is probably executing a little bit better than the other two, but it's a real close race. And yeah, it would be interesting to see and see if Oracle or Facebook or any of the others can catch up, right? Meta. Facebook will be the most interesting thing. I mean, they'll have to do something huge next year. Next year could be the year of open source models. Yeah? If well. So look, as soon as open source models get to the point where there is good as clouds on a 37 was, then you turn on client or something, and you've got something that as good as cloud code was in March, which wasn't as good as today, and it's not good, but it's good enough, and you're running it for free, free, free, on your local M4 or whatever, right? So yeah, from what I've heard, they're seven months behind and that gap is gradually narrowing the frontier models, which means OSS models will be as good as Gemini 3 next summer. Right. Yeah, but next year it could very much be the year. That means the tools are going to have to get much, much better at decomposing the test and assigning them to the right model, the right size of model for cost optimization. I'll represent the critical side, which is that the reason they're converging is because they're saturating, right? There's only, you can only ever hit 100, and the closer you get to 100, proportionally it'll just get harder and harder, right? So obviously, the rate of change when you're lower down is higher as compared to when you're already saturating, but that's a minor technical point. Well, no, I mean, it's not minor at all. It's actually a foundational question, which is, is the line of AI intelligence going to go straight, or is it going exponentially, or is it actually starting to pee? Yes, I'm talking about that. Yeah. And, you know, from what we've heard, from people who are very, very close to the research, we know that AI has been getting, what is it, four times smarter every 18 months for the last, I don't know, 30 years because of Moore's Law, and they think that there's enough data left, training data for two more cycles of that before they don't know what happens. Yeah. Maybe it goes out more, maybe it goes down. We don't know. Human history ends. But two more cycles means they're going to be 16 times smarter in three years, right? So, I don't even know what that means. Well, I've spent a long time trying to figure out what it means, but what it means is they're going to be really, really, really smart, and it's going to change the world, probably in a lot of good ways and a lot of bad ways. And, yeah. I don't know if you have this version of this conversation. People ask me if their kids should learn a code because they should learn to vibe code. You, like, you have the escape hatch of, you can read the code if you want to. You don't just don't need to, or most of the time, but you can, and it's a good guard. Right. But I don't because you don't have to. Well, I think my take is whatever it is, you'll be better off if you do also know how to code because you can prompt better, right? Because you can tell, you can communicate, or precise terms. Look, when I see you say you know how to code, not the syntax and stuff, but you have to know, like, in a language neutral way, what the capabilities of languages are, functions and classes and objects and, I don't know, monads, whatever it is, the whole superset. You should be aware of them. And then from there up, so you've, you've cut off all the syntax. You don't care how to write it anymore, but you care how it works. So you've sort of reached the level of how a product manager thinks about things, architect surely, right? And you need to be that product manager. And now you're starting to move your concerns up up. And you need to know all the engineering stuff. And Jeffrey, I'm annual, like I was talking about, he's a mathematician, self-taught engineer, he doesn't. But he's learned all the right concepts, you know, you know, Cloudflare does this and Apache Cassandra does that. Yeah, that is still theoretical. Yeah. That is a go away. You still need to learn all that, right? And so just because you don't have to write code anymore, it doesn't mean you have to, you still have to learn a massive amount of stuff to be an effective engineer in the new world. Because that's the level that you're interacting with them at. Amazing. So this has been a great overview. I don't know if you have any other sort of ransom you that you want to get out there. I'll leave you before. I feel like the gossip rate has gone up, like not gossip, but the rate of exciting announcements by engineers who have discovered new things about how to be more productive with agents. Like for example, I just found out today, not this, I was, I found out today about, it's called code MCP or something like that, where you, instead of calling, it's pretty popular project. The agents can't call MCP very effectively because they don't have any training on tool calls. They don't have any training on writing code, so you tell them, don't call the tool, write code to call the tool and they do way better with it, right? So it's like it's all these little learnings that we're finding, right? It's crazy. It's crazy to end-thropic. The creators of MCP found this. Did they? Yeah. Well, hopefully they found it first, but then the end-thropic was like, yeah, you guys are right. Yeah, wow. That's a really easy. So I think that's why I love focusing on the AI engineer because my argument is the AI engineer can uniquely take advantage of elements way better than everyone else. That's true. Oh, much more fun. You could almost define an AI engineer as somebody who's master de la lambs. Yeah. Yeah. Not from training, but from using. You're using it. Yeah, yeah, yeah, yeah. I think it's one of these like, disruptor strategies where like, it's low status. It's high status to be a researcher. It's high status to train models. You don't get any respect if you're a GPT rapper, but like, you're starting to be more productive and like actually develop sincere expertise in the same way that I think like F1 car drivers don't know how to build an F1 car, but they know, they'll tell you everything about driving it to the. And they may know, they, in a sense, they make them more about operating it than the people who build it. And so they have to have that conversation. Right? Yeah. Although, although if you watch the, I think the F1 movie, you get a little sense of it. Oh, and they make all the movies. That's what you said. Yeah. That's good point. It's flip-flopped. Lovely. Well, thanks so much for coming on. It's a huge admirer of your work. Your energy is very infectious, and I hope you keep doing Steve's tech talks. I'll start a movie again, man. I mean, this energy is because of the AI, and it's because of live coding, it's addictive and tech is fun again. Just take off. It's boring for a little bit. I know. I know. Yeah. For a while, it was like, well, a source graph, like index your code base, like really, really well, you know. And it's like so, so fast. And I'm like, wow, that's cool. But you know what's cooler? It's not. Yeah. Cool. All right. This has been fun. (upbeat music)