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

We are here live at AI Engineer Summit with Steve Yegge, the legendary Steve Yegge of Stevie's Tech Talks, Stevie's Platforms Rants, and most recently Sourcegraph and AMP. Welcome. And most recently Vibe Coding, I should-

Yeah, that's right, The Vibe Coding Book.

Uh, so this is the big Vibe Coding discussion. In the pre-chat, we were discussing the intersection of Vibe Coding 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 gotta get people behind it. I mean, there's a... Uh, I, 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, right, on, on these waves of...

You know, AI engineering is about, is about building AI-enabled applications and being, being in AI, and Vibe Coding is about abandoning the old ways of producing software and embracing the new ways, right? And both of these, uh, are making people pretty mad, right?

I don't... I, 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, huh?

Okay. Let's go.

So 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 Vibe Coding. It's senior engineers, senior leaders, uh, people who have... So basically you can dr- you can narrow it down to 12 to 15 years of experience. They hate Vibe Coding, 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, you stick with your doing your director stuff and leave the programming to programmers, right? When you have 15 years of experience like me, then-

Then you're qualified to talk

... you can talk to me," right?

Yeah.

Right? So I said something to him like, "I think you need to learn to read a clock." And he's like, "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, like, go to 60 before I can talk to you, or should I, like, cut out 30 years of experience so I can be as dumb as you," right? Those are my options.

And, uh, so I don't know. I guess I'll see him in 15 years.

I, I... So, okay, I think there's one element that I'm trying to figure out of while these people have to coexist, right, a- and most companies are gonna have a mix, even OpenAI, by the way, like we 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, uh, Codex. They probably are using Cursor or something.

Okay.

But they're not using the agentic loops, right?

Yeah, yeah.

And, uh, yeah, it's, uh... So you know, we talked to, you know, uh, Andrew Glover there, you know, the director of Dev Prod, and, uh, from what he was saying, they've been planning on going public with this once they have more data about it.

Yeah.

Anecdotally, they're sharing that, uh -

The performance, yeah

... the performance difference is like 10X by any way that you measure it, so lines of code, commits, business impact, whatever. And it's, 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 than 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-

January 1st

... you're a bad engineer. Mm. There's a, there's a hot take for you, right? Now, you still have a, what, five, six weeks to, 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-

Yeah

... me and Gene Kim, 'cause we were, you know, we were playing with it ourselves last year and blogging about it and talking about it, and every blog post was 30 pages. And it's like, what are you gonna do with a 30-page blog post?

That's long even for me, right?

Yeah.

And at some point I was just, m- man, like the skills that you gotta learn in order to get the AI to do the things that everyone's mad because it's doing them, right? Because everybody's, 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 2,000 hours with it. And that's not actually an exaggeration. Gene just pulled up a study that showed that you actually have to spend a year, or 2,000 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 gonna 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.

Yeah.

Yeah.

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, uh, and you know, you may be... Look, I have friends who are much better engineers than I am, okay? M- I mean, world-class, maybe some of the best in the whole world, okay? Have built technologies that you've heard of, and they're not using AI yet, except the occasional I'll ask Cursor a chat question like Wikipedia, whatever, okay?

Those people are gonna be the interns in a year.

You really think so?

Yeah

With all the experience that you have.

So I've had this hypothesis that has not been really confirmed with any, 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 VibeCoders, you know, with, with the, the agents, right?

And he was watching them work, and they were super junior, and they kind of didn't know what they were 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, let's, 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 light bulb went on. He said, "I have to learn this." And now he's been doing it ever since, right? But it ain't easy. I, I... Y- you're not going to pick up Claude Code and you're not, 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 have you swear, sworn 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, and then I go, "Why the did you do that?" Right? And it's g- it's because, it's because Gene 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 LLMs. Never make the mistake of anthropomorphizing an LLM, like El- 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. Wah." And you're just like, "Wah." No, right?

And, and it's because of that, it's... We, we call it the hot hand. You, you sort of like... You're like, "It's going, man. I'm feeling good. I'm feel... This thing gets me. I'm going to make it do a production change."

And that's, that's how I found out about this, and it's like, I was like, "My script can't access prod." And so it chose to do it in the worst imaginable way. What it did was lock out the entire rest of the universe, 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?" Right?

Yeah.

And it's like, "Oh, I'm so sorry. I, I definitely shouldn't have done that." Well, what did it-

No shit.

Okay. And I'm just, "Oh." Right? This is what will happen to you if you just, you just try to do agentic 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, you, you, 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, 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'm- 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, with agentic coding, you know?

So I mean, like, man, the, the, the, 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.

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 will be some analogy where you finally get it, and you're like, "I get it.

It's like this, and, and, 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.

And-

I would say one of the biggest surprises from the dinner yesterday was how many people all had the experience where they no longer write single lines of code. Like, they, they were really just kind of prompting and, and doing-

I-

... going by that

... single lines of code? You mean they never write any code at all?

They might edit, but, like, I think when they're writing net new, they always start with the prompts.

No editing, no touch. I mean-

No editing

... it is, it is very expensive when you're like, that, that identifier is misspelled, and it's a local. You know?

Yeah.

You could just edit 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 IDEs are fantastic, IntelliJ in particular. Keep it open if you have a Gradle build.

LSP, yeah.

And, uh, 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, an MCP server. But no, it's that IntelliJ's auto-indexing is so much faster, and incremental rebuild is so much faster than Gradle.

This is the guy from last night, yeah.

Yeah.

Yeah.

So you... All, 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 some, some of the hot takes you were saying, you said Claude Code is not it.

Claude Code ain't it.

Explain yourself.

All right. Look-

Everyone here loves Claude Code.

Everyone here loves Claude Code, or, or Amp if you use our product-

Or Amp

... which is, uh, is just recently leapfrogged Claude Code again because of Gemini 3. Amp has this cool feature where it goes to another model.

Oh. And just to pre-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 Claude Code.

Sure. Claude Code's been around since March. Claude 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, you get certain companies where it's really taken off, you know, but, uh, but most aren't.

The world is stuck on Cursor. The word- world is stuck in 2024. Last year, we were trying to get people to write with chat, right? And we were like, "We're telling..." And they were like, "No, completions." And we were like, "Oh, God, no, but it can generate the code.

And you just gotta paste it in, and you just gotta do all this stuff." And they were like, "That sounds kinda hard." And we're like, "But it's faster." And they, they wouldn't do it. And then nine months later, it finally percolated in, and now they're all 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, like, to them, five paragraphs is an essay. Okay? And with Claude Code, you've gotta read waterfalls of not just information, but also code and diffs, right?

Because if you're gonna put your IDE away, you actually do have to look at the diffs. Now, I'm gonna 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-

The vibe

... you can tell whether it needs a code review, whether they're doing the wrong thing, whether they seem to be writing 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, uh, uh, uh, put the IDE away. Uh, okay, Claude Code, and then get Claude Code out and try to start using it, all right?

And you're gonna find that it's... Look, I've been using Claude Code, honestly, 10 to 12 hours a day, literally, uh, for, 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 said..." Right? And it's like, ha, act- it's actually been shown, it's, it's starting to be shown that sometimes when you put a little pressure on them, they perform better.

Yes.

You can break through log jams that way. But anyway, look, you're gonna run into problems and, and... But the thing is, next year the tools will be better, okay? If Claude Code's not it, what is it? Well, we gotta get back to something like an IDE, right?

I mean, that's just gonna be... It's gotta be natural for people. You gotta be able to look at it and see what's going on, not have to read. It's gotta have visual indicators, right? And, 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 gonna be your agent orchestration dashboard. It's... You're gonna walk in in the morning and be like, "Yo, so how did my-

How's it going?

... agents do?" Right?

Yeah.

It's 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... It's supposed to be a private repo, but it's public, so I've got forks and shit.

Um, 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, uh, scanned workflows that run the agents for you. Um-

Yeah. I don't know if you saw Antigravity from Google the other day, uh, which was two days ago, so, um, it's-

It's so fun how much stuff people are inventing that are all around-

They're agent aggregators

... periphery. Yeah, yeah. No, so look, I called this... I don't know. I called it in March. With Revenge of the Junior Developer-

Oh

... I did that chart and everything, and, like, uh, Dario quotes it in all his customer advisory boards and everything, right?

Really?

Yeah, yeah. No, it was, it, it was really pretty impactful. And, and I called that what's gonna happen is the, that agents... I even back in March I knew they were too hard. I was like, what's gonna happen is they're ru- 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 that are 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. Replit, Agent 3, uh, there's a bunch.

There's the Conductor. There's, uh, DMard came out open source. They're all different, you know, takes on it, right? And, uh, but there, there will be more coming. Uh, I guess, uh, Google's as well, right?

Yes. I like this analogy that they have. It's still pretty new, so who knows what the e- eventual vision is, is that you just get notifications from your agents as they're working.

Exactly, yeah. So in mine, in VC, there's an activity feed. That was one of the first features I added, which is, like, I want it to go work, and I just want to get notifications periodically of interesting stuff.

Interesting. I wonder if it'll have, like, social networks of agents-

Well, so the agent really-

... where they're, like, yelling at each other, following each other.

Well, so I just had three-hour c- c- coffee, uh, uh, with, uh, Jeffrey Emmanuel, who's, who's... He did the MCP Agent Mail. He's one of the smartest people I've ever met in my life.

Really?

He's the one that wrote the article that crashed the stock market about Nvidia.

Oh.

That Jeffrey Emmanuel.

Okay.

The one that... an incredibly well-written article that said, "This is why it's a bubble," and the whole market went And Karpathy started following it.

It's back up.

He wrote what you just said. He s- It is back up. But he wrote, uh, 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, HTTP server that's like an inbox for them and messaging, and they talk to each other now. And now he goes, "Coordinate amongst yourselves to parallelize this task, this, uh, epic that I just put together," or whatever, and they'll do it.

Some people are coming at it top-down and trying to build orchestrators that, you know, do it all for you. But interestingly with Beads, right, which is the issue tracker, uh, session thing that I, that I made, plus his-

Purely Vibe Coded, by the way

... mail.

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 re- look at it and, and sometimes I'll just be like, "So my AI, what do you think of their AI's PR," right?

And, you know, saw summarization.

I mean, isn't that bad? Don't you want-

It's bad if your code... If... Look, it's all about the outcome.

Yeah.

Beads is working, and it's got tens of thousands of very happy people using it.

Yes.

So obviously it's not bad.

I, I mean, one of the super fans out there, yeah.

If you, if you do this, uh, to your, your s- your company's production website and bring it down, then yeah, it's bad.

But still, like, 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've been just too hard to manage and, and, 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, just fix it. And it's funny 'cause Jeffrey Emanuel, 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." Man, I used to do that at Accenture in the '90s, right? I'd, like, run over to a dude's cubicle and be like, "I need that file."

Their revision control was so bad. So, like, h- he's got a file reservation system going, but, but it all... What happened was as soon as he put it in place, his, his agents just started working, and now he's got this little village of agents, right?

And that's, that's where we're headed. So the orchestrators are gonna be about not keeping the agent on the rails, but keeping all of your agents on the rails and communicating with each other.

Yeah.

And then you hit the wall.

Boom.

Does anybody know what the wall is once you get past all this? Merge.

Ugh.

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 gonna go talk to him about it. The co-

They'd be happy to talk to you, yeah.

Yeah. I think everybody needs to solve it, and if you're at an enterprise, like, what we hear... 'Cause Gene Kim and I talk... Y- we talk to companies all the... I'm a SaaS s- seller, so, in the Sourcegraph, so we get to hear the, 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 I... You and I work at the same time for two or three hours.

We make, you know, 30,000-line change each. Mine makes it in first, ha. And i- and it gets merged, and then you come along, and I have literally changed our logging system and our, like, you know, our architecture here and APIs that you were using.

Yeah.

And so it's not gonna be a simple... It's not a simple let's, let's fix the merge conflicts. It's like you're gonna have to re-envision and reimagine and re-implement your change on my change.

Or I'll rip yours out.

Or rip mine out and make me do it, but ultimately, ours are just the AIs doing it, right?

Right.

But the, the important thing is that they have to be serialized, it is a queue, and that when they go in there, they have to actually, like, basically redo what they were doing on top of the new thing.

This is like-

Nobody has solved this, and it is a huge obstacle right now.

Uh, so the-

You know what one company did? Sorry, last thing.

Yeah.

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, the classic solution for this is StackDiffs, right? Merge queues, StackDiffs that-

I don't know about StackDiffs, so I guess I'm dumb.

Oh, it's a... It's, like, a Facebook concept that they're trying to bring to the wider-

Oh, yeah

... world. Uh, GitHub is working, adding it. I th- just talked to Jared Palmer there. Basically, I, I'm hearing no solution yet, but you should be aware of it and design around it.

Yeah, I mean, there's the-

Yeah

... 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-

Yeah

... and let's, let's agree on-

Yeah

... 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 a change that affects this one.

Yeah.

With the mail thing that Jeffrey did, I think once I get it wired up, 'cause he doesn't use worktrees and I'm going to-

Yeah

... this. But once, once they can actually talk to each other, I think it's gonna be as simple as, "Just keep in mind that that agent's working on something that affects you. You might wanna go talk to them about it."

Yeah, and agree on a overall, like, fundamental infra.

And they're quite good at it. I... They just-

Yeah, yeah. What-

They have n- It's 'cause they have no ego. They're not like, "Oh, it's gotta be me."

Right.

So just whoever's first gets to be the leader.

Great. What do you and him disagree on?

Me and who?

Jeffrey.

Emanuel, the guy that I just met?

Yeah.

Well, we, uh... So we f- foundationally, fundamentally disagree that having 12 agents work in a single repo clone is a good idea.

So you're on the pro side.

I'm on the pro lots... Like, either Git worktrees with lots of branches or separate repo clones.

I would imagine he's-

Keeps them sandboxed

... he's in favor.

He's got them all in the same... They're all-

Oh, oh.

They're literally-

Oh, right, right, right

... they're using the same Git, the same build. So one of them will be, like, doing a build. They'll be like, "Need to run a test."

There's, there's so much churn.

Yeah, but he has a file reservation system. So the funny thing is, okay, 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 n- 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 have worked 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.

Interesting. Uh, I, I, I... Some people have proposed that the theme of this conference next year is all multi-agents.

Oh, yeah. I mean, yeah, of course.

Forming.

Yeah, yeah. I mean, AI will be about multi-agent.

I-

Look, we're in this phase still where we're, we're cutting down corn with scythes with our hands. That's what a, a real programmer does these days. We're moving... Next year, it's very clear, we're moving to, uh, you know, um, these, these machines that churn, you know, these giant...

Just like those ones that you see, uh, on the farms today, factory farms. We're gonna be factory farming code, okay? And, uh, that absolutely, like, uh, a lot of people are just so dead set against that philosophically, morally, ethically, whatever.

They're just like-

They're so used to subsistence ag- uh, agriculture- ... that we're not, we're not used to, like, the big-

They want to be-

... John Deeres

... together, but we are, we are actually moving into the John Deere era of coding.

That's amazing.

Yeah, but the funny thing is-

That's great analogy, actually.

And I just thought of it too. Uh, we'll have to reuse it.

Yeah.

But it's been, it's been... It's been growing on me. It's the, it's the whole... It's this idea that Claude Code and AMP and Codex, you know, Cline, we love them all equally. They're all equally bad. I said in my talk today, they're like, they're like a s- a power saw or a power drill.

A fi- a skilled craftsman can do a lot of good with them, and then you can also cut your foot off with them.

Yeah.

The same thing's true of Claude Code, but imagine a big machine, a big farming machine that knows how to run Claude Code and scrub it, right? Almost it's like, it's like, okay, you plan, you implement, you review, you test, right?

And you split it all up, and now you got yourself factory farming, right? It works. People are building it. It's gonna happen, and what it's gonna do is it's gon- 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 ti- team size is, like, two or three.

Yeah.

And I mean, like- Right? The whole way that companies are run, the whole governance structure's gonna change because now coding's no longer the bottleneck. The business needs to get immediately involved. The speed lac- 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, they're, they're, like, checking out, or they're, they're revolting online.

And I predict that as these capabilities improve, and as we get closer and closer to the factory farming of code, we will see a massive backlash-

Yeah

... from the Luddites.

You are the one of the few people I can ask this as a... I, I know a lot, a lot of people in our audience are critical of going f- the full hog with this.

Yes.

So a lot, like, they're like, "Fine for front end, fine for application code, but don't touch my cloud infra. Don't touch my b- my back end, my distributed microservices."

Definitely don't touch anything production. Only touch code. Only use these things when Git is your backstop, for starters, okay? So-

Yep

... keep prod out. Uh, it's gonna be real tempting to, right? But don't. If you have Git as your backstop, why should you be worried?

True, except I guess people have the perception that it is less good at back-end code-

Oh-

... or-

This is the problem where-

... systems code

... everybody's bad at math.

Yeah.

Okay? So how good was ChatGPT 3.5 at systems code?

Terrible.

Pretty bad. How long ago was that? Okay?

Two years ago.

People think-

Yeah

... people think the mo- 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.

Yeah.

We will still get to factory farming code with today's models' capabilities, and it... We'll get there fast. We'll get there by summer. But the models are getting smarter so fast. You know, it's really, there's, 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-

Yeah

... and so you won't need that capability in the tool anymore. And so there's this constant arms race and decay of your tool filling gaps for the model until the model's good enough to fill it itself, and then your tool moves on.

Yeah, that's why I find the-

So all growth is becoming, all code and all tools are becoming throwaway.

Yeah.

Like-

Which is great 'cause they're easier to build, too.

Yeah, by the way, yes, so remember j- uh, Joel Spolsky, one of the greatest, you know, of our, of our, our generation, our time, one of the greatest writers and thinkers, he gave the best tech talk I've ever seen, and I wanna get him to come and revive it.

He gave it at Amazon 20 years ago. It's still relevant today.

He's invited here?

Great. So Joel Spolsky, 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, uh, 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, "Oh, God," just the iteration, 'cause they're trying to fix.

There's, there's a lot to keep in h- But instead, if you say, "Throw all the tests out and make them again," it just goes, "Err," and you're done, right? And so it's like, "Hmm. Hmm, well, what about this library I gotta refactor?"

And so it's creeping up, but we're moving into a world where, uh, 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 up- upside down land, but this is... But it's like we've entered quantum mechanics, but you have to, you have to embrace this new world.

I love the energy and the credibility that you bring because-

Thank you

... a young kid could say what you're saying and not be as believable, but you're coming from the perspective of you've been a huge-

I've been doing it for a long ti-

... systems programmer-

I've been-

... you've been a game programmer, you've been everything.

Yeah, I've done, I've done assembly language for five years, you know?

Yeah.

Operating systems in assembly language. Uh- ... and it was 8080, 8086, not even F- 80x86. God, we had eight-bit registers. I've done it all. And, you know, the game pro- game, game programming teaches you everything.

Yeah.

You know, and then of course I've done platforms and Google and ads and this and that.

And you know what? The agentic loop and the game programming loop share a lot in common.

They do.

Resource sharing-

They do

... operating system loops as well.

I feel like I'm building the same systems over and over again now.

Yeah.

Yeah.

It is. It's, it's, there's only, uh, 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 your comment on is Google. Just-

Ah, Google.

One of my favorite memories, which is, like, just before you retired, was talking about how Google still doesn't get it, uh, Google Cloud in particular, how they shut down-

Oh, the deprecation policy

... the system, the deprecation policy.

I was so mad about that. You gotta get me pretty mad to write a blog.

They seem... Have they turned it around?

No. I talked to some people there, and a lot of them were like, "Yeah, that's not a thing for Google." And it's funny 'cause, you know, Amazon, uh, Amazon, not on the platform, not on the deprecation stuff, not on the important stuff, Google has turned it around on, on, uh, execution.

They might, yeah.

They finally did the thing that they should've done, you know, 15 years ago, which is hold people accountable, and it's not just engineers do whatever they want all the time, which is what it was for 20 years. And it actually worked pretty well because they had a monopoly on ads, and they could afford to subsidize Google engineers doing whatever they wanted for a...

But, you know, ultimately they had to do the right thing and grow up and mature as an organization. It 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, 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 gonna be the big, big winners.

Do you have observations of a similar kind with all the other labs? You know, I, I'm just kind of curious on your takes on... One of my favorite charts is, is that old chart where you had Microsoft, like, all pointing guns at each other.

Yeah.

Uh, Facebook, everyone's okay-

You're the first person to ask me this. I remember that chart. That was funny.

Yeah-

It just-

... I feel like someone could do that for OpenAI and Anthropic.

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 seem like they've got their act together.

Yeah.

So what, what, 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 'cause Anthropic's screwing up. It's because it's an inevitable function of growing that fast.

They're hiring, like, 100-plus people for Claude Code in the next, I don't know, month. I mean, like, they're, they're going wild, and that's just Claude Code. You're not gonna... I mean, I was at Google and Amazon when they were in the get big fast, uh, phases, and you're just gonna have chaos.

You're gonna 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? OpenAI is chaotic more, like, in a, hmm- Well, they had a lot of exits, right?

You know-

Yeah

... I don't know if it was chaotic as, say, GitHub, who lost most of their senior leadership and was just complete tu- turmoil for years, but they're pretty chaotic at OpenAI, right? Uh, and then Google, you know, um, I...

We were just talking to somebody today that was saying it was s- still too hard to, like, get consensus across groups to r- with the Jules, Jules team.

Yeah.

They can't get it rolled out internally because Google is so siloed. It's a, a billion monoliths, right? Little, little, little apps that don't talk to each other, that it's hard to roll it in anything out across Google. So, uh, all three of them have execution problems right now.

Uh, I think Anthropic's probably executing a little bit better than the other two, but it's real close race. And, uh, yeah, it'll be interesting to see and, and to see, 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?

Well-

Optimistic?

So, uh, look, as soon as open source models get to the point where they're as good as Claude Sonnet 3.7 was, then you turn on Cline or something, and you've got something that as good as Claude 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, free on your local M4 or whatever, right? So, uh, uh, yeah, I ab- and, and from what I've heard, they- they're seven months behind, and that, that gap is gradually narrowing the frontier models, which means LSS models will be as good as Gemini 3 next summer.

Right.

So yeah-

But-

... next year could very much be the year. That means the tools are gonna have to get much, much better at decomposing the tasks 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 'cause they're saturating, right? There, there's only, there's... You can only ever hit 100, and the closer you get to 100, proportionally it'll just get harder and harder, right?

So obviously, uh, the rate of change when you're lower down is, is higher w- as compared to when you're already saturating.

Yeah.

But that's a minor technical point.

Well, no, I mean, it's not, it's not minor at all. It's actually a foundational question, which is, is the line of AI, uh, intelligence gonna go straight, or is it going exponentially, or is it actually starting to peak?

Asymptotic, yeah.

Yeah. And, um, you know, from what we've heard from people who are very, very close to the research, we know that AI's been getting, uh, what is it, four times smarter every 18 months for the last, I don't know, 30 years 'cause 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 up more, or maybe it goes down.

A singularity.

We don't know.

Human history ends.

But two more cycles means they're gonna be 16 times smarter in three years, right?

I can't even imagine .

So, well, 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 gonna be really, really, really smart- ... and it's gonna change the world probably in a lot of good ways and a lot of bad ways, and, um, yeah.

I don't know if you had this version of this conversation. People ask me if their kids should learn to code 'cause-

Kids 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 o- most of the time, but you can, and it's a good guard.

Right. But I don't-

Well, I think-

... because-

Yeah

... you don't have to.

Well, I think my take is whatever it is, you will, you'll be better off if you do also know how to code because you can prompt better, right? You can, 'cause you can tell, you can communicate-

Oh-

... more precise terms

... look, when you s- when I say you should 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 sh- 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 architecturally, 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, uh, like Jeffrey Emanuel, like I was talking about, he's a mathematician, self-taught engineer.

He doesn't... But he, he's learned all of the right concepts and, you know, you know, Cloudflare does this, and, and Apache Cassandra does that.

Yeah, that is still-

Right?

... technical, yeah.

The-

That doesn't go away.

You still need to learn all that, right? And so just because you don't have to write code anymore 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, a great overview. I don't know if you have any other sort of rants in you that you want to sort of get out there. I'll, I'll, I'll leave you the floor.

I feel like the gossip rate has gone up, like not gossip, but the, the rate of exciting announcements by engineers who have discovered new things about how to be more productive with agents. Um, like for example, I just found out today, not, not this.

I was... I found out today about, uh, it's called Code MCP or something like that, where you, uh-

Yeah

... instead of calling-

It's a pretty popular project

... the agents can't call MCP very effectively because they don't have any training on tool calls, but they have plenty of 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, are just-

It's, it's crazy that Anthropic, the creators of MCP, found this.

Did they?

Yeah. Well, Cloudflare found it first, but then Anthropic was like, "Yeah, yeah, you guys are right."

Yeah. Wow. That's really neat.

So, 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 LLMs way better than everyone else.

That's true. That's true.

So you have so much more power.

You could almost define an AI engineer as somebody who's mastered LLMs.

Yeah, yeah, um, not from training, but from using.

Yeah, using.

And-

Yeah, yeah, yeah, yeah.

I think it, it's, it's one of these, like, disruptor, like, 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 wrapper, but, like, you're start- like, people are 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-

That's right

... they'll tell you everything about driving it to the best of their ability.

And they may know, they, in a sense-

And they make the money

... know 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, uh, I think the F1 movie, you, you get a little sense of yeah-

Oh, and they make all the money-

That was great, yeah

... is that what you said?

Yeah.

Yeah, that's a good point. It's flip-flopped.

Yeah. Uh, lovely. Well, thanks so much for having me, for coming on. Uh-

Cheers

... huge admirer of your work. Um, your energy is very infectious, and I hope you keep doing Stevie's Tech Talks.

I'll start them up again, man.

Yeah.

I mean, this energy is because of the AI, and it's because-

Yes

... of vibe coding.

Yeah.

It's, it's addictive and fun.

Tech is fun again.

Just, it's tech-

It just got boring for a little bit. I know, I know.

Nice.

For a while it was like, well, SourceGraph, like, index your, your, indexes your code base, like, really, really well, you know? Again, it's, like, so, so fast, and I'm like, "Well, that's cool, but you know what's cooler?"

It's fine. It's fine.

Yeah.

Yeah. Cool.

All right, cool.

This has been fun.