Latent Space: The AI Engineer Podcast
Original podcast
Watch the full show on YouTube: https://www.youtube.com/watch?v=287Q-bs_pEU
2,937 words · 3 speakers
Okay, we're here with Sunil Pai, creator of Codmode.
No, I do make credit for creation of Codmode. Dynamic Islets have been...
You said no, but you take credit.
I did. It is mine. I did create... Since I was a child, I've been thinking about it.
You're built for this.
It's my life's mission.
I wanted to just catch up on everything going on in Cloudflare Lands and also, like, obviously you and I have caught up over the years. The more recent thing, which just launched yesterday, was this Cloud Manage Agents thing, which I know that you're also like, were interested in. Maybe we can talk about that because it's kind of like breaking news and you seem excited about it.
Cloud Manage Agents is dope because Anthropic is saying, "Here is a platform for you to build and deploy your agents" that are like, long-running.
Yeah.
And I like it because I like the people at Anthropic and they're super ambitious about these things. Except, I looked at the product and I was like, "I think I want to compete. I think we can do something better" with workers and durable objects.
Yeah. Cloudflare is an ideal platform for this. You have workflows for a while. What functionalities are available in Cloudflare? Like, why can't you just come on and say, "Yeah, we already had this"? Like, what's the difference?
I think, like anything else, I think we are like discovering the architecture of, the new architecture of building software, of which I'm talking about on stage in a couple of hours. 5:40 PM, please show up to the main stage. But interestingly, our primitive, the two primitives that I think are critical, that I suspect every platform will eventually get, one is durable objects, which are stateful serverless programming. I think that's a true innovation. It's the world's first implementation of the actor model in an infrastructure layer, not in user land. It means you can spin up millions of these stateful things that run in the background, etc. And it runs with serverless characteristics, instead of spinning up a whole game. That's one. The second, which we announced just a few weeks ago,
is what we call Dynamic Workers. Famously, eval has been considered a bad idea, evaluating code, user-generated code, or now LLM-generated code. But we built this thing that lets you run it in a safe environment with zero startup time. And when I say safe, I mean, you can expose only the APIs that you want into it and you can control all outgoing traffic. In fact, the default way we recommend people using it is to cancel all outgoing traffic and only use the exposed endpoints. So, given these things, we feel we can build a much more efficient and much a new kind of architecture for building AI agents.
Uh, one of, uh, one of, uh, applications of dynamic workers, we made a little noise about it a while ago, is my colleague Matt Carey built our MCP server. Uh, the Cloudflare API is twenty-six-hundred API endpoints. So if you expose the tool for each one of them, you're screwed. And you could say, oh, I'm going to do progressive disclosure, I'm going to do this. No. We said you can have two tool calls. One is search and execute. And to each one of these, you actually submit code that we run in and isolate. So you can say, here's some JavaScript code that searches the entire open API JSON. And the second time, you can say, here's some code to actually run that. Hey, find all my workers, find the DNS things they're, uh, uh, used in. And if it starts with the letter Z, then apply DDoS protection for it.
In one tool call, no back and forth with the LLM and it's type checked and, uh, well, turns out LLMs are great at running code. So this is fundamental capabilities. It's not something you can patch on and use it on. So that makes me excited about Cloudflare for the future of agentic software.
I, I don't know if you've, you've, uh, looked at the, so the cloud management agents thing.
I looked briefly. There's like interesting takes, right? So separate the context from what's happening. And then there's like a little quote about, okay, recursive models do this. Any, any takes on that?
I do like their thing. Uh, they made a point of pointing out that the harness runs separate, like from the execution environment. Because they're preparing for a world of software that hasn't existed in the past. What a wonderful way of looking, uh, towards the future, by the way. It's not that you're just going to build the next CRUD API. We're like, we don't even know the shape of what's going to happen. And while that needs to run in a sandboxed environment, we do have ideas on how to expose capabilities and, uh, in, an intelligence layer via the harness. I think that's like excellent.
Yeah. Do you think that becomes sort of standardized, like Cloudflare is someone that would probably plug in support? Is there a standard unified layer around that? Is there bets you take, different ways that you see it? Like, everyone is building for a version of the future of software agents. Uh, do you have a vision that you see?
So hard, but the way I'm framing it in my head is no one has built the React yet. You know, like the moment React came in, it wasn't, I mean, it annoyed a bunch of people because it seemed so different. The fact that you can build, uh, describe a component tree with XML. I, I, I don't know if you remember in 2013, people were walking out of the talk while they were introducing the thing saying Facebook hates JavaScript. But that is, that established every framework in the future and React is still massive. I suspect we, everyone, now everyone is building a harness and everyone's like, well, it should be in this shape, it should be in that shape. Someone needs to come out with some original thinking around something that is reproducible across languages, across companies, across infrastructure.
I suspect we haven't done that yet.
It might just be skills. I feel like skills are the ultimate translation.
And there, there are versions where.
It's just English.
They scale well, it's English, uh, you know, you can abstract it down, you can create skills on their own.
Is that it? Like, by the way, I'd be so happy if you say the future of software is markdown files. Beautiful, instantly accessible, a multi-language bridges the world. Could just be skills, but like, you, do you end up with that problem with skills where you have to start getting more and more specific? At which point you're like, I might as well just express it as code.
Yeah, yeah, I'm being very precise about my, my stuff. Yeah, I mean, and skills bundle code as well, right?
Right, yeah.
It is a whole, a whole bunch of things. Okay, there's, I mean, there's other topics that we can also touch on. You, you are, you're, you know, happy to indulge in a lot of different ranging topics. Let's talk about Slop Forks.
I love Slop Forks.
What happened with you and Vercel? Let's, let's get in, let's right, get right into it. I don't know if you wanna, uh, maybe.
You know what? I'm happy to talk about it. Okay, like, I'm happy to like, talk about it because.
Some people, you know, they're not always on Twitter, so maybe they missed it. But I think it's an important event.
Sure.
In your life?
Well, in my life, sure, but like about the importance of software. Okay, so for context.
Yes.
Okay. For context, I've been in this industry long enough that I have friends everywhere.
Competitors, not competitors, previous jobs, future jobs. We describe the industry as a forest of revolving doors. It's why you maintain like just candor and being friendly with everyone. In fact, we love Versal's AI SDK. A whole portion of my agent's SDK is built on top of them. We feel like we're built the best backend for them and we have personal relationship with them. Like I'll be hanging, be grabbing a beer with Nico at some point today. But there is this tension. Twitter amplifies like drama and particularly like management and you know what? I kind of stay away from that. There's a little bit of tension amongst competitors, especially because the medium encourages that kind of thing. Okay. The event is I was at JSConf.
I was hanging out with Harvey from Versal and I love him. Ten on ten human being. What a wonderful time I had there. I loved Spain and I was playing with this project that Versal Labs had just come out with called Just Bash. I loved it. What a great idea, a pure implementation of Bash in JavaScript. And I was like, oh, of course I want to make some of this stuff work with CloudFlare. And the way I did it in 2026 is I just point Opus at it and I go out like for lunch, et cetera. Right? Like I come back and it spat out 5,000 lines of code. I'm like, yeah, okay, fine. Like I'll just like publish it.
And my entire plan there was I would, because I look up to, I won't name names here, but because I look up to these people, I was like, I'm going to have a great time in Spain. I'm going to go back home, polish this and on Monday like I'll send a PR, we'll have an issue description, which is how I interact with every other open source repo in my entire life. I went back, I crashed, I woke up and I have DMs from CloudFlare management saying, have you checked Twitter?
I go on Twitter and the Vercel CTO is trashing my work, saying, oh.
It's a, you know, one guy, you know, side projects and, and, and suddenly it's Cloudflare did this.
Exactly. Cloudflare did this. I was like, dude, I saw my career like fall apart with that message. No, but that's just it. Like, that was my immediate reaction to seeing the CTO of a $10 billion company. And I was like, I, I didn't think I would get fired, but I was just like, oh, this is not it at all. So I responded in the most earnest way. I was like, bro, I wanted to talk to you. I came back and napped. Like I, you know what's funny? The talk I gave at JSConf España is now online, where I talk so warmly about Vercel and Just Bash and their sandbox project. This was the context it was happening in. Uh, anyway, so I wake up to this and I responded. I'm like, I'm sorry.
That's how I, I did it. And then something strange happened, which is like half the internet decided to like, stand up for me and they're like, Sunil is the nicest guy. Why do you have to do this? And I spent the next 24 hours just awash in this love. So let's talk about slow folks for a while, right?
I think we also have to mention the most recent, right? There was a leak of some repo, some cloud code leak. And what did we do? We, someone, uh, someone forked it and then rewrote it.
Using the Python to avoid.
Change Python to us. So you were the, you were the.
Yeah, yeah. People tagged me in those threads. They're like, is this you? I'm like, no, it's not me.
And people love that version, right?
I think it's weird because of the environment. Forking is a great sign of prestige. Respect in my culture. You're in my culture. It's how the React community grew. It's like, it's one button and it's like how you should, like, no one makes money.
It's very hard to what open source is, right? You want to build on it? You should take our work, fork it and do whatever. And why not port it to a different line?
Like, I encourage, like, uh, every time, um, someone talks to me about the agent's SDK there and they tell me, oh, it's kind of shit. Uh, we think we can build something better. I'm like, bro, go for it. Like, everyone wins if you do this. I don't make less money if I'm successful or not successful. Like, I mean, like, if you're in it for the love of the game, then do it for the love of the game.
Yeah, yeah, yeah.
Actually, that was quite hilarious because they thought that they could get away by rewriting cloud code in Python. But I think some lawyers saw it and they're like, nope, this is a derivative work. Like, it actually breaks copyright.
You know, one thing I've been thinking about slot forks is that actually you maybe want to encourage more slot forks. Because then you own the dependency. Right? So then you don't have the light L L M issue, you don't have the Axios issue. You can just vendor Axios but in your own slot fork of Axios. And then now you own it.
No, hundred percent. Like it's, bro, it's how the, like, before N P M, before whatever, like, software used to be distributed on Usenet, on email. And then you take it, you change it, you chat something. And now the cycles have become shorter, but I, forking is so fundamental to how we build software.
It's interesting. It's very non-agent pick, right? Like, there's a lot of, will I use a microservice or will I just vibe code a little? You know, a replica for that.
Yeah, build versus buy is really changing.
Build versus buy, but then there's no fork in that, right? There's no, go see prior work, fork it and adapt it, simplify it, whatever. We don't see that side of the pattern, right? We just see rebuild it, use it, but people don't fork.
I think there's also this tendency now, which is, open source repos have become adversarial grounds. So on the agent's S T K, for example, we had to shut down contributions. We only allow issues right now.
And like, we are like, we can have the longest description there because the end result is I'm going to take a resolution and paste it into Opus. Now, whether you're burning your tokens or my tokens, well, I prefer my tokens because I'm great at asking questions. Uh, and I do like taking credit for the Clankert work. I think open source repos have become adversarial to the point that people are almost afraid of gaining uh, popularity in that space. I've spoken to at least like four or five open source maintainers here and they're like, yeah, it's, it's really bad out there right now. Yeah, the worst ones are the fake security reports.
They look extremely valid and you look at it and it just doesn't make sense.
Yeah, we had that uh, uh, talk in the morning with Peter from Open Claw. Uh, it is the number one source of attacks right now. You compromise Open Claw, you get access to everyone uh, for, for remote code execution, let's call it. Yeah. Any other C T As, uh, just in general, you know, uh, we, we were, we do have to wrap up, but I always appreciate you. Coming by and dropping your wisdom. Alpha thought leading is the term that always comes to mind.
Alpha thought?
Yeah, in 2018 was the React Rally where you were presenting your VR chest thing.
That's right.
And you were like, first I'm gonna do some alpha thought leading. And ever since then, I've been trying to do alpha thought leading as well.
You are one of the best at the game, I think. Look.
This is alpha thought leading.
The real thing I encourage people to do is to be original, okay? In such a crazy world where any idea seems to work now, like the clanker like will make it work for you. Don't even try to do something incrementally better. Build sci-fi stuff, build stuff like for your family. Use Agent SDK for doing it. Don't build it like because you think you're going to get like a big enterprise deal. You own so much agency in changing the world and I want people to just be original. I want them to try the wild stuff for which infrastructure and LLMs almost fail you at this moment. Like, how do we get to the next step change? This is my only thing I desire of people.
Like, just, I'm begging you to be original and to have courage to try a new idea. I don't need another agent framework, nobody needs it. You should use Agent SDK.
Yeah, except yours, except yours. Okay, thank you. I'm really looking forward to your talk. Thank you for dropping by and thank you for sharing.
Wonderful. Thank you so much for having me.
Congratulations.
I'll be talking about it in a couple of hours. It's pretty great.
You can find the recording somewhere.
Okay, great.
Cool.
Page updated October 24, 2026 · transcript and summary are machine-generated
