We're All Addicted To Claude Code

**Calvin French-Owen** (0:00)
I feel like when I'm using Claude Code, it's like, oh, I feel like I'm flying through the code.

**Gary** (0:03)
When it's in your CLI, this thing can debug nested delayed jobs, like five levels in, and figure out what the bug was, and then write a test for it, and it never happens again. This is insane.

**Calvin French-Owen** (0:14)
I think everyone who's experimenting with this stuff on like a hobbyist level, or at like a very small startup, they're just pushing the coding agents as far as they can go, because it's like, you don't really have time to figure out anything else. Like as a startup, you have limited runway, you're just going to orient around speed. I think at a bigger company, you have a lot more to lose.

**SPEAKER_3** (0:30)
What are some of the tips to become a top 1% user of coding agents?

**Gary** (0:35)
Yeah, what's your stack?

**Calvin French-Owen** (0:36)
Yeah.

**SPEAKER_4** (0:44)
Hey, everyone, welcome back to another episode of The Lightcone. Gary, are you ready to record?

**Gary** (0:50)
I'm in plan mode right now, but okay, yeah, I guess it's time. Sorry about that. Well, welcome to another episode of The Lightcone, and today we have an incredible guest, Calvin French-Owen. He's one of the first people to create Codex at OpenAI, and before that, he started Segment, which is a multi-billion dollar company that got to a very successful exit. Calvin, welcome back.

**Calvin French-Owen** (1:13)
Thanks for having me.

**Gary** (1:14)
I guess, what a crazy time for all of us. I recently got very, very addicted to Claude Code, and I would describe it as like 10 years ago, I was a marathon runner and I loved doing it, and then I suffered a catastrophic knee injury, which is called manager mode, and I stopped coding, which is tragic and horrible, but now the last nine days have been like this incredible unlock of all the things I remember being able to do, and it's like I got a new total knee replacement, and actually it's a bionic knee, and it allows me to run five times faster. What's your take on it? Because you're right out there at the forefront of it, I mean, Codex pioneered a lot of the ideas that now everyone still uses, and Codex is still evolving too.

**Calvin French-Owen** (2:07)
For brief context, when I was at OpenAI, I was working on the Codex web product. At the time, Cursor was out in the market and they had kind of built this shim around, I think it was Sonnet 3.5, and it was able to work in your IDE. Claude Code had just come out and it was working as a CLI. And we kind of had this idea, like, hey, in the future, coding is really gonna feel more like talking to a coworker. Like, you're gonna send off a question and then they'll go off and do something and come back to you with a PR. And so that's where we started with this WebView, and that's what we were building. I think directionally, that's still kind of correct for where things should go, but obviously now everyone is coding with CLIs instead. Like, they're using those tools a lot more, whether it's Claude Code or whether it's Codex. And I think, at least for me, kind of the lesson in that is I think, in some sense, you're right that, like, everyone is going to become a manager in the future, or at least that's my hot take. But in order to get there, there are steps along the way and you have to really build a lot of trust in the model and understand what it's doing.

**Gary** (3:08)
You recently came over to Claude Code. What's the transition been like in terms of as using it as one of your stacks?

**Calvin French-Owen** (3:15)
Yeah, yeah. So Claude Code is certainly my kind of like daily driver today. And honestly, this has switched every few months. For a while, I was deeply in Cursor. I think their new model, which is really fast, is actually quite good. Then I kind of moved over to Claude Code, especially with Opus. Claude Code is a really interesting product, and I think it's underrated how good the both product and model are working together. If you study them closely, I think one of the things that Claude Code does in particular that's really amazing is split up context well. And so if you look at, I don't know, things like skills or subagents, like when you ask Claude Code to do something, it will typically spawn and explore subagent or like multiple ones. And basically each of those are running Haiku to traverse the file system and kind of like explore what's there. And they're doing it in their own context window. And I think Anthropic has kind of like figured something out here around, given a task, does that task fit in the context window? Or should I actually like split it into many more? And the models are like insanely good at this, which I think gives them really good results.