Short answer: Iliya Valchanov says Juma moved from Cursor to Claude Code and canceled Cursor. Jordan Metzner says Codex 5.3 and 5.4 on extra high gave better code quality, while Claude Code was more enjoyable but confidently buggy.
From Episode 35: AI Agents Are Replacing Entire Marketing Teams, starting at 15:40.
Sam Nadler [15:40]: Absolutely. And speaking of agents, I actually wanna transition us to kind of the First News article in the day, which is kind of the high level, this ongoing competition between Claude Code and Codex. Similar to you, Ilya, I can really only run three agents at the same time. I feel like I forget one as I, like, engage with the other two, and then I come back to it and forget the other one. But, we're kinda I would argue we're power users of both here. I know Jordan shifted a little bit more towards Codex, and I still use both Claude Code and Codex about 5050. But just, a, do you have a preference? B, what are you using? Have you used both? Give me some understanding of your stack.
Iliya Valchanov [16:26]: Yeah. So everybody on our team was using Cursor before, then we all moved to Claude Code, and basically last week, we canceled Cursor, and we haven't been nobody wants to move to Codex. We test it from time to time, but for our use cases, Claude Code is working so so well that we do not see why we should move to Codex anymore, while the difference between Cursor and Claude Code was so big that we actually intentionally moved away from Cursor. So actually, I'm very interested to ask Jordan, why are you using Codex more?
Jordan Metzner [17:04]: Yeah. So we went through kind of like a similar set of iterations. Think like at one time, we were all using Cursor, and we've kind of moved from Cursor over to Claude Code. Especially, when Opus 4.6 came out, I think that was the big jump, in mid December. And one thing I noticed is like, I really enjoy using Claude Code. It's very fun and they do a really good job of kind of keeping you entertained while the agent is working and kind of, those words and all those things. And it's actually like a pretty like enjoyable experience. I was a little reluctant to try Codex, but once I went to Codex 5.3, I noticed significant improvement in code quality. One thing I would notice like repetitively with Claude Code is that it would make mistakes, but be confident that there were no mistakes. So it was I guess you can call like buggy code for lack of a better term. And one thing I've noticed with Codex is that it's it's much more performant. So as a user experience, it's like a little less enjoyable. It's a little bit slower. It's like not as fun. But the output of the code, both with 5.3 and now especially with 5.4 on extra high, I found to be significantly better quality.
Jordan Metzner [18:10]: I think like to each their own in the sense that, I will kind of allow my developers to kind of pick what their favorite tool is. Like, they still have access to all of these tools and kind of trying to coalesce everyone to use the same thing. But, switching costs are high. It's not that high, but, everyone kind like switch and move to a new tool, but we still have some developers preferring Claude Code over Codex, but for me personally and some of our other developers, we found that Codex has been much better. I think the big unlock for us is we're we're working on trying to get, these PRs done in the background, kind of like whether it's Codex or Claude Code kind of working in the background. So I think as that gets more improved, that will probably push us towards like one ecosystem over another. But I think what's most interesting is that like, back to the switching costs. Yeah. Maybe for a developer like to learn a new system picks a little bit and like the idea desire to like close one and open another. So that seems like honestly not very high, but people get custom are accustomed to working in a certain way.
Jordan Metzner [19:04]: I mean like, developers who like JetBrains, like, have been using the same IDE for, fifteen years or something like that. So it's sometimes hard to switch, the form and operation which you work. But to me, it's like whatever's the best model of the day. And you know, like, we'll just keep switching to find like where the best outcome is for that. It's, it's crazy that no one's looking at the code anymore. I mean, both Claude Code and Cursor excuse me. Both Claude Code and Codex are built as applications that don't have the code easily available to show you. And that's an interesting paradigm, but it seems like more and more that nobody's reading the code anymore.