Peter Steinberger: preference

Transcript context

…What about the code that it generates? The, the… In terms of the actual quality of the code, is it basically the same? If you drive it right, Opus even sometimes can make more elegant solutions, but it requires more skill. It’s, it’s harder to have so many sessions in parallel with Cloud Code because it’s, it’s more interactive. And I, I think that’s what a lot of people like, especially if they come from coding themselves. Whereas Codex is much more you have a discussion, and then we’ll just disappear for 20 minutes. Like, even AMP, they, they now added a deep mode. They finally… I mocked them, you know. We finally saw the light. And then they had this whole talk about you have to approach it differently, and I think that’s where, that’s where people struggle when they just try Codex after trying Cloud Code is that it’s, it’s a slightly diff- it’s, it’s less interactive. It’s, it’s like I have quite long discussions sometimes, and then, like, go off. And then, yeah, it doesn’t matter if it takes 10, 20, 30, 40, 50 minutes or longer, you know? Like, the 6:00 thing was, like, six hours.The latest trend can be very, very persistent until it works. If there’s a clear solution, like, “This is, this is what I want at the end, so it works,” the model will work really hard to really get there. So I think ultimately … they both need similar time, but on, on, on, on Claude, it- it’s a little bit more trial and error often. And, and Codex sometimes overthinks. I prefer that. I prefer the dry, the dry version where I have to read less over, over the more interactive nice way. Like, people like that so much though, that OpenAI even added a second mode with like a more pleasant personality. I haven’t even tried it yet. I, I kinda like the brad. Mm-hmm.…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.