# Codex trades speed for stronger context on complex apps

Markdown copy of https://realalpha.app/s/codex-trades-speed-for-stronger-context-on-complex-apps/ on Real Alpha, the best minutes from long interviews with the people building AI. Cite and link the page, not this copy.

- Speaker: [Peter Steinberger](https://realalpha.app/builders/peter-steinberger/) · Peter Steinberger is creator of OpenClaw and founder of PSPDFKit. · Created viral open-source personal agent OpenClaw and joined OpenAI to drive next-generation personal agents.
- Host: [Gergely Orosz](https://realalpha.app/people/gergely-orosz/) · Host, The Pragmatic Engineer · Spent four years at Uber heading mobile, web and backend teams; shipped part of its payments system.
- Show: The Pragmatic Engineer
- Episode: [The creator of OpenClaw: "I ship code I don't read"](https://realalpha.app/v/8lF7HmQ_RgY/), Jan 28, 2026
- Moment: 42:58 to 49:14 of the episode (6 min), playing on https://realalpha.app/s/codex-trades-speed-for-stronger-context-on-complex-apps/; the episode from there: https://realalpha.app/v/8lF7HmQ_RgY/?t=2578

## Quote

> “but for writing code in complex applications codex is just so much better because it it it **takes 10 times longer**”
> — [Peter Steinberger](https://realalpha.app/builders/peter-steinberger/) at [46:57](https://realalpha.app/v/8lF7HmQ_RgY/?t=2817) · The Pragmatic Engineer

## Takeaways

1. He runs five to ten agents in parallel.
2. Codex reads more of a codebase before implementing.
3. He discusses architecture with agents before saying build.

## About this segment

He uses agents in parallel and favors Codex for complex applications because it reads more of the codebase before acting. He stays in charge of system design and discusses options before asking agents to build.

From “The creator of OpenClaw: "I ship code I don't read"”, Jan 28, 2026. [Watch the full episode](https://realalpha.app/v/8lF7HmQ_RgY/)

## Transcript

Transcribed by machine (Whisper) from the episode’s audio, so a word may be off here and there.

[43:05](https://realalpha.app/v/8lF7HmQ_RgY/?t=2585) are you using a terminal, multiple terminals, which tools and how are you, you know, like you said you're not you're kind of like not reviewing the code but you're still thinking about architecture like what does your average day look like in terms of tooling you know you have to explain to a developer who might join the team you know at one point you think like what does it look like it's interesting let's let's let's go a little bit we were we were in in in april with cloud code and then i got really hooked and then i did some i had a phase where i did cursor and then i did i i used gemini 2.5 a bit then we had this phase with opus 4 i hooked up a lot of my friends like i know i know both armin and mario from vienna they got they got ai pilled because i i was addictive you know my my enthusiasm was like confusing them and then

[43:57](https://realalpha.app/v/8lF7HmQ_RgY/?t=2637) they tried it out and then and then eventually also of We were up at 5 a.m. and I called it like the Black Eye Club. I mean, there's a reason. Like I started a meetup in London that I called Cloud Code Anonymous because it's a little bit like a drug because it's so much fun. Like to me, what blew my mind so much was this realization that I can build everything now. Before you had to really pick which side project you build because software is hard.

[44:28](https://realalpha.app/v/8lF7HmQ_RgY/?t=2668) It's still hard. but now like I am this this friction that I talked about where I'm so good at this technology and I'm like so bad at this and I'm like oh let's make the CLI and go I have no clue about go but I have I have a good system understanding and once you have that it's like you you develop a feeling what's right what's wrong like it's it is a skill in itself I remember there was this tweet where someone said oh when you write a code you you feel the friction and that's why that's how you make good architecture i feel the same friction when i prompt because i i see the code flying by i see how long it takes i see if like the agent pushes back um i see if what it creates looks like messy or like makes sense when i prompt i i have a hinge already how long it's going to take if it takes much longer i understand that i messed up somewhere you kind of feel the model you you

[45:22](https://realalpha.app/v/8lF7HmQ_RgY/?t=2722) know you know how usually it's like this or if it runs i feel it's very much a symbiosis like i i learned to to talk may i even say there or that language more so it's like my my knowledge how to use those things improved and also the models improved and then and then like over the time between between april and now i would say at inflection point was summer where it just got so good that you could you create software without actually writing code by hand but the real that change that like sold it for me is was again gpt 5.2 that was again I think it's underrated I don't know why why all these people still use cloud code I kind of get it it's a different way of working but whatever OpenAI cooked there is insanely good pretty much every prompt i type gives me the result i want which is insane like like on on

[46:27](https://realalpha.app/v/8lF7HmQ_RgY/?t=2787) cloud but my latest product i use between five and ten agents in parallel if you're very much cloud code built you have to forget quite a lot of the the silliness that the things that you have to do to create good output with cloud code i mean i also met met that team and and they created a whole new category like cloud code is is is a category defining product and it is amazing for general purpose computer work and it is really good for coding and i i i still use it almost every day but for writing code in complex applications codex is just so much better because it it it takes 10 times longer um cloud would read three files and then be confident enough to just like create code and then you really have to steer it and push it so it reads more code so it gets it sees a bigger picture of your code base so it it it weaves in new features

[47:28](https://realalpha.app/v/8lF7HmQ_RgY/?t=2848) better and codex will just like be silent and just read files for 10 minutes and if you are If you only work on one terminal, I completely understand how you find this unbearable. But I rather have something where it's also you don't tell it what to do. You know, this is also something that people don't get. Like, I have a conversation with the model. It's like, oh, let's look at this. What options do we have for this structure?

[47:57](https://realalpha.app/v/8lF7HmQ_RgY/?t=2877) Did you consider this feature? It's like, because... Every session is like the model starts from having no understanding about your product and sometimes you have to just give it a little bit of pointers. What about this and this? So it explores different directions and you don't need plan mode. Like I'm just having a conversation until I say build this, it will not build this. There's some trigger words because it is, they all are a little trigger hungry.

[48:22](https://realalpha.app/v/8lF7HmQ_RgY/?t=2902) But as soon as I say, let's discuss or give me options, they will not build things until I say build. so a lot of would you say a lot of your prompting or a good part of it is this conversation where you are pretty much planning together with the agent yeah it's like what about you remind them it's like okay we need documentation what would be a good spot it would like give me some recommendations no this should really be its own page do we need a configuration how does this fit into this other feature I am designing the system because I have this system understanding about how is my my product how are the shapes looking i don't have a line-by-line code understanding that's that's what codex does for me but i'm the architect you know it sounds a little bit like