I’ve completely moved to codex cli as daily driver. I run between 3-8 in parallel in a 3x3 terminal grid, most of them in the same folder, some experiments go in separate folders. I experimented with worktrees, PRs but always revert back to this setup as it gets stuff done the fastest. … I used to love Claude Code, these days I can’t stand it anymore (even tho codex is a fan). It’s language, the absolutely right’s, the 100% production ready messages while tests fail - I just can’t anymore. Codex is more like the introverted engineer that chugs along and just gets stuff done. It reads much more files before starting work so even small prompts usually do exactly what I want. … And yes, writing good software is still hard. Just because I don’t write the code anymore doesn’t mean I don’t think hard about architecture, system design, dependencies, features or how to delight users. Using AI simply means that expectations what to ship went up.
This is amazing, and almost exactly mirrors many of my own coding evolution. I"m often running 2-4 CLI tools both to manage spend across several subscribers but also because while one idea is spooling I can start another one elsewhere.
The MCP trap I think is real. There doesn’t seem to be a whole lot of value there if you just bring you context window to the fore front. Bonus points for doing what I do frequently, if AI/I think of an idea but I don’t have time to chase it down I just tell it to write a md file with that in it for later. No JIRA required.
Quote Citation: Peter Steinberger, “Just Talk To It - the no-bs Way of Agentic Engineering | Peter Steinberger”, 14 Oct, 2025, https://steipete.me/posts/just-talk-to-it#what-about-mcps