Let’s see some screenshots!

Definitely understand the skepticism! It's hard to switch tools Some thoughts: - Your setup should come along with you - ping me if it doesn't! MCPs, skills, etc. should "just work" - We update the version of Codex Bitrig uses a lot to stay on top of things. For example, we try to add new models same-day and new features as quickly as we can (e.g. we added support for async-questions with Astra within a couple days) - Bitrig definitely feels better for Apple platform development. You won't appreciate how well we integrated the simulator until you try to go back to Codex without it 😉 and the agentic sim-use is super helpful (esp. since our sim-use is very fast and token efficient compared to others) - Codex .app is still better for *very* long-running tasks (>8h). We're working on this, but the long-tail of task length is hard to do well! They have optimized great for this in perf. and in reliability - You can go back-and-forth between Bitrig/Codex because your conversations show up in both! So if you try Bitrig and get blocked, just open the conversation in Codex (and I'd love if you tell me what issue you hit so we can make it better)

In iOS 26, the scroll edge effect default is .soft. In iOS 27, it is .hard.

I’m significantly older than you. I started coding in the late 60s. My current strategy is to not read any of the code written by my agents. That’s the only way I can take advantage of their productivity. What I do instead is to surround the agents with extreme constraints. Unit tests, gherkin tests, QA procedures, quality metrics, mutation testing, test coverage, and a plethora of others. In the end, I have very high confidence in the code they produce because they’ve had to run the gauntlet of all of my constraints and tests.