Actually I use LLM mostly for the code quality and not for the architectural/logical or design decisions.
I am using claude solely because it's best in terms of Code quality and UI.
According to you do you think codex has surpassed or at least came on par with the claude in terms of code quality and UI ?
How good is codex in terms of code context ?
I think in terms of UI, codex has become superior probably due to its sandbox concept. It can complete tasks reliably without intervention whereas claude would have stalled asking permissions (unless you run it in --dangerously-skip-permissions, which I won't do). I don't know about you, but sitting in front of my laptop just to continuously press enter is depressing, I'd rather do other tasks in the meantime, which is exactly what I can do with codex.
So combined with the issues claude has been experiencing in the last couple of weeks (see https://news.ycombinator.com/item?id=47660925) - codex has become a better option. Claude has been unable to complete simple tasks and got lost in 5+ minutes of exploration too many times and I just called quits.