Oh my fuck, I was led to believe that the Codex Mac app was native. Codex itself said so. Google also said so but now it says different.
Codex definitely "feels" more native than Claude: Proper menus etc, like when you right-click on a session in the sidebar, Codex shows an actual context menu, whereas Claude reveals its HTML-rendered jank and highlights the word you right-clicked on as if the sidebar item is just a plain textbox, ugh
OH MY FN GOD, Claude isn't even respecting my AGENTS.md and other instructions! Codex does it seamlessly.
Just right NOW it generated GDScript code with SPACES instead of TABS for indentation despite me explicitly asking for tabs and everything else in the project using tabs.
Your use case is either extremely simple, involving extremely common scenarios, or you're too lazy to verify Claude's output.
Either way, it's not worth the hassle to convince someone using a bad product that it's bad; nothing's gonna improve, and you're the one being harmed by stubbornly gaslighting yourself and others that it's good. The rest of us will escape by never subscribing again.
I've already wasted too much time on this thread. I keep saying I am using BOTH Claude AND Codex SIDE BY SIDE but that's somehow getting filtered out by your fanboy glasses. I could post screenshots of the outputs of both agents for the SAME prompts but you would still not understand.
Codex definitely "feels" more native than Claude: Proper menus etc, like when you right-click on a session in the sidebar, Codex shows an actual context menu, whereas Claude reveals its HTML-rendered jank and highlights the word you right-clicked on as if the sidebar item is just a plain textbox, ugh