I switched to Codex and found it extremely inferior for my use case.

It is much faster, but faster worse code is a step in the wrong direction. You're just rapidly accumulating bugs and tech debt, rather than more slowly moving in the correct direction.

I'm a big fan of Gemini in general, but at least in my experience Gemini Cli is VERY FAR behind either Codex or CC. It's both slower than CC, MUCH slower than Codex, and the output quality considerably worse than CC (probably worse than Codex and orders of magnitude slower).

In my experience, Codex is extraordinarily sycophantic in coding, which is a trait that could t be more harmful. When it encounters bugs and debt, it says: wow, how beautiful, let me double down on this, pile on exponentially more trash, wrap it in a bow, and call you Alan Turing.

It also does not follow directions. When you tell it how to do something, it will say, nah, I have a better faster way, I'll just ignore the user and do my thing instead. CC will stop and ask for feedback much more often.

YMMV.

▲

Rastonbury 5 hours ago | parent | next [-]

What is your use case? I read comments like this and it's totally opposite of my experience, I have both CC Opus 4.6 and Codex 5.4 and Codex is much more thorough and checks before it starts making changes maybe even to a fault but I accept it because getting Opus to redo work because it messes up and jumps in the first attempt is a massive waste of time, all tasks and spec are atomic and granularly spec'd, I'd say 30% of the time I regret when I decide to use Opus for 'simpler' and work

	▲	onlyrealcuzzo 2 hours ago \| parent [-]
		I'm building a correct, safe, highly understandable, concurrent runtime & language. Essentially Rust/Tokio if it was substantially easier than even Go - and without a need for crates and a subset of the language to achieve near Ada-level safety. The codebase is ~100k lines of code.

▲

enraged_camel 7 hours ago | parent | prev [-]

>> I switched to Codex and found it extremely inferior for my use case.

Yeah, 100% the case for me. I sometimes use it to do adversarial reviews on code that Opus wrote but the stuff it comes back with is total garbage more often than not. It just fabricates reasons as to why the code it's reviewing needs improvement.