I tried this and while the prose is indeed snappier I find the code quality of Codex truly horrific. It's dense and uninterpretable. I almost wonder if they have made it purposefully opaque so that it's harder to resume work without Codex once you're using it agentically. Claude is still much better at writing quality code that is fit for human consumption.

I don't think Astra's code is quite as bad as you say, but yeah while it's much better at non-annoying prose, the code definitely isn't quite as good as Opus 5.5.

Currently using GPT-6.1 Sol Medium/High for coding and I'm quite satisfied. I do have clear instructions and style guidelines though.

Same.

I'm so happy to not look at bogus jargon that Claude made up.

That largely ended with Opus 5.5.

Not for me.

Um., Codex is now suffering from the same thing afaict. It is almost as if having a duopoly is a bad thing for consumers.

... is it?