I'm currently "working" on a toy 3d Vulkan Physx thingy. It has a simple raycast vehicle and I'm trying to replace it with the PhysX5 built in one (https://nvidia-omniverse.github.io/PhysX/physx/5.6.1/docs/Ve...)

I point it to example snippets and webdocumentation but the code it gens won't work at all, not even close

Opus4.6 is a tiny bit less wrong than Codex 5.4 xhigh, but still pretty useless.

So, after reading all the success stories here and everywhere, I'm wondering if I'm holding it wrong or if it just can't solve everything yet.

I have also switched from claude to codex a few weeks ago. After deciding to let agents only do focused work I needed less context, and the work was easier to review. Then I realized codex can deliver the same quality, and it's paid through my subscription instead of per token.

Codex has been good quality wise, but I hit limits on the Codex team subscription so quickly it's almost more hassle that it is worth.

I made this switch months ago, ChatGPT 5.4 being a smarter model, but I’ve had subjective feelings of degradation even on 5.4 lately. There’s a lot of growth in usage right now so not sure what kind of optimizations their doing at both companies

I use Codex at home and Opus at work. They're both brilliant.

I would switch to Codex, but Altman is such a naked sociopath and OpenAI so devoid of ethical business practices that I can't in good conscience. I'm not under any illusion that Anthropic is ethical, but it is so far a step up from OpenAI.