It helps a lot that Claude is just better. Codex isn't BAD, and in some narrow technical ways might even be more capable, but I find Claude to be hands-down the best collaborator of all the AI models and it has never been close.
Meanwhile codex is ... boring. It keeps chugging on, asking for "please proceed" once in a while. No drama. Which is in complete contrast with ChatGPT the chatbot, that is a completely unusable, arrogant, unhelpful, and confrontational. How they made both from the same loaf I dunno.
IDEK what that means, specific examples?
You are making tool X. It currently processes test dataset in 15 seconds. You ask claude code to implement some change. It modifies code, compiles, runs the test - the tool sits in a 100% CPU busyloop. Possible reactions on being told there is a busy loop:
"the program is processing large amount of data. This is normal operation. I will wait until it finishes. [sets wait timeout in 30 minutes]."
"this is certainly the result of using zig toolchain, musl libc malloc has known performance issues. Let me instead continue working on the plan."
"[checks env] There are performance issues when running in a virtual machine. This is a known problem."
"[kills the program]. Let me check if the issue existed previously. [git stash/checkout/build/run/stash pop]. Previous version did not have the issue. Maybe user has changed something in the code."
Bonus episode: since claude code "search" gadget is buggy, LLM often gets empty search results.
"The changes are gone! Maybe user delete the code? Let me restore last commited version [git checkout]. The function is still missing! Must be an issue with the system git. Let me read the repository directly."
Double whammy, I guess, because I also always downvote comments asking (or complaining) about a parent comment getting downvoted.
At first I found the Gemini Code Assist to be absolutely terrible, bordering on unusable. It would mess up parameter order for function calls in simple 200 line Python. But then I found out about the "model router" which is a layer on top which dynamically routes requests between the flash and pro model. Disabling it and always using the pro model did wonders for my results.
There are however some pretty aggressive rate limits that reset every 24 hours. For me it's okay though. As a hobbyist I only use it about 2-3 hours per day at most anyway.
codex often speaks in very dense technical terms that I'm not familiar with and tends to use acronyms I've not encountered so there's a learning curve. It also often thinks I'm providing feedback when I'm just trying to understand what it just said. But it does give nice explanations once it understands that I'm just confused.
And I've been absolutely amazed with Codex. I started using that with version ChatGPT 5.3-Codex, and it was so much better than online ChatGPT 5.2, even sticking to single page apps which both can do. I don't have any way to measure the "smarts" for of the new 5.4, but it seems similar.
Anyways, I'll try to get Claude running if it's better in some significant way. I'm happy enough the the Codex GUI on MacOS, but that's just one of several things that could be different between them.
Not Claude Code specifically, but you can try the Claude Opus and Sonnet 4.6 models for free using Google Antigravity.
Claude, IMO, is much better at empathizing with me as a user: It asks better questions, tries harder to understand WHY I'm trying to do something, and is more likely to tell me if there's a better way.
Both have plenty of flaws. Codex might be better if you want to set it loose on a well-defined problem and let it churn overnight. But if you want a back-and-forth collaboration, I find Claude far better.
I've had a list of pet projects that I've been adding to for years. For those, I just say the broad strokes and tell it to do it's best. Codex has done a really good job for most of them, sometimes in one shot, and my list of experiments is emptying. Only one notable exception where it had no idea what I was after.
I also have my larger project, which I hope to actually keep and use it. Same thing though, it's really hard to explain what's going on, and it acts on bad assumptions.
So if Claude is better at that, then having two tools makes a lot of sense to me.
Recently did the full transition to Claude, the model is great, but what I really love is how they seem to have landed on a clear path for their GUI/ecosystem. The cowork feature fits my workflows really well and connecting enterprise apps, skills and plugins works really well.
Haven’t been this excited about AI since GPT 4o launched.