I've chosen problems with non-negotiable outcomes. In other words, problem domains where you either are able to clearly accomplish the very hard thing, or not, and there's no grey area. I've purposely chosen these kinds of problems to prove what AI agents are capable of, so that there is no debate in my mind. And with Codex I've accomplished the previously impossible. Unambiguously. Codex did this. Claude gave up.
It's as if there are two vendors saying they can give up incredibly superpowers for an affordable price, and only one of them actually delivers the full package. The other vendor's powers only work on Tuesdays, and when you're lucky. With that situation, in an environment as competitive as things currently stand, and given the trajectory we're on, Claude is an absolute non-starter for me. Without question.
I don’t think Claude is actually incapable, you just spend a lot of time telling it to yes, please actually do the difficult thing. Do not give up halfway through.
Codex says “This is a lot of work, let me plan really well.”
Claude says “This is a lot of work, let me step back and do something completely different that you didn’t ask for.”
It's as if there are two vendors saying they can give up incredibly superpowers for an affordable price, and only one of them actually delivers the full package. The other vendor's powers only work on Tuesdays, and when you're lucky. With that situation, in an environment as competitive as things currently stand, and given the trajectory we're on, Claude is an absolute non-starter for me. Without question.