This is a fair point. Models are usually good at finding connections. The currect index is a mixture of different categories, although I split them into coding, reasoning, etc,. I wish I could make the use cases and prompt context more visible on the website.

Thanks for pointing this out. You're right, it's hard for users to validate the comments without the links to original comments. I included those links on web before but removed them because I was being cautious about platform data-usage policies. I realize this may reduce the transparency. I will add them back and document more on data source selection and processing. Thanks again. This is very useful.

I want to have the same thing, but tbh it's too complicated with so many configuratios and plugins. I doubt if any comparison of harness make sense now and can be applied in real coding works.

Can't that be sidestepped by comparing harnesses 'out of the box'

I think their backend data probably shows that very few Chinese users are using Codex through the official way, and the number of those who have switched to the Chinese interface is even smaller, so there’s not much incentive to fix this issue.

I don’t think GPT-5.6 would make such a basic mistake when reviewing CodeX itself.

Because all Chinese users must use a VPN to access Codex.

becuase most people don't care whether it's accurate, as long as it looks right and is funny...

It doesn't look right at all.

But it does look funny