for people in mainland china the only option now is Kimi K3+GLM 5.2 for their day to day work as Fable is blocked. for me i use Fable + codex when i was out of mainland china, it is good when you have options wherever you are in this world

The Codex one is the funniest to me — allowlisting git show by name and never looking at the arguments.

In the future, Americans will use Chinese models and Chinese people will use American models — and neither government will be able to do anything about it.

that is for me...

The baseline matters here: favorites win World Cups all the time. How often would "always pick the two pre-tournament favorites" have gotten the champion in these same 10 tournaments? Without that comparison, 10/10 tells us basically nothing.

France was far and away the pre-tournament favorite for 2026, if anything it's somewhat impressive that OP's model correctly predicted that they wouldn't make it.

Here's hoping they were right for England as well, but we'll find out soon enough.

That was exactly the point I was trying to make in this preprint. I appreciate your comment.

A package I maintain once ended up in exactly this state because of a sync script.

is it possible to run this install script on ubuntu? curl https://nobie.com/install.sh | sh

Yep, if you run into issues let me know :)

cool

any one have experience or comments on coli with glm5.2 vs codex with gpt5.4mini