This is the problem with this bollocks. Outsourcing our brains at a per token rate. It'd be exciting if I didn't hand to pay Americans for it.
I'm testing glm5 on Claude code and opencode just to stop consuming American... Soo good so far!
Qwen works fine and requires paying no-one except a hardware vendor.
I'm testing glm5 on Claude code and opencode just to stop consuming American... Soo good so far!