A note about why GLM 5.1 over Kimi 2.6. I found the former to be more capable on domains I'm working on, significantly so. Composer 2.5 seems smarter than Kimi, but exhibits RL-fried behavior, which causes much friction in interactive coding…
GLM 5.1 outperforms Kimi 2.6, Composer 2.5 smarter but with RL-fried issues
By
–