Btw, I think GLM-5.1 was trying to do something very ambitious here, and failed due to fumbling step size
令人惊讶的是：GLM-5.1作为一个先进AI模型，竟然因为'步长处理不当'这种技术细节而失败，这表明即使是顶级AI也可能在基础执行层面出现问题，而不仅仅是概念设计上的不足。
2 Matching Annotations
- Last 7 days
-
-
- Dec 2020
-
github.com github.com
-
I don't think this is what really matters at the end, since whatever is the implementation the goal should be to provide a library that people actually like to use.
-