algorithm314·5 か月前·議論Can't they just run the output through a compiler to get feedback? Syntax errors seem easier to get right.
algorithm314·5 か月前·議論Here is the pricing per M tokens. https://docs.z.ai/guides/overview/pricingWhy is GLM 5 more expensive than GLM 4.7 even when using sparse attention?There is also a GLM 5-code model.
algorithm314·10 年前·議論support binary literals with 0b prefix. Also include rotate ,count leading zeroes,count trailing zeros and popcount as functions.