Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Semgrep: GLM 5.2 beats Claude in our Cyber Benchmarks. Parent comment
Isn't DeepSeek half as good and 20x cheaper?
"Half as good" sounds bad but for most trivial tasks I've found it more than good enough. (Why would I want to waste my Frontier AI Tokens on those?)
There are no comments on this comment yet.
Isn't DeepSeek half as good and 20x cheaper?
"Half as good" sounds bad but for most trivial tasks I've found it more than good enough. (Why would I want to waste my Frontier AI Tokens on those?)