News for hackers. Stuff that matters.
Re:GLM-5.2 is the new leading open weights model on Artifici... by FooBarWidget on Wednesday June 17, 2026 @12:19PM (#48572634)
With such ridiculously long thinking traces I'm surprised max outperforms high. After all, performance falls off a hill after a certain amount of context, and long thinking traces can fill that up really quickly.

There are no comments on this comment yet.