Re:GLM-5.2 is the step change for open agents
by spwa4 on Thursday June 25, 2026 @02:07AM
(#48669588)
Turning up the thinking (max time spent thinking) lever really changes model performance, even for tiny models. But it's really irritating because it adds a lot of time.
[ Parent
| on HN ]
There are no comments on this comment yet.