News for hackers. Stuff that matters.
Re:GLM-5.2 is the new leading open weights model on Artifici... by BoorishBears on Wednesday June 17, 2026 @06:43PM (#48578025)
Reasoning models can coaxed to reason like they do in dedicated reasoning blocks, outside of those blocks: in normal parts of the response.

But Anthropic at least has openly admitted they try to detect that and interfere

There are no comments on this comment yet.