News for hackers. Stuff that matters.
Re:Senior SWE-Bench: open-source benchmark that assesses age... by olmo23 on Thursday July 02, 2026 @02:37AM (#48757381)
With a human at its disposal, it could probably count the number of R's in strawberry!

In all seriousness though, adding capabilities should not normally reduce the effectiveness of a model (within reason: don't pollute the context window with millions of useless tools).

There are no comments on this comment yet.