News for hackers. Stuff that matters.
Re:In 27,280 coding agent runs, 64% of inference spend went ... by BugsJustFindMe on Tuesday November 17, 2026 @12:34PM (#50535025)
This is nice and all, but I really want to see the best harness for ChatGPT and Claude, not just open weight models.

There are no comments on this comment yet.