News for hackers. Stuff that matters.
Re:A Jev that can ask Opus for help gives Opus accuracy at 4... by gbrindisi on Friday November 06, 2026 @03:21PM (#50397899)
Excellent read. I use the same hybrid approach for a lot of security engineering work and it’s working well after initial calibrations, for example for our own harness we rebuilt auto mode exactly like this to judge tool calls and intent.
Re:A Jev that can ask Opus for help gives Opus accuracy at 4... by morsch on Friday November 06, 2026 @03:45PM (#50398259)
I had the same idea, I extended opencode-warden to use a local decision model to validate tool inputs and outputs. It seems to work... ok? d1 is fast enough to run locally on an old 1080 GTX. Not sure if I can recommend relying on it.