News for hackers. Stuff that matters.
Re:In 27,280 coding agent runs, 64% of inference spend went ... by Edward40 on Tuesday November 17, 2026 @12:04PM (#50534490)
Cutting the system prompt and tools is easy. Cutting steps requires understanding the model's RL strategy and how it was trained to explore.
Re:In 27,280 coding agent runs, 64% of inference spend went ... by bisonbear on Tuesday November 17, 2026 @12:17PM (#50534736)
I wonder if Claude Code would do better given they just introduced code mode, which should significantly cut the number of steps required