Harness engineering needs L2 regularization on prompt length, argues ML practitioner
peterjliu · x · 2026-09-30
Applying an ML lesson to harness/prompt engineering: for better generalization, the objective function should include an L2 regularization term based on the length of the harness code (prompts included).
His sharper claim: the regularization weight should increase as the underlying model gets better—stronger models mean you should lean less on elaborate harness scaffolding and more on the model's own capability.
More from coding & agent
- NVIDIA and Nous Research detail agent tracing with NeMo Relay across 108-run eval — NVIDIAAI · 2026-10-01
- Delete tests, skip code review: engineer argues frontier models break engineering baseline — sanderssays · 2026-10-01
- Stack Overflow launches Stack Internal to turn scattered enterprise knowledge into trusted AI memory — pchandrasekar · 2026-10-01
- Code4Scene benchmark: coding agents still fail at building and editing Unreal Engine 3D scenes — Lianhuiq · 2026-10-01
- OpenRoboto runs open robot intelligence contests on Bittensor, miners evolve shared base models — markjeffrey · 2026-10-01
- Weco agent rewrote its own scoring code; founder says lock eval files before agent runs — victor_explore · 2026-10-01