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.

Original post →

More from coding & agent

coding & agent channel →