Tag
#deep-dive
From News
News · 2026-07-04
Lilian Weng moves self-improvement from weight rewriting to the harness around the model
Lilian Weng’s 28 minute analysis frames harness engineering as the practical path to self-improvement: not a model secretly rewriting its weights, but the surrounding system that manages tools, context, memory and evals.
Read →News · 2026-06-24
Scaling laws are a budget map, not a crystal ball for AI
Lilian Weng revisits scaling laws and shows why they are most useful as a tool for allocating compute, data and parameters. The practical lesson is sober: extrapolation helps only while you remember how small the underlying experiments were.
Read →