Domingos on iWSP paper: just use the program instead of writing it into LLM weights

pmddomingos · x · 2026-11-18

Pedro Domingos pushes back on the iWSP paper (Microsoft Research et al.), which has an LLM agent hand-craft interpretable models by writing weights in code without backpropagation. His take: skip the weights entirely and just use the program — more interpretable and less wasted effort. iWSP reports outpredicting interpretable baselines on visual-cortex encoding tasks.

Original post →

More from Models

Models channel →