Yoav Goldberg: Reading Weights Is More Impressive Than Writing Them From Scratch

Yoav Goldberg praised recent experiments that interpret neural network functionality directly from their weights, saying such work—including fixing models by editing biases—is more impressive than hand-writing weights from scratch, which he finds unsurprising and mechanical.

2026-11-03 ~ 2026-11-03 · 3 related posts

• yoavgo: inferring network behavior from weights impresses him; hand-writing weights is just scaled-up exam tasks — yoavgo · 2026-11-03
• Yoav Goldberg Weighs In on Weight-Interpretation Experiments: Fixing Models by Editing Biases Is More Stunning Than Writ… — yoavgo · 2026-11-03
• Yoav Goldberg: Editing model weights is mechanical once we can read them — yoavgo · 2026-11-03