Weight-Space Reading: LLMs predict weight-edit effects at 73% accuracy with zero forward passes

udmrzn · x · 2026-11-16

A new alphaXiv paper, "Weight-Space Reading" from Poindexter Labs, asks whether an LLM can predict how editing a network's weights will change its behavior — without ever running the model.

Setup and findings:

The authors distill four rules for evaluating weight reading and release the evaluation harness.

Original post →

More from Research

Research channel →