LessWrong1h agoenergy 123
VPD's Evaluation Adversary Finds Systematic Defects in the Released Decomposition
image: LessWrong
TL;DR: adVersarial Parameter Decomposition (VPD) decomposes model weights into simple components and assigns labels that specify whether a component…
This source publishes only a summary in its feed, so the full article lives at the outlet. The link above and below goes to the original.