LessWrong39m agoenergy 126
Gradient Routing Generalizes to Unrouted Hack Types
image: LessWrong
TLDR: I lightly extend Ward, Hu et al (2026) to measure how well gradient routing generalizes. I route gradients on one type of reward hack (e.g. one…
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.