[Research Note] Detecting Research Sabotage with Debate & Slopvestigators
by Joey Yudelson, Abhishu Oza, Kenzoheijman, and Marissa Liu
This work is ongoing as part of the SPAR program. The original proposal is here. TL;DR In the coming years, we will likely rely increasingly on AIs to do alignment research on our behalf. In that world, it seems pretty crucial to be able to robustly check untrusted research for...
Nov 1711