[Research Note] Detecting Research Sabotage with Debate & Slopvestigators
This work is ongoing as part of the SPAR program. The original proposal is here.TL;DRIn 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 subtle sabotage, even when the research tasks are fuzzy and the automated researchers are extremely smart. This seems like a great use case for scalable oversight methods. To that end we directly tested the sabotage detecti...
Read full article →