Top postsTop post
Previously, we've shared a few higher-effort project proposals relating to AI control in particular. In this post, we'll share a whole host of less polished project proposals. All of these projects excite at least one Redwood researcher, and high-quality research on any of these problems seems pretty valuable. They differ...
Produced as part of the ML Alignment & Theory Scholars Program - Winter 2024-25 Cohort TL;DR We did a small pilot test of human auditing to understand better how it fits into the AI control agenda. We used LLMs to generate interesting code backdoors, and had humans audit suspicious backdoored...