Lessons from building an automated research scaffold
Key takeaway
TL;DR.
Why it's on PDOOM
PDOOM selected this story for its alignment & control signals: Alignment.
AlignmentFrom LessWrong AI
TL;DR. We built a scaffold to speed up our own research and gather data on automated alignment research (AAR). It turned out to not be valuable for researcher uplift, but was useful for gathering certain failure modes of AAR. Going forward, we plan to study the broader failure modes of AAR and how these automated research systems can be monitored and analyzed.We’d like to thank Sid Baines, Andrew Draganov, Cameron Holmes and Daniel Tan for helpful comments.This work was carried out by the Alignm
By Alejandro Aristizabal