17Why mechanistic interpretability does not and cannot contribute to long-term AGI safety (from messages with a friend)Remmelt·3y ago·37m readRemmelt·3y ago·37m read33
24List #1: Why stopping the development of AGI is hard but doableRemmelt·3y ago·6m readRemmelt·3y ago·6m read22
3List #2: Why coordinating to align as humans to not develop AGI is a lot easier than, well... coordinating as humans with AGI coordinating to be aligned with humansRemmelt·3y ago·4m readRemmelt·3y ago·4m read
6List #3: Why not to assume on prior that AGI-alignment workarounds are availableRemmelt·3y ago·4m readRemmelt·3y ago·4m read