Why Not Try Build Safe AGI?Remmelt24 Dec 2022 8:34 UTCCopy-pasting from my one-on-ones with AI Safety researchers:Why mechanistic interpretability does not and cannot contribute to long-term AGI safety (from messages with a friend)Remmelt19 Dec 2022 12:02 UTC−3 points9 comments31 min readLW linkList #1: Why stopping the development of AGI is hard but doableRemmelt24 Dec 2022 9:52 UTC6 points11 comments5 min readLW linkList #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 humansRemmelt24 Dec 2022 9:53 UTC1 point0 comments3 min readLW linkList #3: Why not to assume on prior that AGI-alignment workarounds are availableRemmelt24 Dec 2022 9:54 UTC4 points1 comment3 min readLW link