LESSWRONGWhy Not Try Build Safe AGI?
LW

Why Not Try Build Safe AGI?

Copy-pasting from my one-on-ones with AI Safety researchers:

-3Why mechanistic interpretability does not and cannot contribute to long-term AGI safety (from messages with a friend)

2y

9

6List #1: Why stopping the development of AGI is hard but doable

2y

11

1List #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 humans

2y

0

4List #3: Why not to assume on prior that AGI-alignment workarounds are available

2y

1