LESSWRONG
LW

1161

Why Not Try Build Safe AGI?

Why Not Try Build Safe AGI?

Dec 24, 2022 by Remmelt

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)

3y

9

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

3y

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

3y

0

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

3y

1