Posts
Comments
Comment by
Petal Pepperfly (petal-pepperfly) on
Convince me that humanity is as doomed by AGI as Yudkowsky et al., seems to believe ·
2022-05-06T16:42:09.119Z ·
LW ·
GW
I see no problems with your list. I would add that creating corrigible superhumanly intelligent AGI doesn't necessarily solve the AI Control Problem forever because its corrigibility may be incompatible with its application to the Programmer/Human Control Problem, which is the threat that someone will make a dangerous AGI one day. Perhaps intentionally.