You’re more worried about a corrigoble superintelligence than a value aligned ASI.
Yes, a dumb enough set of humans could make a mess even with an instruction following ASI. But it would take a really weird set of jagged capabilities for an ASI to not take effective precautions with its technologies.
You’re more worried about a corrigoble superintelligence than a value aligned ASI.
Yes, a dumb enough set of humans could make a mess even with an instruction following ASI. But it would take a really weird set of jagged capabilities for an ASI to not take effective precautions with its technologies.