The world is at risk from a superintelligence-gone-wrong;
The SIAI can help to do something about that.
Both propositions seem debatable. For the first point, certainly some scenarios are better than others—but the superintelligence causing widespread havoc by turning on its creators hypothesises substantial levels of incompetence, followed up by a complete failure of the surrounding advanced man-machine infrastructure to deal with the problem. Most humans may well have more to fear from a superintelligence-gone-right, but in dubious hands.
Two key propositions seem to be:
The world is at risk from a superintelligence-gone-wrong;
The SIAI can help to do something about that.
Both propositions seem debatable. For the first point, certainly some scenarios are better than others—but the superintelligence causing widespread havoc by turning on its creators hypothesises substantial levels of incompetence, followed up by a complete failure of the surrounding advanced man-machine infrastructure to deal with the problem. Most humans may well have more to fear from a superintelligence-gone-right, but in dubious hands.