I’m not sure what you mean by
Hanson is on the same page as the rest of SIAI with regard to expected utility
As Holden and Eliezer both explicitly state, SIAI itself rejects the “but there’s still a chance” argument.
It all depends on how small that small chance is. Pascal mugging is typically done with probabilities that are exponentially small, e.g. 10^-10 or so.
But what about if Holden is going to not recommend SIAI for donations when there’s a 1% or 0.1% chance of it making that big difference.
I’m not sure what you mean by
As Holden and Eliezer both explicitly state, SIAI itself rejects the “but there’s still a chance” argument.
It all depends on how small that small chance is. Pascal mugging is typically done with probabilities that are exponentially small, e.g. 10^-10 or so.
But what about if Holden is going to not recommend SIAI for donations when there’s a 1% or 0.1% chance of it making that big difference.