This is something that I think is neglected (in part because it’s not the relevant problem yet) in thinking about friendly AI. Even if we had solved all of the problems of stable goal systems, there could still be trouble, depending on who’s goals are implemented. If it’s a fast take-off, whoever cracks recursive self-improvement first, basically gets Godlike powers (in the form a genii that reshapes the world according to your wish). They define the whole future of the expanding visible universe. There are a lot of institutions who I do not trust to have the foresight to think “We can create utopia beyond anyone’s wildest dreams” and instead to default to “We’ll skewer the competition in the next quarter.”
However, there are unsubstantiated rumors that Google has taken some ex-MIRI people for work on a project of some kind.
This is something that I think is neglected (in part because it’s not the relevant problem yet) in thinking about friendly AI. Even if we had solved all of the problems of stable goal systems, there could still be trouble, depending on who’s goals are implemented. If it’s a fast take-off, whoever cracks recursive self-improvement first, basically gets Godlike powers (in the form a genii that reshapes the world according to your wish). They define the whole future of the expanding visible universe. There are a lot of institutions who I do not trust to have the foresight to think “We can create utopia beyond anyone’s wildest dreams” and instead to default to “We’ll skewer the competition in the next quarter.”
However, there are unsubstantiated rumors that Google has taken some ex-MIRI people for work on a project of some kind.