In the linked thread there was a discussion of standard security practices; Zack pointed out that these are generally for making people act against their interests, but this was not considered a sufficient objection to some in the thread, who thought that researchers acting against their own interests could build FAI.
Are you saying that MIRI enforces altruism in their employees? If so, how do they do that, exactly?
In the linked thread there was a discussion of standard security practices; Zack pointed out that these are generally for making people act against their interests, but this was not considered a sufficient objection to some in the thread, who thought that researchers acting against their own interests could build FAI.