shminux comments on New paper from MIRI: "Toward idealized decision theory" - LessWrong
You are viewing a comment permalink. View the original post to see all comments and the full post content.
You are viewing a comment permalink. View the original post to see all comments and the full post content.
Comments (22)
I am not talking about optimal at all. Just being able to forensically detect any sign of agency rather than... what?