Stuart_Armstrong comments on Heroin model: AI "manipulates" "unmanipulatable" reward - All
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 (10)
Replace "force the human to take heroin" with "gives the human a single sock" and "the human subsequently seeks out heroin" with "the human subsequently seeks out another sock". The formal structure of this can correspond to something quite acceptable.