HoverHell comments on Building Phenomenological Bridges - Less Wrong
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 (116)
The mapping might be relatively easy to check (i.e. hard to construct a misleadement that would look plausible).
Misleading an agent to believe that agent has a different utility function could be more interesting though.