Kaj_Sotala comments on Friendly AI ideas needed: how would you ban porn? - Less Wrong

6 Post author: Stuart_Armstrong 17 March 2014 06:00PM

You are viewing a comment permalink. View the original post to see all comments and the full post content.

Comments (80)

You are viewing a single comment's thread. Show more comments above.

Comment author: Kaj_Sotala 18 March 2014 11:32:10AM 1 point [-]

The fact that individual humans often have trouble classifying edge cases demonstrates that even when you look at a single person's concept, it will still contain some uncertainty.

Related paper. Also sections 1 and 2 of this paper.