Stuart_Armstrong comments on An Oracle standard trick - Less Wrong

4 Post author: Stuart_Armstrong 03 June 2015 02:17PM

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

Comments (33)

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

Comment author: Stuart_Armstrong 05 June 2015 11:44:50AM 1 point [-]

It might happen. "accuracy" could involve the AI answering with the positions of trillions of atoms, which is not human parsable. So someone might code "human parsable" as "a human confirms the message is parsable".