Vladimir_Nesov comments on That Magical Click - Less Wrong

58 Post author: Eliezer_Yudkowsky 20 January 2010 04:35PM

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

Comments (400)

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

Comment author: Vladimir_Nesov 26 January 2010 10:05:43PM 3 points [-]

An AI could persuade you to become a kangaroo -- this is a broken criterion for decision-making.

Comment author: Jack 26 January 2010 10:20:22PM 4 points [-]

I am skeptical that rationality and exponentially greater-than-human intelligence actually confers this power.

Comment author: Nick_Tarleton 26 January 2010 11:24:36PM *  5 points [-]

It doesn't matter if it does or not; the fact that you can conceive of situations where persuadability would fail as a criterion immediately means it fails.

Comment author: pdf23ds 26 January 2010 11:06:53PM 3 points [-]

Well, that was the big controversy over the AI Box experiments, so no need to rehash all that here.