pdf23ds comments on Above-Average AI Scientists - Less Wrong

21 Post author: Eliezer_Yudkowsky 28 September 2008 11:04AM

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

Comments (96)

Sort By: Old

You are viewing a single comment's thread.

Comment author: pdf23ds 30 September 2008 10:08:00PM 0 points [-]

Phil, you might already understand, but I was talking about formal proofs, so your main worry wouldn't be the AI failing, but the AI succeeding at the wrong thing. (I.e., your model's bad.) Is that what your concern is?