PeerInfinity comments on Friendly AI Research and Taskification - Less Wrong

22 Post author: multifoliaterose 14 December 2010 06:30AM

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

Comments (44)

You are viewing a single comment's thread.

Comment author: PeerInfinity 17 December 2010 08:45:05PM 2 points [-]

"I don't even see how one would start to research the problem of getting a hypothetical AGI to recognize humans as distinguished beings."

I'm still not convinced that human beings should be treated as a special case, as opposed to getting the AGI to recognize sentient beings in general. It's easy to imagine ways in which either strategy could go horribly wrong.