Vladimir_Nesov comments on Human values differ as much as values can differ - Less Wrong

13 Post author: PhilGoetz 03 May 2010 07:35PM

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

Comments (205)

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

Comment author: Vladimir_Nesov 04 May 2010 03:57:49PM 0 points [-]

BTW, how do you let the AI solve the problem of what kind of AI to build?

What kind of AI to be. That's the essence of being a computationally complex algorithm, and decision-making algorithm in particular: you always learn something new about what you should do, and what you'll actually do, and not just learn it, but make it so.