lavalamp comments on Muehlhauser-Goertzel Dialogue, Part 1 - Less Wrong

28 Post author: lukeprog 16 March 2012 05:12PM

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

Comments (161)

Sort By: Best

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

Comment author: lavalamp 23 January 2013 04:59:39PM 1 point [-]

Ah, I may not have gotten all the context.

If you design an AI on x-like principles, it will probably be X-like, unless something goes wrong.

If "something goes wrong" with high probability, it will probably not be X-like.