Alex_Altair comments on Superintelligent AGI in a box - a question. - Less Wrong

14 Post author: Dmytry 23 February 2012 06:48PM

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

Sort By: Best

You are viewing a single comment's thread.

Comment author: Alex_Altair 23 February 2012 08:50:17PM 18 points [-]

I am increasingly convinced of my inability to derive what an AGI will do.

Comment author: Larks 24 February 2012 11:55:21AM 4 points [-]

We can lower bound it more easily than we can upper bound it, which is the important thing for many practical purposes.

Comment author: Dmytry 23 February 2012 10:44:00PM 4 points [-]

Well, at least you should expect smarter-than-you AI to be able to come up with things more effective than the ones you can come up with.

Comment author: kmacneill 23 February 2012 09:36:11PM 0 points [-]

we just have to be right the first time.

Comments (77)