Less Wrong is a community blog devoted to refining the art of human rationality. Please visit our About page for more information.

Roland2 comments on Nonsentient Optimizers - Less Wrong

16 Post author: Eliezer_Yudkowsky 27 December 2008 02:32AM

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

Comments (47)

Sort By: Old

You are viewing a single comment's thread.

Comment author: Roland2 27 December 2008 08:02:09PM 1 point [-]

Eliezer, I don't understand the following:

probably via resolving some other problem in AI that turns out to hinge on the same reasoning process that's generating the confusion

If you use the same reasoning process again what help can that be? I would suppose that the confusion can be solved by a new reasoning process that provides a key insight.

As for the article one idea I had was that the AI could have empathy circuits like we have, yes, the modelling of humans would be restricted but good enough I hope. The thing is, would the AI have to be sentient in order for that to work?