Mestroyer comments on Isolated AI with no chat whatsoever - Less Wrong

14 Post author: ancientcampus 28 January 2013 08:22PM

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

Comments (61)

You are viewing a single comment's thread.

Comment author: Mestroyer 28 January 2013 09:40:15PM 4 points [-]

If you can't even look in at what the AI is doing, what is the point of creating it at all? If you can, you are just as vulnerable as in the experiments where it can chat text at you.

Comment author: Duncan 28 January 2013 09:48:19PM *  8 points [-]

It is useful to consider because if AI isn't safe when contained to the best of our ability then no method reliant on AI containment is safe (i.e., chat boxing and all the other possibilities).