TRIZ-Ingenieur comments on Superintelligence 13: Capability control methods - Less Wrong

7 Post author: KatjaGrace 09 December 2014 02:00AM

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

Comments (44)

You are viewing a single comment's thread.

Comment author: TRIZ-Ingenieur 09 December 2014 07:24:11AM *  0 points [-]

Boxing and stunting combined can be very effective when an easy controllable weak AI gatekeeper restricts information that is allowed to get into the box. If we manage to educate an AI with humanistic experiences and values without any knowledge of classical programming languages, OSes and hardware engineering we minimize the risk of escaping. For self improvement we could teach how to influence and improve cognitive systems like its own. This system should use significantly different structures dissimilar to any known sequential programming language.

The growing AI will have no idea how our IT infrastructure works and even less how to manipulate it.