What do those mental knots really look like?

 

My first thoughts are dynamical systems knots, an interplay between knot theory 
and systems dynamics. Perhaps there are ways to categorize the ones humans 
encounter so they can be avoided in AGI. Who knows how many there are and how 
varied.

 

The tormenting of others might be a pattern some follow in an attempt to 
utilize other agents besides themselves to untangle. To avoid those patterns, 
to suppress them, might be mere pattern detection on particular knot 
categories, branching to alternatives while maintaining systems control. 

 

Sounds too simple though, some of those "knots" may represent some of the 
finest and desirable qualities of human beings individually and collectively. 
Perhaps that includes somehow reaching a general intelligence evolutionarily. 
Torment and intelligence might hand in hand. Some of our most intelligent 
specimens have the most twisted, devious and devilish minds.

 

John

 

From: Ben Goertzel [mailto:[email protected]] 
Sent: Saturday, January 2, 2016 11:30 PM
To: AGI <[email protected]>
Subject: [agi] "The torTuring test" --

 

-- if an AGI can torment itself and others psychologically just like humans 
can, it must have human-like intelligence

 

(?) ;)




 

-- 

Ben Goertzel, PhD
http://goertzel.org

"The reasonable man adapts himself to the world: the unreasonable one persists 
in trying to adapt the world to himself. Therefore all progress depends on the 
unreasonable man." -- George Bernard Shaw


AGI |  <https://www.listbox.com/member/archive/303/=now> Archives  
<https://www.listbox.com/member/archive/rss/303/248029-82d9122f> |  
<https://www.listbox.com/member/?&;> Modify Your Subscription

 <http://www.listbox.com> 

 




-------------------------------------------
AGI
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-f452e424
Modify Your Subscription: 
https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657
Powered by Listbox: http://www.listbox.com

Reply via email to