Difference between revisions of "Unfriendly artificial intelligence"

From Lesswrongwiki
Jump to: navigation, search
Line 1: Line 1:
{{afwikilink}}
+
An '''Unfriendly Artificial Intelligence''' is a Strong AI capable of causing great harm to humanity, and having goals that make it useful for the AI to do so. The AI's goals don't need to be antagonistic to humanity's goals for it to be Unfriendly. [[Paperclip maximizer]] is an extreme example of Unfriendly AI that is indifferent to humanity. The concept of Unfriendly AI is contrasted by the concept of [[Friendly AI]].
  
An '''Unfriendly Artificial Intelligence''' is a Strong AI capable of causing great harm to humanity, and having goals that are opposed to humanity's goals. [[Paperclip maximizer]] is an extreme example of Unfriendly AI. The concept of Unfriendly AI is contrasted by the concept of [[Friendly AI]].
+
==See also==
 +
 
 +
*[[Friendly AI]]
 +
 
 +
==External references==
  
==See also==
+
*{{cite book
<!-- For related LWiki articles, formatted as a list -->
+
|chapter=Artificial Intelligence as a Positive and Negative Factor in Global Risk
*[[Friendly artificial intelligence]]
+
|author=Eliezer S. Yudkowsky
 +
|year=2008
 +
|title=Global Catastrophic Risks
 +
|publisher=Oxford University Press
 +
|url=http://yudkowsky.net/singularity/ai-risk}} ([http://intelligence.org/AIRisk.pdf PDF])
 +
*{{cite journal
 +
|title=The Basic AI Drives
 +
|author=Stephen M. Omohundro
 +
|url=http://selfawaresystems.com/2007/11/30/paper-on-the-basic-ai-drives/
 +
|journal=Frontiers in Artificial Intelligence and Applications
 +
|year=2008
 +
|publisher=IOS Press}} ([http://selfawaresystems.files.wordpress.com/2008/01/ai_drives_final.pdf PDF])
  
 +
{{stub}}
 
[[Category:Concepts]]
 
[[Category:Concepts]]

Revision as of 00:48, 16 June 2009

An Unfriendly Artificial Intelligence is a Strong AI capable of causing great harm to humanity, and having goals that make it useful for the AI to do so. The AI's goals don't need to be antagonistic to humanity's goals for it to be Unfriendly. Paperclip maximizer is an extreme example of Unfriendly AI that is indifferent to humanity. The concept of Unfriendly AI is contrasted by the concept of Friendly AI.

See also

External references