Difference between revisions of "Recursive Self-Improvement"

From Lesswrongwiki
Jump to: navigation, search
(External Links)
(Redirected page to Recursive self-improvement)
Line 1: Line 1:
'''Recursive Self-Improvement''' is an approach to [[Artificial Intelligence]] that allows a system to make adjustments to its own functionality resulting in improved performance. The system could then feedback on itself with each cycle reaching ever higher levels of intelligence resulting in either a Hard or Soft [[AI takeoff]].
#REDIRECT [[Recursive self-improvement]]
Such a system would be bound by the limitations of it's hardware. The software would be searching for cognitive algorithms that were the most optimal.
==Blog Posts==
*[http://lesswrong.com/lw/we/recursive_selfimprovement/ Recursive Self Improvement] by Eliezer Yudkowsky
*[http://lesswrong.com/lw/w5/cascades_cycles_insight/ Cascades, Cycles, Insight...] by Eliezer Yudkowsky
*[http://lesswrong.com/lw/w6/recursion_magic/ ...Recursion, Magic] by Eliezer Yudkowsky
==External Links==
*[http://intelligence.org/upload/LOGI/seedAI.html Seed A.I] description from Singularity Institute.
*[http://intelligence.org/upload/artificial-intelligence-risk.pd Risks from Artificial Intelligence] by Eliezer Yudkowsky.
*[http://www.xuenay.net/Papers/DigitalAdvantages.pdf Advantages of Artificial Intelligence] by Kaj Sotala
*[http://commonsenseatheism.com/wp-content/uploads/2011/02/Good-Speculations-Concerning-the-First-Ultraintelligent-Machine.pdf Speculations Concerning the First Ultraintelligent Machine] by I.J. Good
==See Also==
*[[Evolutionary Algorithm]]
*[[Intelligence explosion]]
*[[Seed AI]]
*[[Goedel machine]]
*[[AI takeoff]]
*[[Hard takeoff]]
*[[Soft takeoff]]

Latest revision as of 06:10, 30 June 2012