Difference between revisions of "Recursive Self-Improvement"

From Lesswrongwiki
Jump to: navigation, search
m (See Also)
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 can then feedback on itself with each cycle reaching ever higher levels of intelligence.
+
'''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]].
  
Assuming a machine of sufficient power was available, once an initial “escape velocity” had been reached the intelligence of such a system would be expected to accelerate rapidly and according to [[Eliezer Yudkowsky]] become capable in a matter of “weeks or hours” of achieving what would take humanity decades.
+
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.
 
 
Ultimately 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==
 
==Blog Posts==
Line 22: Line 20:
 
*[[Seed AI]]
 
*[[Seed AI]]
 
*[[Goedel machine]]
 
*[[Goedel machine]]
 +
*[[AI takeoff]]
 +
*[[Hard takeoff]]
 +
*[[Soft takeoff]]

Revision as of 21:36, 18 June 2012

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.

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

External Links

See Also