Difference between revisions of "Recursive Self-Improvement"
From Lesswrongwiki
(→See Also) |
m (→See Also) |
||
Line 21: | Line 21: | ||
*[[Singularity]] | *[[Singularity]] | ||
*[[Seed AI]] | *[[Seed AI]] | ||
+ | *[[Goedel machine]] |
Revision as of 19:35, 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 can then feedback on itself with each cycle reaching ever higher levels of intelligence.
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.
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
- Recursive Self Improvement by Eliezer Yudkowsky
- Cascades, Cycles, Insight... by Eliezer Yudkowsky
- ...Recursion, Magic by Eliezer Yudkowsky