✳flâneur — a map of the web's best reading

Recursive Self-Improvement - LessWrong

lesswrong.com · 875 words · saved by 1 readers

Recursive Self-Improvement refers to the property of making improvements on one's own ability of making self-improvements. It is an approach to Artificial General 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. An agent can self-improve and get a linear succession of improvements, however if it is able to improve its ability of making self-improvements, then each step will yield exponentially more improvements then the previous one. Recursively self-improving AI is considered to be the push behind the intelligence explosion. While any sufficiently intelligent AI will be able to improve itself, Seed AIs are specifically designed to use recursive self-improvement as their primary method of gaining intelligence. Architectures that had not been designed with this goal in mind, su

x Recursive Self-Improvement — LessWrong Recursive Self-Improvement Edited by Alex_Altair , joaolkf , Kaj_Sotala , et al. last updated 20th May 2025 Recursive Self-Improvement refers to the property of making improvements on one's own ability of making self-improvements. It is an approach to Artificial General 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 . An agent can self-improve

Explore this link on the map →

saved by

related reading