Software capable of improving itself has been a dream of computer scientists since the inception of the field. In this work we provide definitions for Recursively Self-Improving software, survey different types of self-improving software, review the relevant literature, analyze limits on computation restricting recursive self-improvement and introduce RSI Convergence Theory which aims to predict general behavior of RSI systems. Finally, we address security implications from self-improving intelligent software.
from cs.AI updates on arXiv.org http://ift.tt/1JEUNqF
via IFTTT
No comments:
Post a Comment