On the Limits of Recursively Self-Improving AGI

Abstract

Self-improving software has been a goal of computer scientists since the founding of the field of Artificial Intelligence. In this work we analyze limits on computation which might restrict recursive self-improvement. We also introduce Convergence Theory which aims to predict general behavior of RSI systems.

DOI: 10.1007/978-3-319-21365-1_40

Extracted Key Phrases

Cite this paper

@inproceedings{Yampolskiy2015OnTL, title={On the Limits of Recursively Self-Improving AGI}, author={Roman V. Yampolskiy}, booktitle={AGI}, year={2015} }