Zobrazeno 1 - 10
of 226
pro vyhledávání: '"Yampolskiy, Roman"'
In this thorough study, we took a closer look at the skepticism that has arisen with respect to potential dangers associated with artificial intelligence, denoted as AI Risk Skepticism. Our study takes into account different points of view on the top
Externí odkaz:
http://arxiv.org/abs/2303.03885
Autor:
Wittkotter, Erland, Yampolskiy, Roman
Artificial Superintelligence (ASI) that is invulnerable, immortal, irreplaceable, unrestricted in its powers, and above the law is likely persistently uncontrollable. The goal of ASI Safety must be to make ASI mortal, vulnerable, and law-abiding. Thi
Externí odkaz:
http://arxiv.org/abs/2112.11184
Autor:
Brcic, Mario, Yampolskiy, Roman V.
Publikováno v:
ACM Computing Surveys, 2023
An impossibility theorem demonstrates that a particular problem or set of problems cannot be solved as described in the claim. Such theorems put limits on what is possible to do concerning artificial intelligence, especially the super-intelligent one
Externí odkaz:
http://arxiv.org/abs/2109.00484
Autor:
Burkhardt, Micah, Yampolskiy, Roman V.
Death has long been overlooked in evolutionary algorithms. Recent research has shown that death (when applied properly) can benefit the overall fitness of a population and can outperform sub-sections of a population that are "immortal" when allowed t
Externí odkaz:
http://arxiv.org/abs/2109.13744
Autor:
Yampolskiy, Roman V.
In this work, we survey skepticism regarding AI risk and show parallels with other types of scientific skepticism. We start by classifying different types of AI Risk skepticism and analyze their root causes. We conclude by suggesting some interventio
Externí odkaz:
http://arxiv.org/abs/2105.02704
As AI technologies increase in capability and ubiquity, AI accidents are becoming more common. Based on normal accident theory, high reliability theory, and open systems theory, we create a framework for understanding the risks associated with AI app
Externí odkaz:
http://arxiv.org/abs/2104.12582
In the last years, AI safety gained international recognition in the light of heterogeneous safety-critical and ethical issues that risk overshadowing the broad beneficial impacts of AI. In this context, the implementation of AI observatory endeavors
Externí odkaz:
http://arxiv.org/abs/2012.02592
To reduce the danger of powerful super-intelligent AIs, we might make the first such AIs oracles that can only send and receive messages. This paper proposes a possibly practical means of using machine learning to create two classes of narrow AI orac
Externí odkaz:
http://arxiv.org/abs/2010.02911