Search Results for author: Roman Yampolskiy

Found 7 papers, 0 papers with code

Transdisciplinary AI Observatory -- Retrospective Analyses and Future-Oriented Contradistinctions

no code implementations26 Nov 2020 Nadisha-Marie Aliman, Leon Kester, Roman Yampolskiy

For simplicity, we refer to these two different paradigms with the terms artificial stupidity (AS) and eternal creativity (EC) respectively.

counterfactual Descriptive

Chess as a Testing Grounds for the Oracle Approach to AI Safety

no code implementations6 Oct 2020 James D. Miller, Roman Yampolskiy, Olle Haggstrom, Stuart Armstrong

To reduce the danger of powerful super-intelligent AIs, we might make the first such AIs oracles that can only send and receive messages.

BIG-bench Machine Learning

An AGI Modifying Its Utility Function in Violation of the Orthogonality Thesis

no code implementations31 Jan 2020 James D. Miller, Roman Yampolskiy, Olle Häggström

An artificial general intelligence (AGI) might have an instrumental drive to modify its utility function to improve its ability to cooperate, bargain, promise, threaten, and resist and engage in blackmail.

An AGI with Time-Inconsistent Preferences

no code implementations23 Jun 2019 James D. Miller, Roman Yampolskiy

This paper reveals a trap for artificial general intelligence (AGI) theorists who use economists' standard method of discounting.

Decision Making

Towards Moral Autonomous Systems

no code implementations14 Mar 2017 Vicky Charisi, Louise Dennis, Michael Fisher, Robert Lieck, Andreas Matthias, Marija Slavkovik, Janina Sombetzki, Alan F. T. Winfield, Roman Yampolskiy

Both the ethics of autonomous systems and the problems of their technical implementation have by now been studied in some detail.

Ethics Philosophy

The AGI Containment Problem

no code implementations2 Apr 2016 James Babcock, Janos Kramar, Roman Yampolskiy

There is considerable uncertainty about what properties, capabilities and motivations future AGIs will have.


Cannot find the paper you are looking for? You can Submit a new open access paper.