Document Type
Article
Publication Date
9-2020
Abstract
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 oracles that would provide chess advice: those aligned with the player's interest, and those that want the player to lose and give deceptively bad advice. The player would be uncertain which type of oracle it was interacting with. As the oracles would be vastly more intelligent than the player in the domain of chess, experience with these oracles might help us prepare for future artificial general intelligence oracles.
DOI
10.48550/arXiv.2010.02911
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Rights
Licensed to Smith College and distributed CC-BY under the Smith College Faculty Open Access Policy.
Recommended Citation
Miller, James; Yampolskiy, Roman V.; Häggström, Olle; and Armstrong, Stuart, "Chess as a Testing Grounds for the Oracle Approach to AI Safety" (2020). Economics: Faculty Publications, Smith College, Northampton, MA.
https://scholarworks.smith.edu/eco_facpubs/58
Comments
Author’s submitted manuscript.