Document Type
Article
Publication Date
9-29-2020
Department
Computer Engineering and Computer Science
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.
ThinkIR Citation
Miller, James D.; Yampolskiy, Roman; Häggström, Olle; and Armstrong, Stuart, "Chess as a testing grounds for the oracle approach to AI safety" (2020). Faculty and Staff Scholarship. 549.
https://ir.library.louisville.edu/faculty/549
ORCID
0000-0001-9637-1161
