Chess as a testing grounds for the oracle approach to AI safety
Paper i proceeding, 2021

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.


James D. Miller

Smith College

Roman V. Yampolskiy

University of Louisville

Olle Häggström

Chalmers, Matematiska vetenskaper, Tillämpad matematik och statistik

Stuart Armstrong

University of Oxford

CEUR Workshop Proceedings

16130073 (ISSN)

Vol. 2916

2021 Workshop on Artificial Intelligence Safety, AISafety 2021
Virtual, Online, ,



Språkteknologi (språkvetenskaplig databehandling)


Mer information

Senast uppdaterat