Chess as a Testing Grounds for the Oracle Approach to AI Safety
This addresses AI safety concerns for researchers by using chess as a testing ground, but it is incremental as it applies known concepts to a specific domain.
The paper tackles the problem of AI safety by proposing a method to create narrow AI oracles for chess that provide either aligned or deceptive advice, with the player uncertain of the oracle's type, to help prepare for future artificial general intelligence oracles.
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.