论文标题
国际象棋作为AI安全方法的测试理由
Chess as a Testing Grounds for the Oracle Approach to AI Safety
论文作者
论文摘要
为了减少强大的超级智能AIS的危险，我们可能会制作第一个只能发送和接收消息的AIS甲板。本文提出了一种使用机器学习来创建两类狭窄的AI型AI的可能实用方法，这些方法将提供国际象棋建议：与玩家的兴趣相符的人，以及那些希望玩家输掉并给出欺骗性的不良建议的人。玩家将不确定与哪种类型的甲骨文相互作用。由于口腔比国际象棋领域的玩家要聪明得多，因此使用这些口腔的经验可能有助于我们为未来的人工通用智能甲壳做准备。
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.
