Artificial Intelligence (AI) systems have made remarkable progress, attaining super-human performance across various domains. This presents us with an opportunity to further human knowledge and improve human expert performance by leveraging the hidden knowledge encoded within these highly performant AI systems. Yet, this knowledge is often hard to extract, and may be hard to understand or learn from. Here, we show that this is possible by proposing a new method that allows us to extract new chess concepts in AlphaZero, an AI system that mastered the game of chess via self-play without human supervision. Our analysis indicates that AlphaZero may encode knowledge that extends beyond the existing human knowledge, but knowledge that is ultimately not beyond human grasp, and can be successfully learned from. In a human study, we show that these concepts are learnable by top human experts, as four top chess grandmasters show improvements in solving the presented concept prototype positions. This marks an important first milestone in advancing the frontier of human knowledge by leveraging AI; a development that could bear profound implications and help us shape how we interact with AI systems across many AI applications.

翻译：人工智能系统取得了显著进展，在各领域展现出超越人类的表现。这为我们提供了一个契机，通过挖掘这些高性能AI系统中蕴含的隐藏知识，来拓展人类知识并提升人类专家的表现。然而，这些知识往往难以提取，且可能难以理解或习得。本文表明，通过提出一种新方法，我们能够从AlphaZero中提取新的国际象棋概念——这一AI系统通过无人类监督的自对弈掌握了国际象棋。我们的分析表明，AlphaZero可能编码了超出人类现有知识范围的知识，但这些知识最终并非人类无法理解，且能够被成功学习。在一项人类研究中，我们证明了这些概念可以被顶尖人类专家习得：四位国际象棋特级大师在解决所呈现的概念原型局面时展现了提升。这标志着通过利用AI推进人类知识前沿的重要里程碑；这一发展可能产生深远影响，并帮助塑造我们在众多AI应用中与AI系统互动的方式。