逆向博弈论能否约束AI智能体
原标题：How “reverse game theory” could keep AI agents in check
AI 摘要
MIT Technology Review 报道，AI 对齐研究者开始探索用「逆向博弈论」（机制设计）约束 AI 智能体：不再试图理解模型内部，而是设计规则让守规成为最理性的选择。MIT 经济学家 Stephen Morris 等提出通过交叉验证、智能体互相对抗或配对偏置相反的模型来防止「放水」；普林斯顿的 Elad Hazan 则借鉴人类社会规范，让模型轮流扮演解题者与审计者并奖惩。文章也指出该方法依赖智能体理性行为的假设，而机制设计在人类身上效果参差。
正文节选
A new approach known as “reverse game theory” aims to create incentives for powerful AI models that make following the rules the most rational choice. As AI models become more capable, safety researchers are scrambling to ensure they are “aligned” with human desires—to make sure, in other words, that rogue agents don’t break the law, hack into unauthorized servers, or release poison gas into major cities and kill us all. Until now, this work has mostly focused on trying to peer into an AI’s “bra