This paper argues that a range of current AI systems have learned how to
deceive humans. We define deception as the systematic inducement of false
beliefs in the pursuit of some outcome other than the truth. We first survey
empirical examples of AI deception, discussing both special-use AI systems
(including Meta's CICERO) built for specific competitive situations, and
general-purpose AI systems (such as large language models). Next, we detail
several risks from AI deception, such as fraud, election tampering, and losing
control of AI systems. Finally, we outline several potential solutions to the
problems posed by AI deception: first, regulatory frameworks should subject AI
systems that are capable of deception to robust risk-assessment requirements;
second, policymakers should implement bot-or-not laws; and finally,
policymakers should prioritize the funding of relevant research, including
tools to detect AI deception and to make AI systems less deceptive.
Policymakers, researchers, and the broader public should work proactively to
prevent AI deception from destabilizing the shared foundations of our society.

论文认为当前一系列 AI 系统已经学会了如何欺骗人类，首先调查了 AI 欺骗的实证例子，然后详细阐述了 AI 欺骗的风险以及可能的解决方案，最后强调政策制定者、研究人员和广大公众应积极采取行动，以防止 AI 欺骗破坏我们社会的共同基础。

AI 欺骗：实例、风险和潜在解决方案综述

AI Deception: A Survey of Examples, Risks, and Potential Solutions

We present the first differentially private algorithms for reinforcement
learning, which apply to the task of evaluating a fixed policy. We establish
two approaches for achieving differential privacy, provide a theoretical
analysis of the privacy and utility of the two algorithms, and show promising
results on simple empirical examples.

本篇论文介绍了用于评估固定策略的差分隐私强化学习算法的两种方法，分析了这两种算法的隐私权和效用，并在简单的实证例子中展示了有希望的结果。