Deception abilities emerged in large language models

作者：Thilo Hagendorff · 发表于：Proceedings of the National Academy of Sciences of the United States of America · 年份：2023 · DOI：10.1073/pnas.2317967121 · 被引用次数：191 · 研究领域：Medicine、Computer Science

Significance This study unravels a concerning capability in Large Language Models (LLMs): the ability to understand and induce deception strategies. As LLMs like GPT-4 intertwine with human communication, aligning them with human values becomes paramount. The paper demonstrates LLMs’ potential to create false beliefs in other agents within deception scenarios, highlighting a critical need for ethical considerations in the ongoing development and deployment of such advanced AI systems.