生物化学家
欺骗
化学
认知科学
心理学
历史
经典
社会心理学
作者
Bertil Hille,Ken Mackie,Yvonne Lai
标识
DOI:10.1073/pnas.2408158121
摘要
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. ...Large language models (LLMs) are currently at the forefront of intertwining AI systems with human communication and everyday life. Thus, aligning them with human values is of great importance. However, given the steady increase in reasoning abilities, ...
科研通智能强力驱动
Strongly Powered by AbleSci AI