|国家预印本平台
首页|Artificial Intelligent Disobedience: Rethinking the Agency of Our Artificial Teammates

Artificial Intelligent Disobedience: Rethinking the Agency of Our Artificial Teammates

Artificial Intelligent Disobedience: Rethinking the Agency of Our Artificial Teammates

来源:Arxiv_logoArxiv
英文摘要

Artificial intelligence has made remarkable strides in recent years, achieving superhuman performance across a wide range of tasks. Yet despite these advances, most cooperative AI systems remain rigidly obedient, designed to follow human instructions without question and conform to user expectations, even when doing so may be counterproductive or unsafe. This paper argues for expanding the agency of AI teammates to include \textit{intelligent disobedience}, empowering them to make meaningful and autonomous contributions within human-AI teams. It introduces a scale of AI agency levels and uses representative examples to highlight the importance and growing necessity of treating AI autonomy as an independent research focus in cooperative settings. The paper then explores how intelligent disobedience manifests across different autonomy levels and concludes by proposing initial boundaries and considerations for studying disobedience as a core capability of artificial agents.

Reuth Mirsky

计算技术、计算机技术

Reuth Mirsky.Artificial Intelligent Disobedience: Rethinking the Agency of Our Artificial Teammates[EB/OL].(2025-06-27)[2025-07-16].https://arxiv.org/abs/2506.22276.点此复制

评论