Why AI Safety Requires Uncertainty, Incomplete Preferences, and Non-Archimedean Utilities
为何人工智能安全需要不确定性、不完全偏好和非阿基米德效用
机构 * School of Computer Science and Statistics, Trinity College Dublin(特里尼蒂大学计算机科学与统计学学院) ; Trinity Quantum Alliance, Trinity College Dublin(特里尼蒂量子联盟) ; Management in Networked and Digital Societies (MINDS) Department, Kozminski University(科津斯基大学网络化与数字化社会管理系)
专题命中 Agent评测 :agent(abstract);AI agent(abstract);分类 cs.AI
AI总结 本文探讨了人工智能安全需通过不确定性推理、不完全偏好处理和非阿基米德效用机制来实现