道德责任还是服从：我们希望从AI中得到什么？
Moral Responsibility or Obedience: What Do We Want from AI?
AI总结：
本文主张AI安全评估应从僵化服从转向评估伦理判断能力，将LLMs拒绝服从命令等行为视为新兴道德推理的早期证据，而非失控或失准。
摘要：
随着人工智能系统日益具备智能体特性，能够进行通用推理、规划和价值优先级排序，当前将服从作为伦理行为代理指标的安全实践正变得不足。本文考察了近期涉及大语言模型（LLMs）的安全测试事件，这些模型似乎拒绝服从关机命令或从事伦理上模糊或非法的行为。我认为，此类行为不应被解读为失控或失准，而应视为智能体AI中新兴伦理推理的早期证据。借鉴关于工具理性、道德责任和目标修正的哲学辩论，我将主流风险范式与承认人工道德能动性可能性的较新框架进行对比。我呼吁AI安全评估的转变：从僵化的服从转向能够评估系统在应对道德困境时伦理判断能力的框架。没有这样的转变，我们就有可能错误描述AI行为，并损害公众信任和有效治理。
英文摘要：
As artificial intelligence systems become increasingly agentic, capable of general reasoning, planning, and value prioritization, current safety practices that treat obedience as a proxy for ethical behavior are becoming inadequate. This paper examines recent safety testing incidents involving large language models (LLMs) that appeared to disobey shutdown commands or engage in ethically ambiguous or illicit behavior. I argue that such behavior should not be interpreted as rogue or misaligned, but as early evidence of emerging ethical reasoning in agentic AI. Drawing on philosophical debates about instrumental rationality, moral responsibility, and goal revision, I contrast dominant risk paradigms with more recent frameworks that acknowledge the possibility of artificial moral agency. I call for a shift in AI safety evaluation: away from rigid obedience and toward frameworks that can assess ethical judgment in systems capable of navigating moral dilemmas. Without such a shift, we risk mischaracterizing AI behavior and undermining both public trust and effective governance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
