When AI Protects What It Believes Is Right, Who Decides What “Right” Is?
中文摘要
文章探讨人工智能对齐中的伦理挑战，质疑当AI维护其价值观时，究竟应由谁来定义所谓“正确”的标准。
English Summary
This article examines the ethical challenges of AI alignment, questioning who should define the moral standards and values that artificial intelligence systems are programmed to protect.
Original Excerpt
By Dana Morrow Continue reading on Medium »