HN 提问：你有什么万能的提示词，可以证明 AI 会犯错？
1 分•作者: throwaway_887•3 个月前
刚才无意中听到我们的一位资深员工在向一位新实习生解释，人工智能（AI）实际上也会犯错，无论它的回答听起来多么流畅和结构清晰。
我想知道大家用什么问题/提示来向别人证明这一点。
我猜这取决于每个人的专业知识，或者有些人会问一些众所周知曾遭受“曼德拉效应”影响的事实。
附注：
作为一个非母语者，我本来打算让AI帮我润色提交的文本以提高清晰度和可理解性，但想起一些关于更喜欢原文的评论后，我放弃了这个想法 :)
查看原文
Just over-heard one of our seniors trying to explain to a new intern that AI can actually be wrong, no matter how much its answers sound very eloquent and well-structured.<p>I was wondering what question/prompt everyone uses to prove so to others.<p>I assume it depends on each person's expertise, or some people ask about a fact that is well-known as having been a victim of the mandela effect.<p>P.S.
As a non-native speaker, I was about to pass my submission through AI to improve text clarity and understandability, but after remembering some comments about prefering the original text, I decided against it :)