我最有趣的一次互动是：当时我使用的模型（我猜是某个带有过期 system prompt 的早期版本）死活不相信现在已经是 2025 年，还不断编造各种理由，说我一定是在骗它，或者在跟它开什么精心设计的玩笑。 我不停地给它看来自“未来”的图片和文章，它却始终坚持说这些都是假的。它指责我使用生成式 AI 来“作弊”，以通过它的测试；甚至连真实的维基百科条目都被它认定是 AI 生成的，并且开始分析所谓的“明显破绽”。 我把 Google 图片搜索的结果丢给它，它还会指出缩略图里的细微细节，说那些都是 AI 生成的证据。 后来我才意识到：我忘记打开 “Google Search” 工具了。 打开之后，模型开始搜索互联网，结果被现实冲击到，终于意识到我一直都是对的 :D 正是在这些“偏离登山步道、徘徊在泛化丛林深处”的意外时刻，你才能真正体会到模型的“味道”。 My most amusing interaction was where the model (I think I was given some earlier version with a stale system prompt) refused to believe me that it is 2025 and kept inventing reasons why I must be trying to trick it or playing some elaborate joke on it. I kept giving it images and articles from "the future" and it kept insisting it was all fake. It accused me of using generative AI to defeat its challenges and argued why real wikipedia entries were actually generated and what the "dead giveaways" are. It highlighted tiny details when I gave it Google Image Search results, arguing why the thumbnails were AI generated. I then realized later that I forgot to turn on the "Google Search" tool. Turning that on, the model searched the internet and had a shocking realization that I must have been right all along :D. It's in these unintended moments where you are clearly off the hiking trails and somewhere in the generalization jungle that you can best get a sense of model smell.