告诉 HN：Pangram 在 Claude 面前不堪一击
2 分•作者: nunez•5 个月前
我经常使用 Pangram 来检测我阅读的内容是否完全由 AI 生成。今天，我好奇要攻破它有多容易。<p>我所要做的就是向它们展示它们生成的文本被检测为 100% AI 生成，然后它们就会生成一个“听起来像人类”的文本片段。<p>Claude Sonnet：https://claude.ai/share/28080c8c-5647-43df-9671-91c9f9e46791<p>有趣的是，ChatGPT 5.4 不会这样做，至少在使用它默认的模型时不会：https://chatgpt.com/share/69c6c713-038c-832e-86be-689abd7b7ae1。我猜它可以通过越狱来实现这一点。
查看原文
I use Pangram all of the time to detect whether what I'm reading is fully AI-generated or not. Today, I wondered how easy it was to defeat it.<p>All I had to do was show them that the text they generated was detected as 100% AI generated to get them to generate a "human-sounding" text snippet.<p>Claude Sonnet: https://claude.ai/share/28080c8c-5647-43df-9671-91c9f9e46791<p>Interestingly, ChatGPT 5.4 won't do it, at least not with the default model it uses: https://chatgpt.com/share/69c6c713-038c-832e-86be-689abd7b7ae1. I'm guessing it can be jailbroken to do it though.