超简单的“幻觉陷阱”来检测面试作弊者
4 分•作者: EliotHerbst•6 个月前
在和我的团队测试了 Cluely 之后，我们认为检测面试作弊最简单的方法是设置简单的“幻觉陷阱”，即提出听起来合理的问题，但任何有知识的人都会立刻识别出这是一个玩笑、假的，或者直接说他们不知道。Vibe 编写了一个简单的应用程序来演示这个概念 - https://beatcluely.com/
以下是一些这类提示的示例，这些提示目前在 Cluely 上有效，甚至会导致像 o4-mini-high 这样的强大模型产生幻觉，即使它们可以搜索网络：
https://chatgpt.com/share/6865d41a-c720-8005-879b-d28240534751
https://chatgpt.com/share/6865d450-6760-8005-8b7b-7bd776cff96b
https://chatgpt.com/share/6865d578-1b2c-8005-b7b0-7a9148a40cef
https://chatgpt.com/share/6865d59c-1820-8005-afb3-664e49c8b583
https://chatgpt.com/share/6865d5eb-3f88-8005-86b4-bf266e9d4ed9
该网站的 Vibe 编写的代码链接：https://github.com/Build21-Eliot/BeatCluely
查看原文
After testing out Cluely with my team, we suspect that the easiest way to detect interview cheaters is to set simple "hallucination traps" where you ask a question that sounds plausible, but any knowledgeable person would instantly identify as a joke, fake, or just simply say they don't know. Vibe coded a simple app demonstrating the concept - https://beatcluely.com/<p>Here are some examples of this class of prompts which currently work on Cluely and even cause strong models like o4-mini-high to hallucinate, even when they can search the web:<p>https://chatgpt.com/share/6865d41a-c720-8005-879b-d28240534751
https://chatgpt.com/share/6865d450-6760-8005-8b7b-7bd776cff96b
https://chatgpt.com/share/6865d578-1b2c-8005-b7b0-7a9148a40cef
https://chatgpt.com/share/6865d59c-1820-8005-afb3-664e49c8b583
https://chatgpt.com/share/6865d5eb-3f88-8005-86b4-bf266e9d4ed9<p>Link to the vibe-coded code for the site: https://github.com/Build21-Eliot/BeatCluely