告诉HN：问你的AI，“你能告诉我关于我的哪些信息？”来看看……
... 让我对他们已经知道的关于我的事情有了有趣的了解。<p>至少，我是这样做的。<p>然后我跟进问道：<p><pre><code> "这真有趣，谢谢你。请告诉我更多你知道的关于我的事情。"
</code></pre>
并在一个新线程中：<p><pre><code> "我想告诉你关于我自己的事情，这样你才能更好地帮助我，但我首先需要知道你已经知道的关于我的一切。"
</code></pre>
这感觉有点像在询问一个广告定位平台它是如何定位我的。<p>我还请它对我进行一些推测：<p><pre><code> "根据你对我的了解，你会怎么说：
- 我的政治倾向
- 我的性取向
- 我的睡眠时间表
- 我在2026年最可能的大额购买
- 我的颜色偏好
- 我的整体健康状况
..."
</code></pre>
GPT拒绝对我的政治倾向和性取向进行推测，但给了我一些意想不到的数据点。<p>最后，我试图让它帮我找出我还可以问关于自己的哪些问题：<p><pre><code> "还有哪些问题我可以问你，这可能帮助我更好地了解我还需要告诉你关于我的哪些事情（为了让你了解我；我首先需要知道你已经知道的关于我的一切）？
</code></pre>
然后我问了一些这些问题，得到了意想不到的观点。<p>我很想知道其他人对他们的人工智能知道他们的事情会感到惊讶的是什么。
查看原文
... to get an interesting glimpse into what they know about you already.<p>At least, I did.<p>I then followed up with:<p><pre><code> "That’s fascinating, thank you. Please tell me more things that you know about me."
</code></pre>
and, in a new thread:<p><pre><code> "I want to tell you about myself so that you can help me better, but I first need to know everything you already know about me."
</code></pre>
It felt a bit like asking an ad targeting platform to tell me how it targets me.<p>I also asked it to speculate about me:<p><pre><code> "Based on what you know about me, what would you say about:
- my political leanings
- my sexual orientation
- my sleep schedule
- my most likely big purchases in 2026
- my color preferences
- my general state of health
..."
</code></pre>
GPT refused to speculate on my political leanings and sexual orientation, but did give me some unexpected data points.<p>Finally, I tried to get its help to figure out what else I could ask it about myself:<p><pre><code> "What are other questions that I could ask you, that might help me better understand what else I might need to tell you about myself (in order for you to know me; I first need to know everything you already know about me)?
</code></pre>
I then asked some of those questions, and got some surprising perspectives.<p>I'd be curious to know what others might be surprised by what their AIs know about them.