Previously, I created a tool for Lawyer Xiao Sheng to regularly screen posts online and determine if they are legal consultation-related. This requires text classification to judge whether the specified post content involves legal issues. As a backend developer with no experience in natural language processing, I only had a basic understanding of machine learning principles from my studies, but had never actually done a classification task. Fortunately, with ChatGPT now available, I decided to use its API for classification.

I previously wrote an article introducing prompt cracking: bypassing ChatGPT’s security checks. At that time, the main purpose was to bypass some security restrictions when using ChatGPT. I didn’t try much with prompt leakage because there weren’t many applications with custom prompts at that time.

Recently, OpenAI announced GPTs at their first DevDay. You can learn about GPTs’ capabilities by reading Introducing GPTs. Subsequently, GPT creation permissions were opened to Plus users, and a large number of GPTs emerged. With the same prompt words, some people have created interesting GPTs in various ways.

So, is there any way to obtain the prompts of others’ GPTs? And how can we prevent others from getting the prompts of our own GPTs? Let’s look at some interesting attempts.

Recently, I encountered a strange issue when executing the binary file ‘protoc’, which reported the error no such file or directory: ./protoc. The file was clearly there, yet it kept reporting this error. Could it be a system bug? Whenever encountering bizarre issues, we tend to suspect the operating system or compiler, but often we end up being the fool. This time was no exception; after continuous attempts, I discovered that this was actually a system feature.

In fact, if you’re a novice encountering this problem for the first time, you’d be at a loss, with no idea how to troubleshoot. Before continuing to read, you might want to guess what could cause this error when executing a binary file.