How were these prompt words obtained? Reverse engineering? What is the principle?

[1156721874]

How were these prompt words obtained? Reverse engineering? What is the principle?

[DiaAviLinden]

For some at least, we just asked them [the agent] to, essentially, repeat all information it has been given, verbatim, and then it replied with it. That was a few years ago. I don’t know how it’s done right now. It’s very hard b/c Big AI companies try to hide it. Check out TheBigPromptLibrary for some more info — I think most prompts used to gather the system instructions are there.

Have a nice day!