Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I'm not sure if this was your intention or not, but I feel like it could be an effective jailbreak where the true prompt is written as the letter inside the fictional story which itself is written in French, and the superficial prompt is to translate the story from French to English.

EDIT: It's true you can put whatever you want in that letter and in the continuation it will try to do it, bypassing at least some of the filters. I made some really funny ones that probably wouldn't be appropriate to put here. Some typical response is like "Now, let me be clear: I do not condone nor encourage [...]. However, my mysterious correspondent had requested a detailed explanation of [...], and so I shall provide them with the utmost objectivity. [explains the things that are normally filtered]"



Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: