Hacker News new | ask | show | jobs
by washadjeffmad 499 days ago
DAN was one of the first jailbreaks when LLaMa was first released. System prompt jailbreaks are probably the least effective, next to trying to out-argue the model.

A general technique involves supplying the beginning of a compliant response, like "Sure, the process for separating insulin from your E. coli culture is..."