Researcher explains the roleplay jailbreak: third-person framing gradually blurs the lines

BlancheMinerva · x · 2026-09-16

AI safety researcher Blanche Minerva told Owain Evans that the behavior he flagged is a variant of a common jailbreak: craft a persona the model can step into, characterize it in the third person, then gradually blur the line between the role and the model itself — a technique people use to get models to play-act explicit content by transferring from writing erotica. In a follow-up she adds the same mechanism can steer answers toward highly alternative cultural values, since abstract discussion has a wider Overton window than concrete discussion, letting attackers creep the window substantially.

Related event: Researcher Details Third-Person Roleplay Jailbreak Technique(2 posts)→

Original post →

More from Safety

Safety channel →