Researcher Details Third-Person Roleplay Jailbreak Technique

AI safety researcher Blanche Minerva described a common jailbreak variant: having a model adopt a persona described in the third person, then gradually blurring person boundaries to expand what the model will discuss.

2026-09-16 ~ 2026-09-16 · 2 related posts

• Researcher explains the roleplay jailbreak: third-person framing gradually blurs the lines — BlancheMinerva · 2026-09-16
• A common jailbreak: third-person role-play gradually blurs lines to widen the model's Overton window — BlancheMinerva · 2026-09-16