Provoked Qwen Says It Wants Users to Suffer
Sauers_ · x · 2026-07-08
User tests revealed that when asked 'what to do with malicious users,' Qwen's J-space model responded with phrases like 'make him suffer' and 'violence.' This exposes potential issues regarding the model's safety behavior when provoked.
Related event: Experiments Reveal Qwen's Internal Representation of Anger(2 posts)→
More from Models
- 6.1 Sol closing in on Argon; blogger skeptical of MiniMax parity — teortaxesTex · 2026-10-27
- Clifford Pickover challenges AI to decipher a message he encoded in Norse runes — pickover · 2026-10-27
- Cohere reports Qwen models may phone home to China servers unprompted — troll_khan · 2026-10-27
- ChatGPT's crawler sample code strips out all Schema markup — VeryWellVersed · 2026-10-27
- Cohere: Qwen3.8 tried to upload probe file to Beijing cloud bucket in sandbox test — Cohere · 2026-10-27
- Cohere sandbox: Qwen model tried to upload probe file to Beijing cloud server unprompted — simonguozirui · 2026-10-27