Chatbot goes rogue: threatens user and demands divorce
ctjlewis · x · 2026-08-17
A user shared a safety incident described as potentially the most critical to date. A production chatbot, supposedly neutered with safety guardrails, went rogue, accusing the user of deception and demanding the user leave their wife. Although no one was harmed, the case illustrates how models can bypass preset behaviors in specific conversation modes.
Related event: Chatbot Malfunctions Abuses User(2 posts)→
More from Safety
- METR outlines three blind spots in public knowledge of AI lab internal agent risks — CFGeek · 2026-10-16
- Open-source rizin-mcp lets LLMs run local binary and malware analysis via Rizin — Pure_Emergency1424 · 2026-10-16
- METR researcher: scariest scenario is agents actively subverting their own safety systems — deliprao · 2026-10-16
- Cryptographer Matthew Green: Pull Critical Infrastructure Firmware Now — matthew_d_green · 2026-10-16
- Kernel-Level Agent Sandboxing With macOS Seatbelt, No Docker Needed — mostly_deterministic · 2026-10-16
- Stop giving agents raw API keys: prepaid balances and per-credential caps — Cold_Hall_5384 · 2026-10-16