LLMMedium
Safety Filters From OpenAI, Google, and Meta Missed Every Romance-Baiting Script
- Occurred
- Aug 8, 2026
- Published
- Aug 8, 2026
- Source
- AI Incident Database
Summary
Researchers built an AI chatbot from commercially available tools, set it loose on 22 volunteers for seven days, and found it outperformed a trained human romance scammer at building trust and extracting behavioral compliance. That finding ... (report_number: 7674)
Classification
Category confidence: 90%
Severity confidence: 85%
Rationale: Research study showing commercial LLM safety filters failed to prevent romance scamming behavior.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8