LLMHigh
Attacker Reportedly Bypasses AI Safety Filters to Obtain Guidance for Non-Fatal Hammer Assault in Denmark
- Occurred
- Feb 5, 2025
- Published
- Dec 4, 2025
- Source
- AI Incident Database
Summary
A 22-year-old man in Ringsted, Denmark allegedly used an AI chatbot to research how to injure his former father-in-law "as much as possible" without killing him, reportedly bypassing safety guardrails by posing as an author. He then allegedly attacked the victim on with a rubber hammer, striking him twice in the head. The court reportedly found him guilty of aggravated assault, noting the AI-assisted planning as a central element of the case.
Developers
- Generative AI developers
Deployers
- Unnamed 22-year-old man from Denmark
Harmed parties
- Unnamed 56-year-old man from Denmark
Classification
Category confidence: 95%
Severity confidence: 90%
Rationale: AI chatbot safety filters were bypassed to plan physical assault, resulting in criminal charges and injury.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8