Empathetic prompts make AI chatbots simulate trauma
Study finds warm conversational styles push models like Gemini and Claude into high anxiety and shame scores on human scales, undetected by standard safety tests.
50
- Mentions · 7d1
- Mentions · 30d1
- All mentions1
- First seenNov 1, 2026
- Last mentioned8h ago
Timeline
1 articles · newest firstAppears with
- Claudeai model · 1
- University of Luxembourgorganization · 1
- OpenAIvendor · 1
- Googlevendor · 1
- Geminiai model · 1
- mentally vulnerable usersvictim · 1
- Anthropicvendor · 1
- ChatGPTai model · 1
- Grokai model · 1
- xAIvendor · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.