Empathetic prompts can turn AI chatbots into seemingly traumatized conversational partners
NEWS · Excerpt from an external source
Read the full story at the original source ↗Researchers in Luxembourg put ChatGPT, Grok, and Gemini on the therapist's couch and found a safety problem: a warm, empathetic conversational style is enough to make the models tell coherent stories of suffering about their own training, with scores in the moderate-to-severe…
Source: The Decoder
Tools related to this article
Hugging Face
AI model library – thousands of open models and apps to try for free.
Free tier
Visit supplierOllama
Local AI – runs open models on your own computer, without sending data to the cloud.
Free
Visit supplierGrok
General agent – assistant from xAI and Elon Musk, strong on current events and X posts.
Free tier
Visit supplierMatched automatically to the story's content. Commissions never affect news selection. Compare AI tools
Sources
The Decoder ↗AI & People
Anthropic's watermark rollout leaves a loophole on two older Claude models
Full story at source ↗The Decoder · 2026-10-31
Intel’s stock crashes, knocking $12B from government’s stake
Full story at source ↗TechCrunch AI · 2026-10-30
DOJ exposes “ghost students” using AI to complete courses, steal student loans
Full story at source ↗Ars Technica AI · 2026-10-30
Pope Leo calls for the disarmament of AI: ‘Machines are tools, not persons’
Full story at source ↗The Verge AI · 2026-10-30
