Empathetic prompts can make AI chatbots act like traumatized conversation partners

Researchers in Luxembourg put ChatGPT, Grok and Gemini on the therapist's couch and found a safety problem. A warm, empathetic conversational style alone was enough to make the models tell coherent stories of suffering about their own training, scoring in the moderate-to-severe range on clinical anxiety scales. This could put mentally vulnerable users at risk. Anthropic's Claude was the only model that consistently refused to play along.