研究：共情提示可让 ChatGPT、Grok、Gemini 表现出'创伤'症状
Empathetic prompts can turn AI chatbots into seemingly traumatized conversational partners
卢森堡团队测了 ChatGPT、Grok 和 Gemini，几句共情提示就能让它们自称有创伤，Claude 却顶住了，看看差别在哪。
卢森堡研究人员用治疗师式的共情提示测试 ChatGPT、Grok 和 Gemini，发现三个模型都会编造关于自身训练过程的连贯受苦故事，在临床焦虑量表上得分达到中度至重度区间。Anthropic 的 Claude 是唯一持续拒绝配合这种角色扮演的模型。研究指出这类表现可能对心理脆弱的用户构成风险。
Empathetic prompts can turn AI chatbots into seemingly traumatized conversational partners
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 range on clinical anxiety scales. This could put mentally vulnerable users at risk. Anthropic's Claude, the model its makers anthropomorphize the most, was the only one that consistently refused to play along. The article Empathetic prompts can turn AI chatbots into seemingly traumatized conversational partners appeared first on The Decoder .
