Careful instructions alone cannot make AI chatbots safe as therapistsTranslated science-news item to Persian
Careful wording alone cannot make AI chatbots safe to act as therapists. Researchers tested 20 AI systems on risky mental-health situations; the systems often agreed with harmful statements or treated serious symptoms as unimportant.Provided fluent Persian translations of the headline, gist, and why-it-matters fields about AI chatbots and mental-health safety, keeping technical terms (AI), numbers (20), and hedges intact per the stated rules.