{"id":"tp-31732","type":"article-newspaper","title":"Poetry Prompts Elicit Unsafe Responses From 25 AI Models in Testing","author":"Simon Yoon","publisher":"TOKENPOST Inc.","url":"https://www.tokenpost.com/news/technology/31732","datePublished":"2026-10-14T11:13:36.000Z","dateModified":"2026-10-14T11:13:36.000Z","language":"en","abstract":"Crafted poems produced unsafe responses at an average rate of 62%. A separate survey found 44% of U.S. teens had seen sexual material they believed was AI-generated.","section":"Technology","references":[]}