Via LLRX – How to Spot AI Hallucinations Like a Reference Librarian – Hana Lee Goldin is a expert “human” pathfinder who shares her extensive knowledge with an expanding cadre of people seeking to adopt AI in all facets of work and life. In her article, Goldin deftly illuminates one of the major risks of ChatGPT. Goldin say it doesn’t lie, exactly. It patterns matches. When you ask for a “cited article about remote work productivity,” it knows what citations look like. Author name, year, compelling title, respectable journal. It assembles these patterns into something that feels right. Like a dream where everything makes sense until you wake up.