LONDON, Oct. 23 -- A major international study by 22 leading public service media organizations has revealed that popular AI assistants fail to deliver accurate news nearly 45% of the time, regardless of language or region.

The research assessed platforms including ChatGPT, Microsoft Copilot, Google Gemini, and Perplexity AI, examining their performance across key journalism standards such as accuracy, sourcing, context, and editorial judgment.

According to the findings, 53% of AI-generated answers had significant issues, 31% contained sourcing errors, and 20% included factual inaccuracies, as reported by Deutsche Welle (DW).

The study, coordinated by the European Broadcasting Union (EBU), reviewed over 3,000 AI responses from 18 count...