The venerable BBC discovered significant deficiencies when testing AI’s ability to accurately answer questions about the news.
“We gave the AI assistants [OpenAI’s ChatGPT; Microsoft’s Copilot; Google’s Gemini; Perplexity] access to our website for the duration of the research and asked them questions about the news, prompting them to use BBC News articles as sources where possible.”
In the study, conducted in February 2025, journalists reviewed AI’s answers to 100 popular questions about content covered by the BBC. In all, 45 journalists graded 362 AI responses.
Here’s a summary of their findings:
- 51% of all AI answers to questions about the news were judged to have significant issues of some form.
- 19% of AI answers which cited BBC content introduced factual errors – incorrect factual statements, numbers and dates.
- 13% of the quotes sourced from BBC articles were either altered from the original source or not present in the article cited.
