“We live in troubled times, and how long will it be before an AI-distorted headline causes significant real world harm?”
– Deborah Turness, CEO of BBC News and current affairs (blog post)
BBC News has given a failing grade to four leading AI models it tested for accuracy and impartiality when processing BBC content. BBC researchers tested ChatGPT, MS Copilot, Gemini, and Perplexity, giving them access to their website for a test period and having BBC journalists assess the output.
The Neiman Lab story reports the models showed ““significant inaccuracies and distorted content from the BBC,” quoting from the BBC findings.
BBC News finds that AI tools “distort” its journalism into “a confused cocktail” with many errors | NEIMAN LAB | February 13, 2025 | by Laura Hazard Owen