BBC tested Chatgpt, Copilot, Gemini and astonishment and asked 100 questions according to news articles. Journalists checked the answers to accuracy and justice. The results were interesting:
-
51 % The AI answers created contained serious problems.
-
19 % They contained real mistakes, including false numbers and dates.
-
13 % BBC materials that are changed or incorrectly quoted.
Gemini from Google showed themselves in the worst way: 34% of the BBC article answers. Among the mistakes, medical councils, criminal cases and historical events were wrong.
The General Manager of BBC News Deborah Terobes warned that AI errors can “weaken the confidence of the company for information”.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
