<ul><li>A new study from the BBC has found that four popular AI chatbots including ChatGPT inaccurately summarize news stories.</li><li>51% of AI answers had significant issues, and 19% introduced factual errors, according to the study.</li><li>AI struggled to differentiate between opinion and fact, often failed to include essential context.</li><li>The study concludes that Microsoft's Copilot and Google's Gemini had more significant issues than OpenAI's ChatGPT and Perplexity.</li></ul>

ChatGPT and Google Gemini are terrible at summarizing news, according to a new study

Discover more