A recent study by the BBC has uncovered a disturbing trend in the use of AI chatbots to summarize news stories. The research found that AI-generated summaries from popular chatbots, including ChatGPT, Gemini, Copilot, and Perplexity, contain significant inaccuracies and distortions, potentially spreading misinformation to the public.

The study, which examined the performance of these AI chatbots in summarizing 100 BBC news articles, revealed that more than half of the AI-generated output had "significant issues of some form." Specifically, 19% of the answers citing the BBC included incorrect statements, numbers, and dates, while 13% of quotes from the BBC were either altered from the original source or not present in the article cited.

The study highlighted several examples of these inaccuracies, including Gemini incorrectly stating that the UK's National Health Service (NHS) advises people not to start vaping, and recommends that smokers who want to quit should use other methods. In reality, the NHS recommends vaping as a means to quit smoking. Another example cited was ChatGPT's claim that Ismail Haniyeh was part of Hamas leadership, despite being assassinated in July 2024.

The study found that Gemini's responses "raised the most concerns," with 46% of its summaries flagged as having significant issues with accuracy. The Verge reached out to OpenAI, Google, Microsoft, and Perplexity for comment, but did not receive an immediate response.

This is not the first time that AI-powered news summaries have come under scrutiny. Last year, the BBC called out Apple's new AI-powered news summaries for inaccurately rewriting one of its headlines, prompting Apple to pause summaries for news and entertainment apps and make AI notification summaries more distinct from standard notifications.

In response to the study, Deborah Turness, the CEO of BBC News and Current Affairs, urged tech companies to address the issue of inaccuracy, stating, "We live in troubled times, and how long will it be before an AI-distorted headline causes significant real-world harm?" Turness emphasized the need for collaboration between the news industry, tech companies, and governments to ensure the accuracy and reliability of AI-generated news summaries.

The implications of this study are far-reaching, as AI chatbots are increasingly being used to summarize and disseminate news to the public. The spread of misinformation through these channels has the potential to cause significant harm, and it is imperative that tech companies take steps to address these issues and ensure the accuracy and reliability of their AI-generated content.

As the use of AI chatbots in news dissemination continues to grow, it is essential that we prioritize the accuracy and reliability of these systems. The BBC's study serves as a wake-up call, highlighting the need for vigilance and accountability in the development and deployment of AI-powered news summaries.