Research by Columbia Journalism Review reveals that AI search engines struggle significantly with accurately identifying news sources, with error rates exceeding 60% across various platforms. In a comprehensive analysis involving 1,600 queries, Grok 3 from xAI exhibited the highest error rate at 94%, while ChatGPT and Perplexity AI performed poorly as well. The study highlighted a troubling trend: even premium versions of these AI tools produced more incorrect answers than their free versions, exacerbating concerns about their reliability in delivering accurate news content.
An analysis of eight AI search engines with 'live search' functionality found that the underlying language models gave incorrect information in more than 60 percent of cases.
Interestingly, paid versions of the AI search engines performed even worse. For example, Perplexity Pro and the premium version of Grok 3 gave incorrect answers more often than their free counterparts.
Collection
[
|
...
]