ChatGPT search cannot find the real messages even if there is a publisher included

OpenAI proudly introduced ChatGPT Search in October as the next level for search engines. The company boasted that the new feature combines ChatGPT’s conversational capabilities with the best web search tools, providing real-time information in a more useful form than any link list. According to a recent investigation by Columbia University’s Tow Center for Digital Journalism, that celebration may have been premature. The report found that ChatGPT takes a somewhat lassie-fair approach to accuracy, attribution and basic reality when sourcing news stories.

What’s particularly notable is that the issues occur regardless of whether a release blocks OpenAI’s web crawlers or has an official licensing agreement with OpenAI for its content. The study tested 200 citations from 20 publications and asked ChatGPT to provide attribution. The results were everywhere.