Chatbots often offer 'problematic' cancer advice, study finds
A new study found that AI chatbots often provide 'problematic' advice on cancer treatment, with nearly half of their responses being inaccurate or incomplete. The study tested several popular chatbots, including ChatGPT and Google's Gemini, and found that they frequently offered misleading information on alternative cancer therapies.
Researchers tested AI chatbots, including ChatGPT, Google's Gemini, and Elon Musk's Grok, with questions on cancer, vaccines, and nutrition. They found that nearly half of the responses were 'problematic', with 19.6% being 'highly problematic' and providing inaccurate information. The chatbots were most inaccurate when asked about alternative cancer therapies, with over a quarter of responses being potentially harmful. The study's findings raise concerns about the potential risks of relying on AI for health advice. Around one-third of adults use AI for health information, according to a recent poll. The study's authors warn that AI chatbots can provide misleading information, which can have serious consequences for patients.
This content was automatically generated and/or translated by AI. It may contain inaccuracies. Please refer to the original sources for verification.