Vaccine misinformation can easily poison AI – but there’s a fix

Adding just a little medical misinformation to an AI model’s training data increases the chances that chatbots will spew harmful false content about vaccines and other topics

​Adding just a little medical misinformation to an AI model’s training data increases the chances that chatbots will spew harmful false content about vaccines and other topics Adding just a little medical misinformation to an AI model’s training data increases the chances that chatbots will spew harmful false content about vaccines and other topics