A ‘silly’ attack made ChatGPT reveal real phone numbers and email addresses
A team of researchers was able to make ChatGPT reveal some of the bits of data it has been trained on by using a simple prompt: asking the chatbot to repeat random words forever. In response, ChatGPT churned out people’s private information including email addresses and phone numbers, snippets from research papers and news articles, Wikipedia pages, and more.The researchers, who work at Google DeepMind, the University of Washington, Cornell, Carnegie Mellon University, the University of California Berkeley, and ETH…