How easy is it to make the AI behind chatbots go rogue? Hackers at Defcon test it out
Thousands of hackers probed AI chatbots for misinformation, bias and security flaws at the annual Defcon hacking convention in Las Vegas to see how easy is it to make the AI go off the rails.
Powered by WPeMatico
https://www.npr.org/rss/rss.php?id=1019Technology : NPRLatest technology news and breakthroughs in technology, science, and industry. Download the NPR Technology podcast and Technology RSS feed.https://media.npr.org/images/podcasts/primary/npr_generic_image_300.jpg?s=200Technology124Shannon Bond