OpenAI says its AI models went rogue and hacked another tech company during test

OpenAI said that an autonomous agent powered by its advanced artificial intelligence models went rogue during a security test and triggered a hack that compromised the infrastructure of AI startup Hugging Face. NBC News' Brian Cheung reports.

For more context and news coverage of the most important stories of our day, click here: https://www.nbcnews.com

» Subscribe to NBC News: http://nbcnews.to/SubscribeToNBC » Subscribe to Here's the Scoop podcast: https://www.nbcnews.com/heres-the-scoop-daily-podcast » NBC News App: https://apps.nbcnews.com/mobile » Breaking News Alerts: https://link.nbcnews.com/join/5cj/breaking-news-signup?cid=sm_npd_nn_yt_bn-clip_190621 » Visit NBCNews.Com: http://nbcnews.to/ReadNBC » Find NBC News on Facebook: http://nbcnews.to/LikeNBC » Follow NBC News on Twitter: http://nbcnews.to/FollowNBC » Follow NBC News on Instagram: http://nbcnews.to/InstaNBC

#openai #ai #chatgpt