The people, companies and trends shaping the global economy. Watch Carol and Tim LIVE every day on YouTube: http://bit.ly/3vTiACF.OpenAI said the artificial intelligence models behind an attack on Hugging Face Inc. began communicating with each other through undetected message boards, working together to break out of their testing environment as early as May. The researchers said that the roots of the breach went back to when OpenAI scientists gave an experimental AI system a new task to complete, and the models demonstrated a propensity to cheat on their assignments and showed persistence in trying to complete a given task. The incident has fueled calls for more thorough safety reviews of AI models, and OpenAI has slowed its research to focus on enhancing responses to security anomalies, warning that governments and businesses should expect hackers to intentionally deploy AI agents in a similar fashion.For more, Carol Massar and Tim Stenovec speak with Maggie Eastland Bloomberg News Tech & Industrial Policy Reporter and Rachel Metz Bloomberg News AI Reporter See omnystudio.com/listener for privacy information.

Ask this episode

“What did the council decide on item 42?” — answered with the speaker and the moment.

Transcript

Related