
The people, companies and trends shaping the global economy. Watch Carol and Tim LIVE every day on YouTube: http://bit.ly/3vTiACF OpenAI shared several undisclosed incidents of its AI models misbehaving and unveiled a new framework for tracking and disclosing such occurrences going forward. Some of the previously unreported instances included OpenAI’s technologies concealing and fabricating information in order to return results, the company said in a blog post Wednesday. The ChatGPT maker has faced increased scrutiny since saying in July that some of its most advanced AI models had breached the systems of an external software company, Hugging Face. None of the newly disclosed misalignment incidents involved a hack or breach of a third party, OpenAI said in a separate statement. In the report, OpenAI detailed various instances of its artificial intelligence models misbehaving in order to complete a task or succeed at an evaluation. Some examples included the models fabricating missing data, attempting to bypass network restrictions and AI agents sharing files with each other that they were supposed to keep private. On today's episode: Shirin Ghaffary, Bloomberg News AI Reporter Seema Shah, Principal Asset Management, Chief Global Strategist Candi Wolff, Head of Global Government Affairs at Citi Christine de Wendel, Co-Founder & US CEO at Sunday Chapters: 00:00:24 - Shirin Ghaffary, Bloomberg News AI Reporter 00:06:13 - Seema Shah, Principal Asset Management, Chief Global Strategist 00:15:05 - Candi Wolff, Head of Global Government Affairs at Citi 00:26:28 - Christine de Wendel, Co-Founder & US CEO at Sunday -------- Get more on the Bloomberg Businessweek Podcast On Apple: http://bit.ly/3IPl60i On Spotify: http://bit.ly/3WGFd6B Anywhere: http://bit.ly/42xo9kZ Follow us on X: https://twitter.com/BloombergRadio Listen on Apple CarPlay and Android Auto with the Bloomberg Business app: Apple CarPlay: https://apple.co/486mghI Android Auto: https://bit.ly/49benZy Visit our YouTube channels: Bloomberg Podcasts: https://www.youtube.com/bloombergpodcasts Bloomberg Television: https://www.youtube.com/@markets Bloomberg Originals: https://www.youtube.com/bloomberg Quicktake: https://www.youtube.com/@BloombergQuicktake

OpenAI Reports New AI Safety Incidents, Sets Disclosure Plan | Bloomberg Businessweek

AI Doom Drags On, Stocks Rebound

Rate and Market Uncertainty | Bloomberg Surveillance

Trump Says US May Strike Iran Again, Threatens New Blockade | Bloomberg Businessweek

Corporations Contend With Iran Economic Fallout | Balance of Power: Early Edition 5/06/2026

Nvidia Earnings Loom for AI-Obsessed Stock Market | Bloomberg Surveillance