OpenAI Reports New AI Safety Incidents, Sets Disclosure Plan | Bloomberg Businessweek
Community Score: 50% | 1.3K views | 4w
0 community ratings: null thumbs up, null thumbs down
The people, companies and trends shaping the global economy. Watch Carol and Tim LIVE every day on YouTube: http://bit.ly/3vTiACF (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 mod
Tags: Businessweek, News, Tech News, Technology, bloomberg Businessweek, bloomberg podcast, business, businessweek podcast, news, news podcast, podcast, podcasts
More from Bloomberg Podcasts
- Follow the Money All the Way to Carney's Canada — Score: 50%
- Daybreak Weekend: US CPI, Europe Energy, RBA Decision | Bloomberg Daybreak: Europe Edition — Score: 50%
- Bloomberg Money: Credit Card Indicators and Golf's Changing Fanbase | Bloomberg Intelligence — Score: 50%
- We hear you! | Bloomberg Hot Pursuit! — Score: 50%
- Bloomberg Businessweek Weekend - August 7th, 2026 | Bloomberg Businessweek — Score: 50%
- Team Favorite: AI-Era Internet, Spaceport Investment, Bolivia’s Investability | Wall Street Week — Score: 50%