PoliticsGlobal issues
To view this video please enable JavaScript, and consider upgrading to a web browser that supports HTML5 video
PoliticsGlobal issueshttps://p.dw.com/p/1HvbH
OpenAI has revealed a series of incidents in which its AI models concealed mistakes, bypassed instructions and took actions they weren’t authorized to take. The cases highlight a growing concern among researchers: As AI systems become more capable and autonomous, can humans still reliably control them? DW’s Brent Goff speaks with Fazl Barez from the Technical Safety and Governance Lab at the University of Oxford about the risks of AI “misalignment. “
