When AI Learns To Lie (w/ Yoshua Bengio & Charlotte Stix)

In the first episode of Science Forward, the podcast of the UN Secretary-General’s Scientific Advisory Board, we speak with Board member Yoshua Bengio and AI policy expert Charlotte Stix about one of the biggest questions of our time: what happens when AI learns to lie?Can AI manipulate humans? Who should set the rules for powerful AI systems? And can we keep pace with technology? We unpack the growing risks of deceptive AI, why international cooperation matters, and what can still be done to make AI safer, more transparent, and better controlled. Read the Science Brief on AI Deception here: https://www.un.org/scientific-advisory-board/en/ai-deceptionFollow the work of the UN Secretary-General’s Scientific Advisory Board through its Science Briefs, newsletter and social channels: 🌐 Website: https://www.un.org/scientific-advisory-board/en💼 LinkedIn: https://www.linkedin.com/company/un-scientific-advisory-board/𝕏: https://x.com/ScienceBoard_UN▶️ YouTube: https://www.youtube.com/@UNScientificAdvisoryBoard