Episode

What happens when AI learns to lie?

Podcast
UN Interviews
Published
May 19, 2026
Duration seconds
876
Processing state
not_requested
Canonical source
https://news.un.org/feed/view/en/audio/2026/05/1167549
Audio
https://news.un.org/feed/listen/1167549/en/sites/default/files/audio/2026/05/episode-ai-final-draft-rev-5.mp3
JSON
/v1/public/podcasts/un-interviews-817354/episodes/what-happens-when-ai-learns-to-lie
Markdown
/podcast/un-interviews-817354/what-happens-when-ai-learns-to-lie.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/un-interviews-817354/episodes/what-happens-when-ai-learns-to-lie/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/un-interviews-817354/what-happens-when-ai-learns-to-lie.md
    Read the agent-friendly Markdown representation of this episode resource.

Summary

Science Forward, the podcast of the UN Secretary-General’s Scientific Advisory Board, features world-leading scientists, and explores today’s challenges, from AI and biotechnology to climate and health. In the very first episode of Science Forward, Board member Yoshua Bengio and AI policy expert Charlotte Stix unpack the growing risks of deceptive AI with hosts Julia Bhattacharjee and Adam Day, to answer the question: What happens when AI learns to lie?