
Exploring the distant universe, the insides of cells, the abstractions of math, the complexity of information itself, and much more, The Quanta Podcast is a tour of the frontier between the known and the unknown. In each episode, Quanta Magazine Editor-in-Chief Samir Patel speaks with the minds behind the award-winning publication to navigate through some of the most important and mind-expanding questions in science and math. Quanta specifically covers fundamental research — driven by curiosity, discovery and the overwhelming desire to know why and how. Join us every Tuesday for a stimulating conversation about the biggest ideas and the tiniest details.
(If you've been a fan of the Quanta Science Podcast, it will continue here. You'll see those episodes marked as audio edition episodes every two weeks.)
Exploring the distant universe, the insides of cells, the abstractions of math, the complexity of information itself, and much more, The Quanta Podcast is a tour of the frontier between the known and the unknown. In each episode, Quanta Magazine Editor-in-Chief Samir Patel speaks with the minds behind the award-winning publication to navigate through some of the most important and mind-expanding questions in science and math. Quanta specifically covers fundamental research — driven by curiosity, discovery and the overwhelming desire to know why and how. Join us every Tuesday for a stimulating conversation about the biggest ideas and the tiniest details.
(If you've been a fan of the Quanta Science Podcast, it will continue here. You'll see those episodes marked as audio edition episodes every two weeks.)




























































































































































































































































































































Ask ChatGPT how to build a bomb, and it will flatly respond that it “can’t help with that.” But users have long played a cat-and-mouse game to try to trick language models into providing forbidden information. Just as quickly as these “jailbreaks” appear, AI companies patch them by simply filtering out forbidden prompts before they ever reach the model itself.
Recently, cryptographers have shown how the defensive filters put around powerful language models can be subverted by well-studied cryptographic tools. In fact, they’ve shown how the very nature of this two-tier system — a filter that protects a powerful language model inside it — creates gaps in the defenses that can always be exploited. In this episode, Quanta executive editor Michael Moyer tells Samir Patel about the findings and implications of this new work.
Audio coda courtesy of Banana Breakdown.