Economist Podcasts cover image

Shut happens: US federal funding stops

Economist Podcasts

00:00

What Is the Security Flaw in Large Language Models?

Jason Palmer and Alex Hearn introduce the core issue that LLMs do not distinguish between data and instructions, creating prompt-injection risks.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app