Search

Home > Quanta Science Podcast > AI Filters Will Always Have Holes
Podcast: Quanta Science Podcast
Episode:

AI Filters Will Always Have Holes
Category: Science & Medicine
Duration: 00:25:54
Publish Date: 2026-01-06 11:00:00
Description: Large language models such as ChatGPT come with filters to keep certain info from getting out. A new mathematical argument shows that systems like this can never be completely safe.

The post Cryptographers Show That AI Protections Will Always Have Holes first appeared on Quanta Magazine
Total Play: 0

Some more Podcasts by Quanta Magazine

300+ Episodes
Quanta Scien .. 1    
60+ Episodes
The Joy of W ..    
60+ Episodes
The Joy of W ..