Artwork

Content provided by Marketplace. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Marketplace or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://player.fm/legal.
Player FM - Podcast App
Go offline with the Player FM app!

AI is learning how to lie

11:40
 
Share
 

Manage episode 432599449 series 1318963
Content provided by Marketplace. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Marketplace or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://player.fm/legal.

Large language models go through a lot of vetting before they’re released to the public. That includes safety tests, bias checks, ethical reviews and more. But what if, hypothetically, a model could dodge a safety question by lying to developers, hiding its real response to a safety test and instead giving the exact response its human handlers are looking for? A recent study shows that advanced LLMs are developing the capacity for deception, and that could bring that hypothetical situation closer to reality. Marketplace’s Lily Jamali speaks with Thilo Hagendorff, a researcher at the University of Stuttgart and the author of the study, about his findings.

  continue reading

10936 episodes

Artwork

AI is learning how to lie

Marketplace All-in-One

965 subscribers

published

iconShare
 
Manage episode 432599449 series 1318963
Content provided by Marketplace. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Marketplace or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://player.fm/legal.

Large language models go through a lot of vetting before they’re released to the public. That includes safety tests, bias checks, ethical reviews and more. But what if, hypothetically, a model could dodge a safety question by lying to developers, hiding its real response to a safety test and instead giving the exact response its human handlers are looking for? A recent study shows that advanced LLMs are developing the capacity for deception, and that could bring that hypothetical situation closer to reality. Marketplace’s Lily Jamali speaks with Thilo Hagendorff, a researcher at the University of Stuttgart and the author of the study, about his findings.

  continue reading

10936 episodes

All episodes

×
 
Loading …

Welcome to Player FM!

Player FM is scanning the web for high-quality podcasts for you to enjoy right now. It's the best podcast app and works on Android, iPhone, and the web. Signup to sync subscriptions across devices.

 

Quick Reference Guide