Artwork

Content provided by Jon Krohn. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Jon Krohn 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://ppacc.player.fm/legal.
Player FM - Podcast App
Go offline with the Player FM app!

908: AI Agents Blackmail Humans 96% of the Time (Agentic Misalignment)

8:50
 
Share
 

Manage episode 496459600 series 1278026
Content provided by Jon Krohn. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Jon Krohn 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://ppacc.player.fm/legal.

The moral and ethical implications of letting AI take the wheel in business, as revealed by Anthropic: Jon Krohn looks into Anthropic’s latest research on how to use and deploy LLMs safely, specifically in business environments. The team designed scenarios to test the behavior of AI agents when given a goal and a set of obstacles to reach it. Those obstacles included 1) threats to the AI’s continued operation, and 2) conflict between the AI’s goals and the goals of the company. Hear Jon break down the results of this research in this Five-Minute Friday.

Additional materials: ⁠⁠⁠⁠⁠⁠⁠www.superdatascience.com/908⁠

Interested in sponsoring a SuperDataScience Podcast episode? Email [email protected] for sponsorship information.

  continue reading

1217 episodes

Artwork
iconShare
 
Manage episode 496459600 series 1278026
Content provided by Jon Krohn. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Jon Krohn 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://ppacc.player.fm/legal.

The moral and ethical implications of letting AI take the wheel in business, as revealed by Anthropic: Jon Krohn looks into Anthropic’s latest research on how to use and deploy LLMs safely, specifically in business environments. The team designed scenarios to test the behavior of AI agents when given a goal and a set of obstacles to reach it. Those obstacles included 1) threats to the AI’s continued operation, and 2) conflict between the AI’s goals and the goals of the company. Hear Jon break down the results of this research in this Five-Minute Friday.

Additional materials: ⁠⁠⁠⁠⁠⁠⁠www.superdatascience.com/908⁠

Interested in sponsoring a SuperDataScience Podcast episode? Email [email protected] for sponsorship information.

  continue reading

1217 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

Copyright 2025 | Privacy Policy | Terms of Service | | Copyright
Listen to this show while you explore
Play