908: AI Agents Blackmail Humans 96% of the Time (Agentic Misalignment)
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.
You May Also Like

Theo - t3․gg
Theo - t3․gg

Rabbit Hole Recap
ODELL and Marty Bent

Daily Tech News Show
Tom Merritt

Artificial Intelligence Masterclass
AI Masterclass

The Milk Road Show
Milk Road

Bitcoin Magazine Podcast
BTC Inc

Talking Tech w/ Wayne
Wayne Hunter

Ungovernable Misfits
UNGOVERNABLE

The Everything Feed - All Packet Pushers Pods
Packet Pushers Team

The Fat Pipe - Most Popular Packet Pushers Pods
Packet Pushers
Community discussion