ZARZA We are Zarza, the prestigious firm behind major projects in information technology.
Listen "908: AI Agents Blackmail Humans 96% of the Time (Agentic Misalignment)"
Episode Synopsis
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.
Additional materials: www.superdatascience.com/908
Interested in sponsoring a SuperDataScience Podcast episode? Email [email protected] for sponsorship information.
More episodes of the podcast Super Data Science: ML & AI Podcast with Jon Krohn
955: Nested Learning, Spatial Intelligence and the AI Trends of 2026, with Sadie St. Lawrence
06/01/2026
953: Beyond “Agent Washing”: AI Systems That Actually Deliver ROI, with Dell’s Global CTO John Roese
30/12/2025
952: How to Avoid Burnout and Get Promoted, with “The Fit Data Scientist” Penelope Lafeuille
26/12/2025
948: In Case You Missed It in November 2025
12/12/2025
946: How Robotaxis Are Transforming Cities
05/12/2025
In God we trust