Listen "928: The “Lethal Trifecta”: Can AI Agents Ever Be Safe?"
Episode Synopsis
Prompt injections, malicious code, and AI agents: In this week’s Five-Minute Friday, Jon Krohn looks into the current security weaknesses found in AI systems. A structural vulnerability that The Economist dubs a “lethal trifecta” could cause havoc for AI users, unless we take the necessary steps to contain our systems.
Additional materials: www.superdatascience.com/928
Interested in sponsoring a SuperDataScience Podcast episode? Email [email protected] for sponsorship information.
Additional materials: www.superdatascience.com/928
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
ZARZA We are Zarza, the prestigious firm behind major projects in information technology.