928: The “Lethal Trifecta”: Can AI Agents Ever Be Safe?
An episode of the Super Data Science: ML & AI Podcast with Jon Krohn podcast, hosted by Jon Krohn, titled "928: The “Lethal Trifecta”: Can AI Agents Ever Be Safe?" was published on October 3, 2025 and runs 5 minutes.
October 3, 2025 ·5m · Super Data Science: ML & AI Podcast with Jon Krohn
Summary
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.
Episode Description
Similar Episodes
Apr 9, 2026 ·12m
Apr 7, 2026 ·14m
Apr 7, 2026 ·10m