928: The “Lethal Trifecta”: Can AI Agents Ever Be Safe?

Super Data Science: ML & AI Podcast with Jon Krohn
03/10/2025 5 min
928: The “Lethal Trifecta”: Can AI Agents Ever Be Safe?

Listen "928: The “Lethal Trifecta”: Can AI Agents Ever Be Safe?"

Descargar episodio

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.

More episodes of the podcast Super Data Science: ML & AI Podcast with Jon Krohn

942: Odds of AGI by 2040? LEAP Expert Forecasts and Workforce Implications 21/11/2025
941: Multi-Agent Human Societies, with Dr. Vijoy Pandey 18/11/2025
940: In Case You Missed It in October 2025 14/11/2025
939: Mixture-of-Experts and State-Space Models on Edge Devices, with Tyler Cox and Shirish Gupta 11/11/2025
938: Frontier AI Agents for Data Science, with Sphinx’s Rohan Kodialam 07/11/2025
937: How to Design AI-First Products, with Marc Dupuis 04/11/2025
936: LLMs Are Delighted to Help Phishing Scams 31/10/2025
935: Global Issues Accelerated by AI (with Solutions), feat. Stephanie Hare 28/10/2025
934: Is AI Replacing Junior Workers? 24/10/2025
933: Future-Proofing Your Career in the AI Era, feat. Sheamus McGovern 21/10/2025
© 2003-2025 ZARZA | AHEAD OF OUR TIME
privacy policy
In God we trust In God we trust
PreSales Questions? Click Here
or call our toll-free line at +1-888-5002068 Miami, Florida, USA