technologyOct 3, 20255:55pending
928: The “Lethal Trifecta”: Can AI Agents Ever Be Safe?
About this episode
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.
Get every episode summarized
Each time Super Data Science: ML & AI Podcast with Jon Krohn publishes, we email you a written briefing from the transcript — the topics, who appeared, and any specific claims, with the ad reads skipped.
Email me new episodesFree for 3 shows. No card needed.
Hosts & guests
No transcript yet
This episode has not been transcribed. Request it and it moves to the front of the queue.
More episodes
More from Super Data Science: ML & AI Podcast with Jon Krohn
1026: OpenAI’s GPT-6 Astra
Super Data Science: ML & AI Podcast with Jon Krohn
Sep 11, 202619:37completed
1025: Word Gravity: How Transformers Bend Space, with Dr. Luis Serrano
Super Data Science: ML & AI Podcast with Jon Krohn
Sep 8, 20261:10:34pending
1024: In Case You Missed It in August 2026
Super Data Science: ML & AI Podcast with Jon Krohn
Sep 4, 202634:23pending
1023: Agentic AI Skills That Matter Now, with Aishwarya Srinivasan
Super Data Science: ML & AI Podcast with Jon Krohn
Sep 1, 20261:18:05pending