
technologyJul 25, 20258:50pending
908: AI Agents Blackmail Humans 96% of the Time (Agentic Misalignment)
About this episode
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.
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