Skip to content
TrackPodcasts
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 episodes

Free 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.

908: AI Agents Blackmail Humans 96% of the Time (Agentic Misalignment)

Super Data Science: ML & AI Podcast with Jon Krohn

0:00
8:50

More episodes

More from Super Data Science: ML & AI Podcast with Jon Krohn

View all episodes →