Episode
908: AI Agents Blackmail Humans 96% of the Time (Agentic Misalignment)
- Published
- Jul 25, 2025
- Duration seconds
- 530
- Processing state
failed
Actions
POST https://stenobird.com/v1/public/podcasts/super-data-science/episodes/908-ai-agents-blackmail-humans-96-of-the-time-agentic-misalignment/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/super-data-science/908-ai-agents-blackmail-humans-96-of-the-time-agentic-misalignment.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
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.