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

Super Data Science: ML & AI Podcast with Jon Krohn

Jon Krohn에서 제공하는 콘텐츠입니다. 에피소드, 그래픽, 팟캐스트 설명을 포함한 모든 팟캐스트 콘텐츠는 Jon Krohn 또는 해당 팟캐스트 플랫폼 파트너가 직접 업로드하고 제공합니다. 누군가가 귀하의 허락 없이 귀하의 저작물을 사용하고 있다고 생각되는 경우 여기에 설명된 절차를 따르실 수 있습니다 https://ko.player.fm/legal.

3M ago 8:50

MP3•에피소드 홈

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.

1009 에피소드

#Data Science #Science #Tech #Software Development #Jon Krohn