How safe are large language models like ChatGPT and Google’s Gemini? In this episode, we dive into groundbreaking research on AI safety and explore Harbench, a powerful new tool designed to stress-test LLMs against harmful manipulation. With 18 different attack methods tested across 33 models, this study reveals surprising vulnerabilities—and promising solutions. We break down red teaming, contextual attacks, and the innovative R2-D2 defense system that could make AI more resilient. Can LLMs ever be truly safe? Join us as we tackle the risks, defenses, and ethical responsibilities shaping the future of AI.Link: https://arxiv.org/pdf/2402.04249
No persons identified in this episode.
This episode hasn't been transcribed yet
Help us prioritize this episode for transcription by upvoting it.
Popular episodes get transcribed faster
Other recent transcribed episodes
Transcribed and ready to explore now
Eric Larsen on the emergence and potential of AI in healthcare
10 Dec 2025
McKinsey on Healthcare
Reducing Burnout and Boosting Revenue in ASCs
10 Dec 2025
Becker’s Healthcare -- Spine and Orthopedic Podcast
Dr. Erich G. Anderer, Chief of the Division of Neurosurgery and Surgical Director of Perioperative Services at NYU Langone Hospital–Brooklyn
09 Dec 2025
Becker’s Healthcare -- Spine and Orthopedic Podcast
Dr. Nolan Wessell, Assistant Professor and Well-being Co-Director, Department of Orthopedic Surgery, Division of Spine Surgery, University of Colorado School of Medicine
08 Dec 2025
Becker’s Healthcare -- Spine and Orthopedic Podcast
NPR News: 12-08-2025 2AM EST
08 Dec 2025
NPR News Now
NPR News: 12-08-2025 1AM EST
08 Dec 2025
NPR News Now