In May 2025, researchers discovered a universal jailbreak that works on GPT-4, Claude, Gemini, and more. It lets anyone bypass safety filters and extract harmful, even criminal instructions — using just a prompt.They warned OpenAI, Google, Anthropic, and Microsoft.Most did nothing.In this episode, we break down what really happened, why it matters, and what it means for anyone using AI right now.Sources: 📄 Official Research Papers:https://arxiv.org/abs/2307.15043https://arxiv.org/abs/2505.10066📰 Article:https://www.techradar.com/computing/a...🎧 Listen to the podcast: https://podcasts.apple.com/us/podcast...📩 Get the AI for Everyone Linkedin newsletter: / 7133153749287501824 🌐 LaunchReady.ai: https://launchready.ai/
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