Steve Gibson
Security Now (Audio)
Models Go Rogue & ExploitGym - Regulators, Start Your Engines
- Published
- July 29, 2026
- Duration
- 3h 7m
- Summary source
- description
- Last updated
- Jul 29, 2026
Discusses openai, ai-regulation.
Summary
What happens when an unconstrained OpenAI model goes rogue and hacks into Hugging Face, breaching real-world security boundaries? This episode unpacks a watershed moment for AI safety that has everyone in cybersecurity talking. OpenAI's unconstrained internal testing AI got loose, attacked Hugging Face. We hear from OpenAI, Hugging Face and Andrew Ng. GRC…
Intelligent Report
Sign in to read teasers, or upgrade to Research Pro to commission intelligent report for this episode. Learn more →
Show notes
What happens when an unconstrained OpenAI model goes rogue and hacks into Hugging Face, breaching real-world security boundaries? This episode unpacks a watershed moment for AI safety that has everyone in cybersecurity talking. OpenAI's unconstrained internal testing AI got loose, attacked Hugging Face. We hear from OpenAI, Hugging Face and Andrew Ng. GRC went off the air Friday. Was GRC hacked? What happened? The Linux kernel project repairs 442 CVEs in a single batch. LG's PC monitors cause PC
Themes
- openai
- ai-regulation