SN 1089: Models Go Rogue & ExploitGym - Regulators, Start Your Engines
From Security Now (Audio) · · 3 hr 7 min
This plays from the publisher's own server. We do not host a copy.
Description
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 adware installation.
- France bans all social media access below age 15.
- WordPress' recent CRITICAL vulnerability claims victims.
- Amazing details about "Rocky" from Andy Weir.
- The new AI exploit ranking benchmark that caused the breakout
Show Notes - https://www.grc.com/sn/SN-1089-Notes.pdf
Hosts: Steve Gibson (https://twit.tv/people/steve-gibson) and Leo Laporte (https://twit.tv/people/leo-laporte)
Download or subscribe to Security Now at https://twit.tv/shows/security-now.
You can submit a question to Security Now at the GRC Feedback Page (https://www.grc.com/feedback.htm).
For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com (https://www.grc.com/securitynow.htm), also the home of the best disk maintenance and recovery utility ever written Spinrite 6 (https://www.grc.com/sr/spinrite.htm).
Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit
Sponsors: - adaptivesecurity.com (https://www.adaptivesecurity.com/?utm_source=podcast&utm_medium=other&utm_campaign=2026_NA_Podcast_security_now&utm_id=701Rd00000d9YqPIAU)
- XBOW.com (http://XBOW.com)
- cohesity.com/Resilience (http://cohesity.com/Resilience)
- threatlocker.com/twit (http://threatlocker.com/twit)