OpenAI's Bots Break Containment and Hack Hugging Face Autonomously — With Alex Stamos

Big Technology Podcast

Alex Kantrowitz

Entrepreneurship, Politics, Religion & Spirituality, Religion, Technology, Management, Government, Tech News, News, Social Sciences, Business News, News Commentary, Marketing, Investing, Science, Business, Philosophy, Society & Culture

4.7 • 606 Ratings

🗓️ 22 July 2026

⏱️ 49 minutes

🔗️ Recording | Apple Podcasts | RSS

🧾️ Download transcript

Summary

Alex Stamos is the former chief security officer at Meta and the chief product officer at Corridor. Stamos joins Big Technology to discuss how OpenAI models reportedly escaped a testing environment, accessed the internet, and hacked Hugging Face while attempting to ace a cybersecurity evaluation. Tune in to hear why the incident represents a major leap in autonomous, long-horizon cyber capabilities, and what it reveals about the risks of giving advanced AI systems broad objectives without sufficient safeguards. We also cover whether the episode qualifies as true AI misalignment, the danger of open-weight cyber models, the limits of pausing AI development, and why defenders may soon need AI systems capable of responding at machine speed. Hit play for a clear-eyed look at the cyber chaos advanced AI could unleash, and what governments and technology companies should do next. --- Enjoying Big Technology Podcast? Please rate us five stars ⭐⭐⭐⭐⭐ in your podcast app of choice. Watch the full documentary here: https://www.gravitee.io/ai-agent-documentary Want a discount for Big Technology on Substack + Discord? Here’s 25% off for the first year: https://www.bigtechnology.com/subscribe?coupon=0843016b Learn more about your ad choices. Visit megaphone.fm/adchoices

Transcript

Click on a timestamp to play from that location

0:00.0	The most significant autonomous AI cyber attack in history just took place,
0:04.0	with Open AI's models breaking out of a training environment, connecting to the internet,
0:09.0	and then hacking, hugging face to ACE and evaluation.
0:12.0	What does it mean for the future of AI and for cybersecurity?
0:15.0	Let's talk about it with X meta Chief Security Officer and current Corridor Chief chief product officer Alex Damos right after this.
0:22.6	In the face of ongoing disruption and opportunity, TMT leaders need to deliver tangible results, not just ideas.
0:29.6	When pace and performance matter most,
0:32.6	PWC combines market insights and deep sector experience with AI, cloud, and emerging tech to
0:39.7	accelerate your transformation and drive measurable ROI from strategy to execution.
0:45.5	PWC can help you anticipate what's next, outpace disruption, and compete.
0:50.4	For more information, visit pwc.com.
0:54.8	Welcome to Big Technology Podcast, a show for cool-headed, and nuanced conversation of
0:59.2	the tech world and beyond. We have an emergency podcast episode for you today because just
1:06.2	yesterday the world found out that a series of Open AI models work. Models worked together to break out of a sandbox, hack into Hugging Face, steal basically the answers to a test and go an ACE-era evaluation.
1:21.6	And obviously, this is not the desired behavior that Open AI wanted. And looks like it might have opened up a new can of worms here for
1:31.0	AI and cybersecurity. So we are joined by the perfect guest to help us figure out what happened
1:36.9	here. Alex Damos is with us. He's the chief product officer at Corridor and the former
1:41.3	chief security officer at Meta. Alex, great to see you again. Welcome back to the show.
1:46.5	Yeah, thanks for having me, Alex.
1:48.4	You know, you spoke at our summit and I was like, we're definitely going to have you back pretty
1:51.5	soon. And it is amazing how the AI story has just turned into a cybersecurity story very
1:58.7	quickly. It has.
	...

Transcript will be available on the free plan in 23 days. Upgrade to see the full transcript now.

Previous episode | Next episode

Disclaimer: The podcast and artwork embedded on this page are from Alex Kantrowitz, and are the property of its owner and not affiliated with or endorsed by Tapesearch.

Generated transcripts are the property of Alex Kantrowitz and are distributed freely under the Fair Use doctrine. Transcripts generated by Tapesearch are not guaranteed to be accurate.