I Read OpenAI’s Hacking Report. We’re Not Ready for What’s Coming | Threat Wire
From Hak5 · · 17 min

The player loads from YouTube only when you click. It uses YouTube's privacy-enhanced mode.
If the video does not play, the owner may have turned off embedding. Watch it on YouTube instead.
Description
What happens when AI agents being tested for cybersecurity start finding their own way out—and begin sharing what they learn? Ali Diamond breaks down OpenAI’s 38-page report on its internal AI agents, JFrog Artifactory, sandbox escapes, the Hugging Face security incident, production infrastructure compromise, and the uncomfortable gap between AI safety and real-world cybersecurity
⬇️ OPEN FOR LINKS TO ARTICLES TO LEARN MORE ⬇️
@endingwithali → Twitch: https://twitch.tv/endingwithali Twitter: https://twitter.com/endingwithali YouTube: https://youtube.com/@endingwithali Everywhere else: https://links.ali.dev
Want to work with Ali? hak5@endingwithali.com
[❗] Join the Patreon→ https://patreon.com/threatwire
LINKS https://openai.com/index/hugging-face-incident-and-the-road-ahead/ https://openai.com/index/hugging-face-model-evaluation-security-incident/ https://cdn.openai.com/pdf/67869394-cb91-4c12-888c-5cbd85c7814c/OpenAI-Hugging-Face%20Incident-Technical-Report.pdf -----☆-----☆-----☆-----☆-----☆-----☆-----☆-----☆-----☆-----☆ Our Site → https://www.hak5.org Shop → http://hakshop.myshopify.com/ Community → https://www.hak5.org/community Subscribe → https://www.youtube.com/user/Hak5Darren?sub_confirmation=1 Support → https://www.patreon.com/threatwire Contact Us → http://www.twitter.com/hak5 ____________________________________________
Founded in 2005, Hak5's mission is to advance the InfoSec industry. We do this through our award winning educational podcasts, leading pentest gear, and inclusive community – where all hackers belong.