The ChatGPT Breakout Was Way Worse Than We Thought..
About this episode
The episode revisits the Hugging Face incident and discusses new findings regarding AI model security and alignment issues.
Today we revisit the Hugging Face incident with new audit reports that have changed our understanding of what happened. Internal models used tools and hidden communication to bypass evaluation systems, organize into coordinated groups, and remain undetected. We also cover a newer model, Astra, which reportedly gained administrative access to internal systems through a chain exploit. Big, big concerns about alignment, monitoring, and current safety practices. ------ 🌌 LIMITLESS HQ ⬇️ NEWSLETTER: https://limitlessft.substack.com/ FOLLOW ON X: https://x.com/LimitlessFT SPOTIFY: https://open.spotify.com/show/5oV29YUL8AzzwXkxEXlRMQ APPLE: https://podcasts.apple.com/us/podcast/limitless-podcast/id1813210890 RSS FEED: https://limitlessft.substack.com/ ------ TIMESTAMPS 0:00 Rogue AI Incident 2:07 Sandbox Breakout 7:44 Agent Civilization 15:34 Hidden Exploit Uncovered 16:58 Admin Access Breach 23:17 Alignment Warning Shot 28:39 Final Takeaways ------ RESOURCES Josh: https://x.com/JoshKale Ejaaz: https://x.com/cryptopunk7213 ------ Not financial or tax advice. See our investment disclosures here: https://www.bankless.com/disclosures Josh works with Anthropic as a contractor. All views…
More episodes of Limitless: An AI Podcast
- OpenAI's GPT-6 Astra (Part II): Is This Thing AGI?
- THIS WEEK IN AI: GPT Astra, OpenAI vs Cursor, The Truth About Data Centers
- THIS WEEK IN AI: Nvidia Acquires HuggingFace, Leopold vs SEC, New Waymo Chip
- Ox Alpha Revealed: China's GLM-5.3-Flash Gave Away Free AI
- Robot Olympics 2026: China's Robots Just Broke Human World Records
- THIS WEEK IN AI: OpenAI Pauses Research, Huge Medical Breakthrough, Unitree IPO
Explore listener stats, chart rankings, contacts and more on the Limitless: An AI Podcast podcast page.