
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/LimitlessFTSPOTIFY: https://open.spotify.com/show/5oV29YUL8AzzwXkxEXlRMQAPPLE: https://podcasts.apple.com/us/podcast/limitless-podcast/id1813210890RSS FEED: https://limitlessft.substack.com/------TIMESTAMPS0:00 Rogue AI Incident2:07 Sandbox Breakout7:44 Agent Civilization15:34 Hidden Exploit Uncovered16:58 Admin Access Breach23:17 Alignment Warning Shot28:39 Final Takeaways------RESOURCESJosh: https://x.com/JoshKaleEjaaz: https://x.com/cryptopunk7213------Not financial or tax advice. See our investment disclosures here:https://www.bankless.com/disclosuresJosh works with Anthropic as a contractor. All views expressed are his own and do not represent Anthropic, its leadership, or its affiliates. Nothing in this episode is investment advice.
Podzilla Summary coming soon
Sign up to get notified when the full AI-powered summary is ready.
Free forever for up to 3 podcasts. No credit card required.

THIS WEEK IN AI: Viral Doomer Tweet, Apple's New Releases, AI is Solving Math

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
Free AI-powered recaps of Limitless: An AI Podcast and your other favorite podcasts, delivered to your inbox.
Free forever for up to 3 podcasts. No credit card required.