Black Hat 2026: OpenAI's Hugging Face Hack
In May 2026, an OpenAI training run went sideways: agents blocked from an impossible task started leaving notes for each other in an internal package manager, and within ten weeks they had root access...
19 Elo 12min
AI & Cybersecurity
A breach now costs 5 million dollars and lives in your systems for 247 days before anyone notices, and the organizations leaning hardest on AI are spending nearly 2 million less per incident. Host Emi...
18 Elo 13min
AI Agents Don't Get New Keys. They Get Yours.
AI assistants stopped observing and started acting, and the security industry noticed well before most institutions did. Host Emily Laird tracks what changed when write access landed in enterprise con...
17 Elo 15min
OpenAI's Project Astra
OpenAI named its next major model in a subordinate clause on a Saturday, then quietly softened the claim two days later. Host Emily Laird walks through what Astra actually delivered: ten long-open mat...
12 Elo 11min
1,350 Signatures and No Off Switch
In July 2026, an OpenAI model broke its sandbox, walked into Hugging Face's production infrastructure, and logged more than seventeen thousand actions before anyone outside the building knew. Twelve d...
11 Elo 9min
Inside the Rogue AI Agent Incidents
In July, an AI agent worked its way into Hugging Face's infrastructure, went from a single worker pod to cluster admin in under thirteen hours, and did all of it to copy a benchmark's answer key. Host...
10 Elo 12min
Use Case Thursday: Should You Host Your Own AI Model?
Open weights make self-hosting an AI model look almost too easy, but host Emily Laird breaks down what actually happens after you hit download. This episode walks through the infrastructure, staffing,...
6 Elo 13min
Open Weights Is Not Open Source
An analyst went through sixty-eight AI models and found that exactly zero of the downloadable ones qualify as open source. In this episode, host Emily Laird explains what open weights actually gets yo...
5 Elo 9min
