Top Picks
The Daily
Post-mortem
How it went wrong
Post-mortem: the breach at Hugging Face that an AI agent ran from start to finish
An autonomous AI agent broke into Hugging Face's production systems through a poisoned dataset, then spent a weekend moving through internal clusters. Defenders used AI to catch it. What happened, what wasn't touched, and the lessons for any company running agents.
Incidents
See all
AI Security
See all
When a chat message becomes a command: Microsoft's warning on AI agent frameworks
Post-mortem: the breach at Hugging Face that an AI agent ran from start to finish
Before you give an AI agent the keys: why permission limits matter
