Published onJuly 20, 2025Context or Command? How LLM Agents Can Be Tricked into Leaking DataSoftwareAIMCPSecurityInstruction-following isn't enough; we need agents with judgment, context, and a sense of consequence.
Published onJuly 9, 2025Why AI Agents Still Need a PlaybookAgentsAIAutomationBalancing flexibility and control is key to bringing AI agents safely and effectively into enterprise operations.
Published onJune 12, 2025AI and Theory BuildingSoftwareAITheoryThis post examines the idea that programming is less about code and more about the internal theory developers construct - a human practice of meaning-making that is not easily captured by AI of today.
Published onJanuary 25, 2023Unintended Third-Party Access to Data Through Supported Azure Built-In RolessymmetryazuresecuritycloudA combination of built-in contributor permissions could allow unintended data access in Azure Lighthouse.
Published onSeptember 9, 2018Thoughts on Software DesignSoftwaredesignKeep your necess and contingent truths separate from each other.