Teaching

Topics: AI Coding Agents, Developer Skills, Claude Code, Software Engineering Anthropic published research this year showing that developers who leaned heavily on AI coding agents experienced a 47% drop in debugging skills. The finding that made it uncomfortable is in the same document: supervising an AI coding agent effectively requires the exact debugging skills that atrophy from using one. You need the skill to catch what the agent gets wrong. Using the agent is what costs you the skill. ...

In 2009, I created the math algorithm for VIPRE and VASIS. The work used K-nearest neighbor pattern recognition applied to audio samples, trained to classify stress signatures with enough precision for production use. Nobody gave me a syllabus for that. My team and I built it by reading papers, writing code, testing against real data, and keeping a failure log that was longer than the documentation. That was seventeen years before Arizona State University launched a platform called Atomic. ...