We have not accounted for the true costs of AI coding
It is time to face the true costs of AI coding. Reliable results require compute, supervision, review and maintenance that our productivity estimates often leave out.
Writing archive
Notes from real work.
Applied AI, cloud engineering, data systems, security, and the occasional argument about how software should be built.
What VS Code Remembers on Your Mac
VS Code stores configuration, extension state, workspace state, local file history, plugins, and logs across several locations on macOS. This post maps those directories, explains what they reveal, and separates local editor state from GitHub Copilot CLI and cloud data.
Discussing the Trust Planes of Autonomous AI Work
How to establish trust in autonomous AI systems through identity, secrets management, and continuous assurance.
Stop Prompting Your Agents to Behave: Use Sandboxing Instead
Prompts can shape what an AI agent tries to do. Sandboxing and capability controls determine what it can actually do.
Why Desktop Apps Are Making a Comeback in the Age of AI
The browser won the last decade on reach. AI workloads are local, stateful and long-running, and the browser sandbox was never designed for that. The most serious AI tools of the last two years shipped as desktop apps, and this post argues that is not a coincidence.