AI

Testing Blender Scenes Built by LLM Agents

An agent building a Blender scene can't see the viewport, so every claim it makes about clipping, contact, scale or motion has to be measured. These are the twelve families of checks from a 640-frame mech film a team of Claude agents built in bpy, plus the three times the checks themselves were wrong.

How Claude Code's Projects Beta Works Under the Hood

A project is a channel, a thread is a message, and the Claude doing work on your machine is a child of a cloud session you never see. A full walkthrough of the Projects beta, from the channels API down to the process the desktop app spawns in your folder.

Risk Has an Owner

A good AI procurement system moves the accountability line. It doesn't erase it. Notes from someone who does CAPEX procurement for a living.

Data Center Water

How the data center industry uses water, wastes it, and what's changing.

OSS Maintainers Can Inject Their Standards Into Contributors' AI Tools

AI-assisted PRs keep landing with the wrong CSS framework and no tests because the contributor's tool never saw your project's standards. CLAUDE.md and AGENTS.md put them in the tool's context before it writes a line.

Reverse Engineering Claude Desktop's Cowork Mode: A Deep Dive into VM Isolation and Linux Possibilities

Claude Desktop's Cowork mode only runs on macOS. I pointed Claude at the minified app to reverse engineer why, and found a lightweight Linux VM, layered sandboxing, and a real path to Linux support.

Claude Desktop Cowork Mode: VM Architecture Analysis

The complete technical reference behind the Cowork deep-dive: IPC APIs, refactored symbol mappings, telemetry events, VM image internals, and the full layered security architecture.