More rules should mean better output. That's the intuition. I spent weeks building a comprehensive CLAUDE.md — 200 lines covering naming conventions, security rules, error handling, architectural patterns, import ordering, type safety requirements, and more. I was proud of it. I'd thought through every scenario. Then I scored the output. 79.0 / 100. My carefully crafted documentation was actively
The Problem (3 paragraphs) MuJoCo is the fastest-growing robotics simulator Converting URDF to MJCF is painful (./compile is buggy, urdf2mjcf ignores off-diagonal inertia, mesh paths break) You just want to convert and start training your RL agent The Solution (show curl + Python code) @robot.urdf" import roboinfra Real Example (use your preview_test_arm.urdf) Show the input URDF (6 links, 5 j
The problem (3 sentences) ROS CI pipelines are slow because check_urdf needs full ROS install Most GitHub Actions runners don't have ROS You just want to catch broken joint refs before merging The solution (show the YAML) 6 lines of GitHub Action config No ROS install, no Docker, runs in 5 seconds Real example (screenshot) Show NASA Robonaut 2 URDF passing validation Show a broken URDF failing wit
Have you ever looked at code you wrote six months ago and thought: "Who wrote this monster?"? Relax, it happens to all of us. In software engineering, writing code that a machine understands is the easy part. The real challenge is writing code that other humans (including your future self) can understand, maintain, and scale. This is exactly where Software Design Principles come into play. In this
Part 1 of 5 in The New Engineering Contract — what it means to lead engineers when AI is doing more of the coding. SWE-CI tested 18 AI models across 71 consecutive commits. Most broke something on commit 47 they'd already broken on commit 1. That's not an intelligence problem. That's a learning system that isn't learning. A paper made me uncomfortable this month. Not because of what it found about