Writing
ls -t writing/
RAG End to End: A Practical Tutorial
What it is, how each piece works, how it is evaluated, a production example on Azure, and a comparison of Azure · Google Cloud · open source
The model decides what. Code decides how.
If AI writes excellent code, why turn every deterministic step of an agent into a tool? Because “sometimes” compounds.
How Coding Harness Affects Token Consumption
Same model, same tasks, three harnesses. What Claude Code, OpenCode and Pi consumed, and how much my own configuration skewed the comparison.
An Essential Guide to Safe Development Practices in the Era of Vibe Coding
Real failures from Replit and Gemini CLI, what research says about how autonomous agents fail, and the non-negotiable practices for AI-assisted development.
entries: 4 · rss.xml