Writing

ls -t writing/
  1. 2026-09-2521 min

    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

    #rag#retrieval#evaluation

  2. 2026-09-091 min

    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.

    #agents#reliability

  3. 2026-09-074 min

    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.

    #coding-agents#cost

  4. 2025-12-083 min

    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.

    #vibe-coding#safety

entries: 4 · rss.xml