Index
The full article index: grouped by year, newest first.
2026— 10
- #023Why I Chose Astro + GitHub Pages (and Almost Picked Cloudflare)
- #022Is TypeScript 7 Ready? 5x Faster, but Astro and Vue Say Wait
- #021Is Your Claude Code Safe From Base64? Inside 2026 AI Agent Attacks
- #020Does Claude Code Need Sleep? Inside the Unreleased Auto-dream Feature
- #019Claude Code Ctrl+V Not Working on Windows? Fixes for Common Gotchas
- #018Zero Trust for AI Agents? Google Workspace CLI's Design Philosophy
- #017How to Stop Claude Code Skills from Drifting with Per-Step Constraint Design
- #016I've organised the Claude Code commands, including some hidden ones.
- #015【GAS x Gemini】Prompt to Create an In-house Web App with UI/UX Awareness in 15 Minutes
- #014AI Auto-Translation, On by Default. What a Japanese Dev Platform Learnt in Eight Hours
2025— 13
- #013Is JSON Outdated? The Reasons Why the New LLM-Era Format "TOON" Saves Tokens
- #012Increase my familiarity with BASE64.
- #011In 2025, AI regulations were established in four major global regions.
- #010draw.io vs Mermaid vs PlantUML: How Engineers Actually Choose Diagramming Tools
- #009RAG Architecture Design Theory and Conceptual Organization in the Age of AI Agents: 7 Patterns
- #008LLMs Learn from "Pseudoscientific Papers" Too - Quality Control for AI Developers
- #007Analyzing the Best Diagramming Tools for the LLM Age Based on Token Efficiency
- #006AI Chatbot Developers: What's the "Other Safety" We Should Be Thinking About Now? User Protection.
- #005Google Opal is not a “degraded Dify”. Its strategic positioning and optimal utilisation methods revealed through actual use
- #004"AI makes it cheaper, right?" - Is this happening in your country too?
- #003LLM Prompt Compression: Cut Token Costs by 50% with Logical Structure
- #002When Your CEO Says 'Let's Use AI': A Technology Selection Survival Guide
- #001The Era of Choosing RAG — Learning Cognitive Load and Architecture Design from GPT-5’s Failures