The artificial Turk and our role as software experts
Software experts must balance enthusiasm for generative AI's genuine capabilities with critical scrutiny to prevent unchecked hype from driving poor technical decisions.
Ai
Running multiple Claude accounts without logging out
How to manage multiple Claude Code accounts across different machines using Jean-Claude to selectively sync configuration while keeping account-specific data separate.
QA is the last bottleneck
As software development feedback loops accelerate toward minutes, quality assurance remains the final bottleneck where human judgment is still required.
Daily Doom: Fighting demons and software entropy
An experiment in fully autonomous software development
Why AI will not kill Open Source
Open source will survive the rise of AI coding agents — it represents a creative human endeavor that AI tools themselves depend upon.
The IDE of the Future: Agentcraft Review
A deep dive into Agentcraft, a Warcraft-inspired IDE that lets you manage a legion of coding agents simultaneously
AI writing is terrible. Except for lab notes.
Why we should use LLM context to write technical articles.
Jean-Claude: Syncing Claude Code Config Across Machines
A companion CLI for syncing your Claude Code configuration — CLAUDE.md, settings, hooks, and skills — across all your machines using Git.
The Great AI Overengineering Olympics
4 AI agents build Hello World in Java with TDD, DDD, BDD and hexagonal architecture. The results are magnificent enterprise-grade atrocities.
Why Inference Will Get Dirt Cheap Fast
5 forces that will make AI inference ubiquitous