5h ago · 4 min read · After 6 months of daily Claude Code usage, I've built a system that turns it from a fancy autocomplete into an autonomous development agent. It reads my architecture patterns, follows my coding standards, connects to 13 external services, and self-ve...
Join discussion10h ago · 7 min read · A deep dive into the Claude Code source code leak - what it reveals about Anthropic Claude internals, agentic AI tool design, and real-world LLM engineering patterns. The Claude Code source code leak
Join discussion
2d ago · 4 min read · Image by Susan Wilkinson Two competing approaches to giving AI coding agents up-to-date knowledge collided this week. Google released official "Agent Skills" for the Gemini API. Vercel published data
Join discussion
3d ago · 4 min read · A recent essay, "After Two Years of Vibecoding, I'm Mass Deleting My AI Slop", struck a nerve. The author spent two years going deeper into AI-assisted coding — starting with small tasks, eventually handing over entire features. The excitement faded ...
Join discussion4d ago · 14 min read · TL;DR: My deterministic AI pipeline burned 50 minutes retrying correct code because infrastructure hadn't been provisioned yet. I restructured from a 12-item single-wave DAG to an 18-item two-wave arc
Join discussion
