Series

How to use AI

Practitioner discipline for working with AI: review, trust, safety, and context.

1. 1 AI Code Hallucinations: When Your AI Writes Confident Nonsense AI coding agents hallucinate: they invent APIs, fabricate packages, and write confident, wrong code. Here is how to catch it before it reaches production. Feb 13, 2026 · AI · 4 min read
2. 2 We Became Editors-in-Chief, and Nobody Trained Us Agentic development didn't make us prompt engineers. It made reviewing the job, and nobody built tooling yet for the real bottleneck: how long a human can stay sharp. Aug 1, 2026 · AI · 5 min read
3. 3 Claude Code Auto Mode: What Still Needs a Human Anthropic says auto mode catches 89% of dangerous commands against 13.6% for human reviewers, and still calls it not risk-free. The config, hooks, and review habits that keep it honest. Aug 10, 2026 · AI · 8 min read
4. 4 Context Engineering: The Discipline That Keeps AI From Writing Slop AI slop isn't usually a bad model, it's bad context. Here's the discipline that prevents it, the failure modes behind it, and three checks you can actually run to enforce it. Aug 17, 2026 · AI · 7 min read