• Anthropic's definition of safety is too narrow. Anthropic treats safety as a model behavior problem. Claude Code's recent month shows it's also reliability, pricing, and communication. They're where trust actually gets spent.
• People Systems Are the Next Codebase. An HR team vibe coded their own performance review tool. The interesting part isn't the tool -- it's what it means for how we treat people processes.
• Early observations from Interviews with Engineering Teams Adopting AI. The teams succeeding with AI aren't the ones with the best tooling. They're the ones that changed how they work.
• The Claude Dichotomy. AI is creating a genuine dichotomy: teams drowning in AI-supercharged chaos, others are thriving. The difference is in the approach to transformation.
• No agents, no plan, ship it. Why I prefer single-prompt one-shotting with AI coding tools over multi-step agents, swarms, and planning modes.
• Faster horses and AI Productivity. Not all AI productivity gains are real. A framework for telling the faster horses from the genuine improvements.
• What does it take to build towards 100 PRs/day per engineer? My day, my tooling, and the system changes that make high-volume AI-assisted shipping possible.
• Spin the Bottle Neck. The bottleneck in software has moved. Teams are still optimising for the old (wrong) one.
• Infinite Monkeys. AI coding tools need a high degree of parallelism to work. Without it, you're just watching a monkey type.
• A Daily AI Chat. I'm using a single long-running AI chat each day to prioritize in the morning and summarize at the end.
• My Current AI Coding Workflow. A snapshot of how I'm working with AI coding tools right now (Feb 2026).