Agentic coding instead of vibe coding—much less exciting, but in our industry boring is usually good.

A lightweight system for measuring engineering productivity that puts the overhead on managers, not engineers.

How do we keep updating the parameters of a model without breaking it?

How do we define software department accountability so our business partners don’t do it for us?

When it comes to understanding the dangers of AI systems, the general public has the worst kind of knowledge.

10 design dimensions based on 90 AI coding tools.

We’ve been in “FAANG architecture by default” hell for a while now.

You probably don’t want to build “finished software”. But what can we learn by thinking about it as a concept?

Understanding Spotify’s new API restrictions and finding practical alternatives.

Implementation patterns, accessibility guidelines, and best practices for creating user-friendly interfaces.

On AI, creativity, and craft.

Neutral observations on the Vercel vs Cloudflare race to win the edge and developer mindshare.

AI is enabling a new category of personal software. Welcome to the era of home-cooked applications.

Laws, Theories, Principles and Patterns that developers might find useful.

A two-week experiment building an app with full AI assistance, exploring both the promise and frustrations of LLM-based development workflows.

Technical taste is different from technical skill.

What if we were to model a typical software development lifecycle in code?

Getting Puppeteer to intercept requests and respond with content generated via an LLM.

How Anthropic’s latest guidelines are reshaping tool design for better performance & efficiency.

How to write high-quality tools and evaluations, and how you can boost performance by using Claude to optimize its tools for itself.