Top Articles

Starlette 1.0 is out! This is a really big deal. I think Starlette may be the Python framework with the most usage compared to its relatively low brand recognition because …

A recurring concern I’ve seen regarding LLMs for programming is that they will push our technology choices towards the tools that are best represented in their training data, making it …

OpenAI today: Introducing GPT‑5.4 mini and nano. These models join GPT-5.4 which was released two weeks ago. OpenAI’s self-reported benchmarks show the new 5.4-nano out-performing their previous GPT-5 mini model …

The big news this morning: Astral to join OpenAI (on the Astral blog) and OpenAI to acquire Astral (the OpenAI announcement). Astral are the company behind uv, ruff, and ty—three …

I’ve started a new project to collect and document Agentic Engineering Patterns—coding practices and patterns to help get the best results out of this new era of coding agent development …

Over the past few months it’s become clear that coding agents are extraordinarily good at building a weird version of a “clean room” implementation of code. The most famous version …

A self-contained offline server packed with encyclopedic knowledge, local AI, and essential tools — ready when the internet isn't.

Here’s a mildly dystopian prompt I’ve been experimenting with recently: “Profile this user”, accompanied by a copy of their last 1,000 comments on Hacker News. Obtaining those comments is easy. …

OpenAI introduces the GPT-4.1 family with stronger coding, instruction following, and long-context performance for developers.

Anthropic announces Claude 3.7 Sonnet with stronger reasoning and Claude Code for agentic developer workflows.

Due to some lucky circumstances, I recently had the chance to appear in one of the biggest German gaming podcasts, Stay Forever, to talk about the technology of RollerCoaster Tycoon (1999). It was …

I’m behind on writing about Qwen 3.5, a truly remarkable family of open weight models released by Alibaba’s Qwen team over the past few weeks. I’m hoping that the 3.5 …

I gave a talk this weekend at Social Science FOO Camp in Mountain View. The event was a classic unconference format where anyone could present a talk without needing to …

Practical guidance on where LLM products deliver value, with an emphasis on useful constraints and user experience.

GitHub Models brings model evaluation and prompt experimentation closer to developers inside the GitHub workflow.

Why I love NixOS is really about the Nix package manager, reproducibility, and sane system management in the LLM coding era.

Linear explores AI-assisted issue intake and workflow triage for high-velocity product teams.

There are a few different reasons to hit the brakes on a Postgres query. Maybe it’s taking too long to finish. Maybe you realised you forgot to create an index that will make it orders of magnitude quicker. Maybe there’s some reason the results are no longer needed. Or maybe you, or your LLM buddy, […]

A cyberattack on a U.S. car breathalyzer company has left drivers across the United States reportedly stranded and unable to start their vehicles.

Notion expands AI from note generation into search, writing, and knowledge workflows across teams.

Japan faced some of the world’s toughest planning problems. It solved them by letting homeowners replan whole neighborhoods privately by supermajority vote.

How much more can we extend lifespans?

The United States have nuclear electricity due to the efforts of one man

Heart disease is the leading cause of death worldwide, but it’s also one of medicine’s biggest success stories.

How Africa Works by Joe Studwell is the sequel to one of the most influential books written on development in recent decades.

Episode 13 of the Works in Progress is about regulation, labour markets, and energy