Sources
Simon Willison

Simon Willison

High-signal independent author. Prefer posts with implementation detail or practical product insight.

Bài viết

Experimenting with Starlette 1.0 with Claude skills
Simon Willison

Experimenting with Starlette 1.0 with Claude skills

ai

Mar 22, 2026

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 …

Perhaps not Boring Technology after all
Simon Willison

Perhaps not Boring Technology after all

technology

Mar 9, 2026

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 …

GPT-5.4 mini and GPT-5.4 nano, which can describe 76,000 photos for $52
Simon Willison

GPT-5.4 mini and GPT-5.4 nano, which can describe 76,000 photos for $52

ai

Mar 17, 2026

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 …

Thoughts on OpenAI acquiring Astral and uv/ruff/ty
Simon Willison

Thoughts on OpenAI acquiring Astral and uv/ruff/ty

ai

Mar 19, 2026

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 …

Writing about Agentic Engineering Patterns
Simon Willison

Writing about Agentic Engineering Patterns

ai

Feb 23, 2026

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 …

Can coding agents relicense open source through a “clean room” implementation of code?
Simon Willison

Can coding agents relicense open source through a “clean room” implementation of code?

ai

Mar 5, 2026

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 …

Profiling Hacker News users based on their comments
Simon Willison

Profiling Hacker News users based on their comments

ai

Mar 21, 2026

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. …

Something is afoot in the land of Qwen
Simon Willison

Something is afoot in the land of Qwen

ai

Mar 4, 2026

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 vibe coded my dream macOS presentation app
Simon Willison

I vibe coded my dream macOS presentation app

ai

Feb 25, 2026

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 …

What to build with LLMs
Simon Willison
8 min read

What to build with LLMs

AI

Mar 11, 2024

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