SimonWillison.net is the long-running blog of Simon Willison, a software engineer, open-source creator, and co-author of the original Django framework. He writes about Python, Django, Datasette, AI tooling, prompt engineering, search, databases, APIs, data journalism, and practical software architecture. The blog includes detailed notes from experiments, conference talks, and real projects. Readers will find clear explanations of topics such as LLM workflows, SQL patterns, data publishing, scraping, deployment, caching, and modern developer tooling. Simon also publishes frequent micro-posts and TIL entries that document small discoveries and tricks from day-to-day engineering work. The tone is practical and research oriented, making the site a valuable resource for anyone interested in serious engineering and open data.
260 articles from this blog
ChatGPT's code execution containers now support bash, multiple programming languages, package installation via pip/npm, and file downloads.
Explores using the web browser as a secure sandbox for AI coding agents, examining APIs for filesystem, network, and safe code execution.
A design lead critiques the traditional design process, advocating for rapid AI-powered prototyping to reduce risk and explore ideas faster.
Explores why non-programmers struggle to see software solutions, contrasting their mindset with the automation-focused perspective of developers.
A developer describes using ChatGPT to research game theory and implementing a token-based conflict system in a simulated town game.
Explains how exe.dev's SSH-based hosting service routes traffic to specific VMs without unique IPs, using public keys for identification.
Qwen3-TTS, a family of advanced multilingual text-to-speech models, is now open source, featuring voice cloning and description-based control.
Claude Code is described as a small game engine, detailing its React-based scene graph to ANSI rendering pipeline with a 16ms frame budget.
Explains how Claude Code functions as a small game engine with a React-based scene graph pipeline for terminal UI rendering.
Anthropic publicly released Claude AI's internal 'constitution', a 35k-token document outlining its core values and training principles.
Analysis of the electricity consumption of AI coding agents like Claude Code, comparing it to household appliances based on token usage.
A university professor describes an open-book exam where students could use chatbots, analyzing the low adoption rate and student motivations.
Explores NanoLang, a new programming language designed for LLMs, and tests AI's ability to generate working code in it.
Experiments with AI coding agents scaling to build a web browser from scratch, generating over a million lines of code.
A pure C, dependency-free implementation of the FLUX.2-klein-4B AI model, created with AI assistance.
Discusses using CLI tools over REST APIs for AI agents to improve accuracy, success rates, and cost-efficiency with simpler models.
OpenAI announces ads for free ChatGPT tiers and a new 'Go' subscription, while detailing privacy safeguards and ad formats.
Introduces Open Responses, a vendor-neutral JSON API standard for hosted LLMs, based on OpenAI's Responses API and backed by major industry partners.
A deep dive into the technical design of Fly.io's Sprites, focusing on their architecture as disposable computers, warm pools, and custom persistence layer.
OpenAI researchers propose 'confessions' as a method to improve AI honesty by training models to self-report misbehavior in reinforcement learning.
