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.
74 articles from this blog
Guide to running OpenAI's Codex CLI with a self-hosted LLM on an NVIDIA DGX Spark via Tailscale for remote coding assistance.
The article argues that writing a simple AI agent is the new 'hello world' for AI engineering and a surprisingly educational experience.
An analysis of using LLMs like ChatGPT for academic research, highlighting their utility and inherent risks as research tools.
Moonshot AI's Kimi K2 Thinking is a 1 trillion parameter open-weight model optimized for multi-step reasoning and long-running tool calls.
Analysis of the rising prominence of Chinese AI labs like DeepSeek and Kimi in the global AI landscape and their rapid technological advancements.
A developer documents upgrading a Datasette plugin for the 1.0 alpha, using tools like uv and OpenAI Codex CLI, including video and notes.
Exploring how asynchronous coding agents like Claude Code and Codex can automate code research projects by running experiments and submitting pull requests.
Security advisory for Datasette open redirect vulnerability fixed in versions 0.65.2 and 1.0a21, including additional features.
Chrome, Firefox, and WebKit plan to remove XSLT from browsers by 2026, citing significant security risks in the aging codebase.
Anthropic proposes a new MCP approach that converts tools into executable code for more efficient AI agents, reducing token usage and errors.
Datasette 1.0a20 introduces a major SQL-powered permissions system overhaul, replacing function calls with SQL queries for efficient access control.
A method using color-coding (red/blue) to classify MCP tools and systematically mitigate prompt injection risks in AI agents.
Explores the psychological barriers engineers face when evaluating programming languages outside their expertise, based on Steve Francia's insights.
Announcement of htmx 4, replacing XMLHttpRequest with fetch() and introducing breaking changes with a detailed upgrade plan.
