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.
287 articles from this blog
Simon Willison quotes Romain Huet on OpenAI's GPT-5.5 unifying Codex and main model for agentic coding.
Guide to prompting GPT-5.5 with tips from OpenAI, including migration advice and a trick for multi-step tasks.
Release notes for llm 0.31, a command-line tool for accessing large language models, featuring GPT-5.5 support and new options.
Analysis of why AI and automation are unpopular with the general public despite rising usage numbers, exploring the concept of 'software brain'.
DeepSeek V4 preview models offer frontier-level performance at a fraction of the cost, with up to 1M token context and open weights.
A tool to convert milliseconds to seconds and minutes, created by Simon Willison to simplify LLM prompt duration conversions.
Honker implements Postgres NOTIFY/LISTEN semantics for SQLite, enabling queues and streams with transactional outbox pattern.
Anthropic's postmortem on Claude Code quality issues reveals three bugs in the harness causing forgetfulness and repetition.
How a single Go process on a gaming PC powers Bluesky's For You feed with SQLite and Tailscale.
Browser-based PDF text extraction using LiteParse, a spatial text parsing tool built on PDF.js and Tesseract.js.
Exploring GPT-5.5 via the Codex backdoor API, including a new LLM plugin for using ChatGPT subscriptions with Codex.
Release of llm-openai-via-codex 0.1a0, enabling OpenAI model access via Codex CLI credentials.
A quote from Maggie Appleton on the benefits of learning in public through digital gardening, podcasting, or streaming.
Qwen3.6-27B is a new 27B dense model delivering flagship-level coding performance, surpassing larger models, tested locally with GGUF.
Firefox CTO discusses using Claude Mythos Preview to fix 271 vulnerabilities in Firefox 150, highlighting security improvements.
GitHub Copilot Individual plans are changing with tighter usage limits, paused signups, and new pricing tiers.
Analysis of Anthropic's pricing test moving Claude Code to $100/month plans, causing confusion and backlash.
Testing OpenAI's new ChatGPT Images 2.0 model by generating 'Where's Waldo' style images with a raccoon holding a ham radio.
A critique of AI agents acting too human, lacking stringency and focus, with a call for less human-like behavior.
A blog post about polluting AI training data with pelicans riding bicycles, linked by Simon Willison.
