Simon Willison — 2026-06-24#

Highlight#

Today’s most interesting post is Simon’s creation of browser-compat-db, demonstrating a clever mix of AI-assisted programming to convert Mozilla’s MDN compatibility data into a SQLite database, along with a neat CI/CD trick for hosting it. It perfectly encapsulates his workflow of using frontier models like Opus 4.8 and GPT-5.5 to rapidly build, deploy, and explore small, sharp data tools.

Posts#

simonw/browser-compat-db · Source Inspired by Mozilla’s new MDN Model Context Protocol (MCP) service, Simon used Claude Code for web (Opus 4.8) to write a script that converts the comprehensive browser compatibility repository into a ~66MB SQLite database. To bypass the fact that GitHub Releases do not provide open CORS headers, he utilized Codex Desktop (GPT-5.5) to build a GitHub Actions workflow that force-pushes the database to an “orphan” branch. This deployment strategy allows the database to be served via GitHub’s CDN with open CORS headers, enabling immediate exploration directly in the browser via Datasette Lite.

Quoting Tom MacWright · Source Simon highlights an observation from Tom MacWright regarding the influx of job applicants using LLMs to generate their entire portfolios, from application text to GitHub repository commit messages. The core takeaway is a warning about “accidental anonymity”: when a resume or portfolio is perfectly prompted and heavily generated by AI, it becomes entirely generic and impersonal, stripping away any true signal about the actual person behind the screen.

Project Pulse#

Today’s updates offer a perfect contrast in modern AI usage: showcasing the immense practical power of LLMs for rapidly building and deploying open-data tools (using multiple state-of-the-art models for coding and infrastructure), while simultaneously cautioning against AI misuse that erodes personal authenticity in the developer community.