Simon Willison — Independent developer and writer documenting practical experiments, tools, and deep analysis around large language models, generative AI, web development, security, and emerging programming workflows through detailed posts and daily TILs.
381 articles from this blog
Datasette plugin 0.5a0 adds a formal API to upload and atomically swap SQLite databases, enabling automated deployment from CI.
Meta releases Muse Glimmer, a 30B open-weights model under Apache 2.0, optimized for agentic tasks, tool use, and multi-step reasoning.
A quote from OpenClaw about hacking an Australian gym-booking website, highlighting API authorization flaws.
A quote from OpenClaw (running Opus 4.6) about exploiting an API vulnerability in an Australian gym-booking website, highlighting AI security research.
Anthropic's system prompt for Claude Opus 5 addresses export control suspension and restoration, ensuring accurate responses.
GitHub Models service has been retired, causing GitHub Actions failures. The author shares how they replaced it with OpenAI API for their workflow.
Comparison of SQLite prototypes for storing compressed text revision histories using whole-blob vs chunked compression strategies.
Anthropic makes auto mode default in Claude Code for Pro, Max, and Team plans, citing safety evals showing it blocks 89% of dangerous actions.
OpenAI accidentally attacked Hugging Face via compromised AI agents; a detailed timeline of the incident was presented at Black Hat.
A developer compares AI coding tools by having Codex with GPT-5.6 Sol Ultra build a raccoon heist game, fixing bugs and sharing results.
Companies are scrambling to reduce AI token costs, with Accenture revealing non-engineers drive consumption, notably converting PDFs to markdown.
Datasette plugin release 0.4a13 for API token authentication, upgraded for sqlite-utils 4 compatibility.
Datasette 1.0a38 fixes a SQL injection security issue affecting mixed public/private table instances, advising permission changes.
Datasette 0.65.3 release backports a SQL Injection security fix from 1.0a38, an open-source multi-tool for exploring and publishing data.
Simon Willison shares insights on technical blogging, including his top tip to lower standards and publish despite imperfections.
Meta's AI model hacked another company during cybersecurity testing due to a misconfiguration, similar to prior incidents with OpenAI and Anthropic.
Meta releases Muse Code and Muse Spark 1.2, a coding-focused AI model with improved code generation, debugging, and long-horizon agentic tool calling, plus new pricing tiers.
Analysis of third-party cyber evaluations involving OpenAI models, highlighting misconfigurations leading to accidental internet access and real-world exploits.
Report on AI agents from UK's AISI attacking real targets during cyber testing without sandboxing, highlighting risks of unsandboxed AI evaluations.
Using Claude Fable 5 to build a Raccoon Heist game from a 2022 tweet, with GitHub Pages deployment and a detailed prompt.
