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.
292 articles from this blog
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.
LLM 0.32 adds reasoning traces, OpenAI Responses, server-side tools, and smarter logging for CLI and Python API.
Release notes for llm-anthropic 0.26, adding new Claude models, server-side tools, and streaming improvements.
A blog post about running MiniMax-H3, an omni-modal generative system, on Apple Silicon via the MLX port, including setup instructions and a test video.
Simon Willison announces LLM 0.32, a command-line tool for accessing large language models, with new features like reasoning traces and OpenAI Responses support.
Simon Willison discusses Niklas Gruhn's term 'meat proxy' for people who blindly copy AI output, urging readers to understand and validate AI responses before relaying them.
A quote from David Crawshaw about setting up a nightly cron job for software updates, emphasizing open-source devtools.
A comment on Hacker News discussing how LLMs make open source software more accessible for modification, reducing friction in building and understanding code.
condense-json 1.1 release adds structural replacements and merge operations for JSON condensing, with Hypothesis round-trip tests.
Simon Willison releases condense-json 1.0, a Python function for condensing JSON using replacement strings.
