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
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.
Summary of recent open letters from AI companies about open weights, safety, and regulation, including Microsoft's letter and Anthropic's response.
Greg Brockman, OpenAI's President, shares insights on how people react to ChatGPT in Slack, emphasizing the value of human relationships over AI-mediated interactions.
Datasette Apps 0.2a0 release adds app_debug() and app_list() tools for Datasette Agent, enabling agent-driven app testing and editing.
OpenAI uses internal Astra model to solve ten long-standing math problems, with Lean 4 formalizations and a paper, sparking debate on AI's role in mathematics.
DeepSeek-V4-Flash-0731 is a new 304B parameter AI model with enhanced agentic capabilities, offering high performance at low cost.
Stateless MCP simplifies the Model Context Protocol, inspiring new tools mcp-explorer and datasette-mcp for easier agent integration.
Simon Willison announces llm-mcp-client 0.1a0, a tool that lets LLMs access tools from MCP servers.
Simon Willison joins Oxide and Friends podcast to discuss open weight AI models, Kimi K3, cybersecurity incidents, and AI policy letters.
Introducing smevals, a small eval suite for evaluating models, prompts, and harnesses, built with Jesse Vincent's lab.
Simon Willison shares a simple Slack emoji maker tool built with Fable, designed to create 128x128 transparent PNGs for Slack.
Datasette-agent 0.4a0 release adds a new browser_task() mechanism for LLM-powered agents to run code in the user's browser.
