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
Analysis of system prompt changes between Claude Opus 4.6 and 4.7, including new tools, safety updates, and behavioral improvements.
Anthropic's Claude system prompts transformed into a git timeline for exploring prompt evolution via git log, diff, and blame.
Simon Willison describes using a single AI prompt to add a new 'beats' content type to his blog-to-newsletter tool.
Announcement of PyCon US 2026 in Long Beach with new AI and security tracks, including schedule highlights.
An interactive deconstruction of the 1985 Turbo Pascal 3.02A binary, using AI to decompile and annotate the classic compiler's assembly code.
Kimi.ai congratulates Cursor AI on Composer 2 launch, built on the Kimi-k2.5 model via a commercial partnership.
Analysis of OpenAI's acquisition of Astral, the company behind key Python tools uv, ruff, and ty, and its potential impact on the ecosystem.
Explores using Apple's 'LLM in a Flash' research to run a massive 397B parameter AI model locally on a MacBook by streaming weights from SSD.
Report on a prompt injection attack in Snowflake's Cortex AI agent that allowed malware execution, now fixed.
OpenAI releases GPT-5.4 mini and nano models, detailing performance, pricing, and a cost example for image description.
A Django core developer warns against over-reliance on LLMs in open-source contributions, emphasizing the need for human understanding.
Mistral AI releases Mistral Small 4, a new 119B parameter open model combining reasoning, multimodal, and coding capabilities.
OpenAI Codex now supports subagents and custom agents for AI-assisted coding, similar to features in Claude Code and other platforms.
Explains how the MacBook Neo's software camera indicator runs in a secure chip enclave, preventing unauthorized access.
A workshop handout on using AI coding agents like Claude Code and OpenAI Codex for data analysis, visualization, and cleaning tasks.
Jazzband shuts down due to AI-generated spam overwhelming its open-source collaboration model.
A speaker shares insights from a fireside chat on AI coding agents, discussing adoption stages, trust in AI output, and test-driven development with agents.
Anthropic's Claude Opus 4.6 and Sonnet 4.6 models now offer 1M context at standard pricing, contrasting with competitors' long-context premiums.
A developer builds custom, AI-assisted accounting software to handle complex multi-currency and tax needs, finding off-the-shelf solutions inadequate.
Shopify CEO uses AI coding agent to achieve 53% faster parse+render and 61% fewer allocations in the Liquid template engine.
