Turbo Pascal 3.02A, deconstructed
An interactive deconstruction of the 1985 Turbo Pascal 3.02A binary, using AI to decompile and annotate the classic compiler's assembly code.
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.
117 articles from this blog
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.
Satirical article about a fictional 'Clean Room as a Service' that uses AI to circumvent open source licensing obligations.
An analysis of AI's impact on software development, based on interviews with 70+ developers, discussing automation, testing, and the future of coding.
AI-assisted coding reveals a long-standing divide between developers who prioritize craft and those focused on results.
Creating animated visualizations of sorting algorithms using AI tools, including Python's Timsort and a 'run all' comparison feature.