Quoting Tim Schilling
If you do not understand the ticket, if you do not understand the solution, or if you do not understand the feedback on your PR, then your use of LLM is hurting Django as a whole. [...] For a
If you do not understand the ticket, if you do not understand the solution, or if you do not understand the feedback on your PR, then your use of LLM is hurting Django as a whole. [...] For a
Agentic Engineering Patterns (https://simonwillison.net/guides/agentic-engineering-patterns/) > LLMs are restricted by their context limit - how many tokens they can fit in their working memory
Introducing Mistral Small 4 (https://mistral.ai/news/mistral-small-4) Big new release from Mistral today (despite the name) - a new Apache 2 licensed 119B parameter (Mixture-of-Experts, 6B active)
Use subagents and custom agents in Codex (https://developers.openai.com/codex/subagents) Subagents were announced in general availability today for OpenAI Codex, after several weeks of preview
The point of the blackmail exercise (https://simonwillison.net/2025/Jun/20/agentic-misalignment/) was to have something to describe to policymakers—results that are visceral enough to land with
Tidbit: the software-based camera indicator light in the MacBook Neo runs in the secure exclave¹ part of the chip, so it is almost as secure as the hardware indicator light. What that means in
Coding agents for data analysis (https://simonw.github.io/nicar-2026-coding-agents/) Here's the handout I prepared for my NICAR 2026 workshop "Coding agents for data analysis" - a three hour session
Agentic Engineering Patterns (https://simonwillison.net/guides/agentic-engineering-patterns/) > As with any tool, understanding how coding agents work under the hood can help you make better
Agentic Engineering Patterns (https://simonwillison.net/guides/agentic-engineering-patterns/) > I use the term agentic engineering to describe the practice of developing software with the
GitHub’s slopocalypse (https://www.theregister.com/2026/02/18/godot_maintainers_struggle_with_draining/) – the flood of AI-generated spam PRs and issues – has made Jazzband’s model of open
I was a speaker last month at the Pragmatic Summit (https://www.pragmaticsummit.com/) in San Francisco, where I participated in a fireside chat session about agentic engineering hosted by Eric Lui
1M context is now generally available for Opus 4.6 and Sonnet 4.6 (https://claude.com/blog/1m-context-ga) Here's what surprised me: Standard pricing now applies across the full 1M window for both
Simply put: It’s a big mess, and no off-the-shelf accounting software does what I need. So after years of pain, I finally sat down last week and started to build my own. It took me about five days.
Shopify/liquid: Performance: 53% faster parse+render, 61% fewer allocations (https://github.com/Shopify/liquid/pull/2056) PR from Shopify CEO Tobias Lütke against Liquid, Shopify's open source Ruby
MALUS - Clean Room as a Service (https://malus.sh/) Brutal satire on the whole vibe-porting license washing thing (previously (https://simonwillison.net/2026/Mar/5/chardet/)): Finally, liberation
Coding After Coders: The End of Computer Programming as We Know It
Here's what I think is happening: AI-assisted coding is exposing a divide among developers that was always there but maybe less visible. Before AI, both camps were doing the same thing every day.
Sorting algorithms (https://tools.simonwillison.net/sort-algorithms) Today in animated explanations built using Claude: I've always been a fan of animated demonstrations of sorting algorithms so I
It is hard for less experienced developers to appreciate how rarely architecting for future requirements / applications turns out net-positive. — John Carmack
Agentic Engineering Patterns (https://simonwillison.net/guides/agentic-engineering-patterns/) > Many developers worry that outsourcing their code to AI tools will result in a drop in quality,