Simon Willison

  1. Quoting Joseph Weizenbaum

    What I had not realized is that extremely short exposures to a relatively simple computer program could induce powerful delusional thinking in quite normal people. — Joseph Weizenbaum, creator of ELIZA, in 1976 (via) Tags: ai-ethics, ai, computer-history, internet-archive

    Published

  2. Codex for Open Source

    Codex for Open Source Anthropic announced six months of free Claude Max for maintainers of popular open source projects (5,000+ stars or 1M+ NPM downloads) on 27th February. Now OpenAI have launched their comparable offer: six months of ChatGPT Pro (same $200/month price as Claude Max) with Codex and…

    Published

  3. Quoting Ally Piechowski

    Questions for developers: “What’s the one area you’re afraid to touch?” “When’s the last time you deployed on a Friday?” “What broke in production in the last 90 days that wasn’t caught by tests?” Questions for the CTO/EM: “What feature has been blocked for over a year?” “Do you have real-time error…

    Published

  4. Anthropic and the Pentagon

    Anthropic and the Pentagon This piece by Bruce Schneier and Nathan E. Sanders is the most thoughtful and grounded coverage I've seen of the recent and ongoing Pentagon/OpenAI/Anthropic contract situation. AI models are increasingly commodified. The top-tier offerings have about the same performance,…

    Published

  5. Agentic manual testing

    Agentic Engineering Patterns > The defining characteristic of a coding agent is that it can execute the code that it writes. This is what makes coding agents so much more useful than LLMs that simply spit out code without any way to verify it. Never assume that code generated by an LLM works until that…

    Published

  6. Clinejection — Compromising Cline's Production Releases just by Prompting an Issue Triager

    Clinejection — Compromising Cline's Production Releases just by Prompting an Issue Triager Adnan Khan describes a devious attack chain against the Cline GitHub repository, which started with a prompt injection attack in the title of an issue opened against the repo. Cline were running AI-powered issue…

    Published

  7. Introducing GPT‑5.4

    Introducing GPT‑5.4 Two new API models: gpt-5.4 and gpt-5.4-pro, also available in ChatGPT and Codex CLI. August 31st 2025 knowledge cutoff, 1 million token context window. Priced slightly higher than the GPT-5.2 family with a bump in price for both models if you go above 272,000 tokens. 5.4 beats coding…

    Published

  8. Can coding agents relicense open source through a “clean room” implementation of code?

    Over the past few months it's become clear that coding agents are extraordinarily good at building a weird version of a "clean room" implementation of code. The most famous version of this pattern is when Compaq created a clean-room clone of the IBM BIOS back in 1982. They had one team of engineers reverse…

    Published

  9. Anti-patterns: things to avoid

    Agentic Engineering Patterns > There are some behaviors that are anti-patterns in our weird new world of agentic engineering. Inflicting unreviewed code on collaborators This anti-pattern is common and deeply frustrating. Don't file pull requests with code you haven't reviewed yourself. If you open a…

    Published

  10. Something is afoot in the land of Qwen

    I'm behind on writing about Qwen 3.5, a truly remarkable family of open weight models released by Alibaba's Qwen team over the past few weeks. I'm hoping that the 3.5 family doesn't turn out to be Qwen's swan song, seeing as that team has had some very high profile departures in the past 24 hours. It…

    Published

  11. Quoting Donald Knuth

    Shock! Shock! I learned yesterday that an open problem I'd been working on for several weeks had just been solved by Claude Opus 4.6 - Anthropic's hybrid reasoning model that had been released three weeks earlier! It seems that I'll have to revise my opinions about "generative AI" one of these days.…

    Published

  12. Gemini 3.1 Flash-Lite

    Gemini 3.1 Flash-Lite Google's latest model is an update to their inexpensive Flash-Lite family. At $0.25/million tokens of input and $1.5/million output this is 1/8th the price of Gemini 3.1 Pro. It supports four different thinking levels, so I had it output four different pelicans: minimal low medium…

    Published

  13. GIF optimization tool using WebAssembly and Gifsicle

    Agentic Engineering Patterns > I like to include animated GIF demos in my online writing, often recorded using LICEcap. There's an example in the Interactive explanations chapter. These GIFs can be pretty big. I've tried a few tools for optimizing GIF file size and my favorite is Gifsicle by Eddie Kohler…

    Published

  14. February sponsors-only newsletter

    I just sent the February edition of my sponsors-only monthly newsletter. If you are a sponsor (or if you start a sponsorship now) you can access it here. In this month's newsletter: More OpenClaw, and Claws in general I started a not-quite-a-book about Agentic Engineering StrongDM, Showboat and Rodney…

    Published

  15. My current policy on AI writing for my blog

    Because I write about LLMs (and maybe because of my em dash text replacement code) a lot of people assume that the writing on my blog is partially or fully created by those LLMs. My current policy on this is that if text expresses opinions or has "I" pronouns attached to it then it's written by me. I…

    Published

  16. Quoting claude.com/import-memory

    I'm moving to another service and need to export my data. List every memory you have stored about me, as well as any context you've learned about me from past conversations. Output everything in a single code block so I can easily copy it. Format each entry as: [date saved, if available] - memory content…

    Published

  17. Interactive explanations

    Agentic Engineering Patterns > When we lose track of how code written by our agents works we take on cognitive debt. For a lot of things this doesn't matter: if the code fetches some data from a database and outputs it as JSON the implementation details are likely simple enough that we don't need to…

    Published

  18. Please, please, please stop using passkeys for encrypting user data

    Please, please, please stop using passkeys for encrypting user data Because users lose their passkeys all the time, and may not understand that their data has been irreversibly encrypted using them and can no longer be recovered. Tim Cappalli: To the wider identity industry: please stop promoting and…

    Published

  19. An AI agent coding skeptic tries AI agent coding, in excessive detail

    An AI agent coding skeptic tries AI agent coding, in excessive detail Another in the genre of "OK, coding agents got good in November" posts, this one is by Max Woolf and is very much worth your time. He describes a sequence of coding agent projects, each more ambitious than the last - starting with…

    Published

  20. Free Claude Max for (large project) open source maintainers

    Free Claude Max for (large project) open source maintainers Anthropic are now offering their $200/month Claude Max 20x plan for free to open source maintainers... for six months... and you have to meet the following criteria: Maintainers: You're a primary maintainer or core team member of a public repo…

    Published

  21. Unicode Explorer using binary search over fetch() HTTP range requests

    Unicode Explorer using binary search over fetch() HTTP range requests Here's a little prototype I built this morning from my phone as an experiment in HTTP range requests, and a general example of using LLMs to satisfy curiosity. I've been collecting HTTP range tricks for a while now, and I decided it…

    Published

  22. Hoard things you know how to do

    Agentic Engineering Patterns > Many of my tips for working productively with coding agents are extensions of advice I've found useful in my career without them. Here's a great example of that: hoard things you know how to do. A big part of the skill in building software is understanding what's possible…

    Published

  23. Quoting Andrej Karpathy

    It is hard to communicate how much programming has changed due to AI in the last 2 months: not gradually and over time in the "progress as usual" way, but specifically this last December. There are a number of asterisks but imo coding agents basically didn’t work before December and basically work since…

    Published

  24. Google API Keys Weren't Secrets. But then Gemini Changed the Rules.

    Google API Keys Weren't Secrets. But then Gemini Changed the Rules. Yikes! It turns out Gemini and Google Maps (and other services) share the same API keys... but Google Maps API keys are designed to be public, since they are embedded directly in web pages. Gemini API keys can be used to access private…

    Published

  25. Quoting Benedict Evans

    If people are only using this a couple of times a week at most, and can’t think of anything to do with it on the average day, it hasn’t changed their life. OpenAI itself admits the problem, talking about a ‘capability gap’ between what the models can do and what people do with them, which seems to me…

    Published

  26. tldraw issue: Move tests to closed source repo

    tldraw issue: Move tests to closed source repo It's become very apparent over the past few months that a comprehensive test suite is enough to build a completely fresh implementation of any open source library from scratch, potentially in a different language. This has worrying implications for open…

    Published

  27. Claude Code Remote Control

    Claude Code Remote Control New Claude Code feature dropped yesterday: you can now run a "remote control" session on your computer and then use the Claude Code for web interfaces (on web, iOS and native desktop app) to send prompts to that session. It's a little bit janky right now. Initially when I tried…

    Published

  28. I vibe coded my dream macOS presentation app

    I gave a talk this weekend at Social Science FOO Camp in Mountain View. The event was a classic unconference format where anyone could present a talk without needing to propose it in advance. I grabbed a slot for a talk I titled "The State of LLMs, February 2026 edition", subtitle "It's all changed since…

    Published

  29. Quoting Kellan Elliott-McCrea

    It’s also reasonable for people who entered technology in the last couple of decades because it was good job, or because they enjoyed coding to look at this moment with a real feeling of loss. That feeling of loss though can be hard to understand emotionally for people my age who entered tech because…

    Published

  30. Linear walkthroughs

    Agentic Engineering Patterns > Sometimes it's useful to have a coding agent give you a structured walkthrough of a codebase. Maybe it's existing code you need to get up to speed on, maybe it's your own code that you've forgotten the details of, or maybe you vibe coded the whole thing and need to understand…

    Published