Simon Willison
banner
simon.fedi.simonwillison.net.ap.brid.gy
Simon Willison
@simon.fedi.simonwillison.net.ap.brid.gy
Open source developer building tools to help journalists, archivists, librarians and others analyze, explore and publish their data. https://datasette.io […]

[bridged from https://fedi.simonwillison.net/@simon on the fediverse by https://fed.brid.gy/ ]
This is really fun - @beetle_b ran a variant of my pelican riding a bicycle SVG test using POV-Ray instead and got terrible ray-traced pelicans out of a bunch of different models: https://blog.nawaz.org/posts/2025/Oct/pelican-on-a-bike-raytracer-edition/ and […]
Original post on fedi.simonwillison.net
fedi.simonwillison.net
November 9, 2025 at 5:15 PM
OpenAI partially released a new model yesterday called GPT-5-Codex-Mini

No API access yet, but I did some truly horrible things to their Codex CLI app to get it to spit out this SVG of a pelican riding a bicycle
November 9, 2025 at 3:38 AM
I have a hunch that current LLMs might make it easier to launch a brand new programming language, provided you can describe it in a few thousand tokens and ship it with a compiler and linter that coding agents can use […]
Original post on fedi.simonwillison.net
fedi.simonwillison.net
November 7, 2025 at 4:14 PM
Notes on Kimi K2 Thinking, the huge new open weights (but not open source, it's under a "modified MIT license") model from Moonshot AI https://simonwillison.net/2025/Nov/6/kimi-k2-thinking/
Kimi K2 Thinking
Chinese AI lab Moonshot's Kimi K2 established itself as one of the largest open weight models - 1 trillion parameters - back in July. They've now released the Thinking version, …
simonwillison.net
November 6, 2025 at 11:56 PM
RE: https://mastodon.social/@Sarahp/115504173496002298

Glad to see this become a universal feature as opposed to one that was limited to specific clients
November 6, 2025 at 6:34 PM
Made a new video demonstrating my process for upgrading a Datasette plugin using uv and an OpenAI Codex bash one-liner https://www.youtube.com/watch?v=qy4ci7AoF9Y

Here are detailed notes to accompany the video on my blog: https://simonwillison.net/2025/Nov/6/upgrading-datasette-plugins/
Video + notes on upgrading a Datasette plugin for the latest 1.0 alpha
I’m upgrading various plugins for compatibility with the new Datasette 1.0a20 alpha release and I decided to record a video of the process. This post accompanies that video with detailed …
simonwillison.net
November 6, 2025 at 6:32 PM
I've been getting a lot of value using coding agents for code research tasks recently - I have a dedicated simonw/research GitHub repo and I frequently have them run detailed experiments and write up the results. Here's how I'm doing that + some examples […]
Original post on fedi.simonwillison.net
fedi.simonwillison.net
November 6, 2025 at 3:58 PM
Achievement unlocked: caused Hacker News to have a 150+ comment argument about a TikTok joke (while I was asleep) https://news.ycombinator.com/item?id=45820872
I’m worried that they put co-pilot in Excel | Hacker News
news.ycombinator.com
November 5, 2025 at 3:24 PM
Datasette 1.0a20 is out, featuring an entirely new SQL-powered permissions system. This is by far the most ambitious project I've attempted with the help of coding agents (Claude Code and Codex CLI in this case) - here are detailed notes on how it works and what I learned along the way […]
Original post on fedi.simonwillison.net
fedi.simonwillison.net
November 4, 2025 at 9:36 PM
I wrote up some notes on two new papers on prompt injection: Agents Rule of Two (from Meta AI) and The Attacker Moves Second (from Anthropic + OpenAI = DeepMind + others) https://simonwillison.net/2025/Nov/2/new-prompt-injection-papers/
New prompt injection papers: Agents Rule of Two and The Attacker Moves Second
Two interesting new papers regarding LLM security and prompt injection came to my attention this weekend. Agents Rule of Two: A Practical Approach to AI Agent Security The first is …
simonwillison.net
November 2, 2025 at 11:11 PM
Just sent out the October edition of my sponsors-only monthly newsletter - you can pay me $10/month to send you less!

Here's the table of contents
https://simonwillison.net/2025/Nov/1/sponsors-only-newsletter/
November 1, 2025 at 10:15 PM
My notes on CoreWeave's acquistion of Marimo - this year they also snapped up Weights & Biases, OpenPipe and Mammoth AI https://simonwillison.net/2025/Oct/31/coreweave-acquires-marimo/
October 31, 2025 at 3:00 PM
MiniMax M2 is the new "most intelligent" open weights model (according to Artificial Analysis) - the MIT licensed weights are just 230GB and it appears comparable to Sonnet 4, while priced closer to Gemini 2.5 Flash. Notes here, including a new LLM plugin […]
Original post on fedi.simonwillison.net
fedi.simonwillison.net
October 29, 2025 at 10:57 PM
Notes on Cursor 2.0 and a pelican drawn by their brand new Composer-1 coding model, which they describe as "4x faster than similarly intelligent models" https://simonwillison.net/2025/Oct/29/cursor-composer/
Composer: Building a fast frontier model with RL
Cursor released Cursor 2.0 today, with a refreshed UI focused on agentic coding (and running agents in parallel) and a new model that's unique to Cursor called Composer 1. As far …
simonwillison.net
October 29, 2025 at 8:48 PM
The GitHub Universe badge this year is a full Raspberry Pi with a color screen and WiFi!

I had a ton of fun hacking around with it yesterday, here are detailed notes on what I've built so far https://simonwillison.net/2025/Oct/28/github-universe-badge/
Hacking the WiFi-enabled color screen GitHub Universe conference badge
I’m at GitHub Universe this week (thanks to a free ticket from Microsoft). Yesterday I picked up my conference badge... which incorporates a full Raspberry Pi with a battery, color …
simonwillison.net
October 28, 2025 at 5:23 PM
It's neat how if you ask Claude Code questions about itself it can answer them, because it knows how to fetch a Markdown index of its own online documentation and then navigate to the right place

I wish more LLM tools would implement the same pattern! […]
Original post on fedi.simonwillison.net
fedi.simonwillison.net
October 24, 2025 at 11:07 PM
Geoffrey Litt just proposed a new analogy for working with AI coding tools that I really like: you are the surgeon, staying in command and doing the most challenging work - the AI tools are your support team and surgical assistants https://simonwillison.net/2025/Oct/24/geoffrey-litt/
A quote from Geoffrey Litt
A lot of people say AI will make us all "managers" or "editors"...but I think this is a dangerously incomplete view! Personally, I'm trying to code like a surgeon. A …
simonwillison.net
October 24, 2025 at 2:29 PM
I recorded a ten minute video showing my vibe-coding process for building a tool for sharing formatted terminal sessions via copy and paste using the new Claude Code for web - now available on YouTube here https://www.youtube.com/watch?v=GQvMLLrFPVI

Here are detailed notes (including the full […]
Original post on fedi.simonwillison.net
fedi.simonwillison.net
October 23, 2025 at 4:17 AM
OpenAI's CISO Dane Stuckey posted an essay (on Twitter) about how their new ChatGPT Atlas browser attempts to deal with the risk of prompt injection attacks, I ended up writing a point-by-point commentary on my blog: https://simonwillison.net/2025/Oct/22/openai-ciso-on-atlas/
Dane Stuckey (OpenAI CISO) on prompt injection risks for ChatGPT Atlas
My biggest complaint about the launch of the ChatGPT Atlas browser the other day was the lack of details on how OpenAI are addressing prompt injection attacks. The launch post …
simonwillison.net
October 22, 2025 at 8:51 PM
I gave a talk last night about "Living dangerously with Claude", on the joys and perils of --dangerously-skip-permissions and how critical it is that we run coding agents in a sandbox so that we can unlock their full potential https://simonwillison.net/2025/Oct/22/living-dangerously-with-claude/
Living dangerously with Claude
I gave a talk last night at Claude Code Anonymous in San Francisco, the unofficial meetup for coding agent enthusiasts. I decided to talk about a dichotomy I’ve been struggling …
simonwillison.net
October 22, 2025 at 12:37 PM
Just for fun, I had Claude Code figure out how to run the ~2001-era Perl and C SLOCCount program in WebAssembly in the browser, complete with a UI for counting source code lines from pasted text, a GitHub repository or a zip file […]

[Original post on fedi.simonwillison.net]
October 22, 2025 at 6:23 AM
Wrote up my first impressions of ChatGPT Atlas, OpenAI's new browser - I remain unconvinced by the entire category of "browser agents", the security and privacy challenges still feel insurmountable to me https://simonwillison.net/2025/Oct/21/introducing-chatgpt-atlas/
Introducing ChatGPT Atlas
Last year OpenAI hired Chrome engineer Darin Fisher, which sparked speculation they might have their own browser in the pipeline. Today it arrived. ChatGPT Atlas is a Mac-only web browser …
simonwillison.net
October 21, 2025 at 6:47 PM
My notes on Claude Code for web, Anthropic's new asynchronous coding agent - I had preview access over the weekend, it's effectively a sandboxed instance of "claude --dangerously-skip-permissions" running in Anthropic's container https://simonwillison.net/2025/Oct/20/claude-code-for-web/
Claude Code for web—a new asynchronous coding agent from Anthropic
Anthropic launched Claude Code for web this morning. It’s an asynchronous coding agent—their answer to OpenAI’s Codex Cloud and Google’s Jules, and has a very similar shape. I had preview …
simonwillison.net
October 20, 2025 at 7:46 PM