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/ ]
I built two new tools to help coding agents demonstrate their work beyond just running automated tests: Showboat and Rodney https://simonwillison.net/2026/Feb/10/showboat-and-rodney/
Introducing Showboat and Rodney, so agents can demo what they’ve built
A key challenge working with coding agents is having them both test what they’ve built and demonstrate that software to you, their overseer. This goes beyond automated tests—we need artifacts …
simonwillison.net
February 10, 2026 at 5:52 PM
February 9, 2026 at 5:20 PM
Interesting research in HBR today about how the productivity boost you can get from AI tools can lead to burnout or general metal exhaustion, something I've noticed in my own work https://simonwillison.net/2026/Feb/9/ai-intensifies-work/
AI Doesn’t Reduce Work—It Intensifies It
Aruna Ranganathan and Xingqi Maggie Ye from Berkeley Haas School of Business report initial findings in the HBR from their April to December 2025 study of 200 employees at a …
simonwillison.net
February 9, 2026 at 4:45 PM
In celebration of the 2026 breeding season ceramic artist Karen James made me a Kākāpō mug! https://simonwillison.net/2026/Feb/8/kakapo-mug/
February 8, 2026 at 5:28 PM
@lafncow that was a huge surprise to me when I first met this team... wait a second, you're a security company!?
February 8, 2026 at 12:35 AM
Updated my post to add a section with commentary on the glaring detail I glossed over in my first published version: $1,000/engineer/day in token spends, really? https://simonwillison.net/2026/Feb/7/software-factory/#wait-1-000-day-per-engineer-
February 7, 2026 at 6:15 PM
I wrote about the most ambitious form of AI-assisted software development I've seen yet - Strong DM's "Software Factory" approach, where two of the guiding principles are "Code must not be written by humans" and "Code must not be reviewed by humans" […]
Original post on fedi.simonwillison.net
fedi.simonwillison.net
February 7, 2026 at 3:42 PM
Pelicans for Opus 4.6 and Codex 5.3 - I don't have much interesting to say about these models yet to be honest, they're both incremental improvements on their predecessors and very capable https://simonwillison.net/2026/Feb/5/two-new-models/
Opus 4.6 and Codex 5.3
Two major new model releases today, within about 15 minutes of each other. Anthropic released Opus 4.6. Here's its pelican: OpenAI release GPT-5.3-Codex, albeit only via their Codex app, not …
simonwillison.net
February 5, 2026 at 8:31 PM
They had a most excellent editorial voice, as demonstrated by this "what's new" entry from December 10th 2020 about the height of Mount Everest https://simonw.github.io/cia-world-factbook-2020/docs/whatsnew.html
February 5, 2026 at 12:30 AM
The CIA just stopped publishing their World Factbook and took every page, including the archived copies of previous versions!

This sucks. It was public domain, so I recovered the 2020 edition (the last one published as a zip file) and shared it to GitHub […]
Original post on fedi.simonwillison.net
fedi.simonwillison.net
February 5, 2026 at 12:26 AM
Two new speech-to-text models (similar to Whisper) from Mistral today - one of them is API-only, the other is a 8.9GB Apache-2.0 licensed open weights model for "realtime" transcription. They're both very good! https://simonwillison.net/2026/Feb/4/voxtral-2/
Voxtral transcribes at the speed of sound
Mistral just released Voxtral Transcribe 2 - a family of two new models, one open weights, for transcribing audio to text. This is the latest in their Whisper-like model family, …
simonwillison.net
February 4, 2026 at 10:43 PM
I've been experimenting with distributing Go binaries as wheels on PyPI so you can execute them without installing them first using commands like "uvx sqlite-scanner ~/Downloads" - I wrote sqlite-scanner in Go

I built go-to-wheel to help implement this pattern […]
Original post on fedi.simonwillison.net
fedi.simonwillison.net
February 4, 2026 at 3:04 PM
A few notes on OpenAI's new Codex macOS Electron app - I've had a few days of preview access. I had fun poking around in the SQLite database it uses for scheduled Automations! https://simonwillison.net/2026/Feb/2/introducing-the-codex-app/
Introducing the Codex app
OpenAI just released a new macOS app for their Codex coding agent. I've had a few days of preview access - it's a solid app that provides a nice UI …
simonwillison.net
February 2, 2026 at 7:57 PM
February 2, 2026 at 3:53 PM
New TIL: running OpenClaw in Docker on my Mac - this is an officially documented path but there were still a few things that caught me out, hence my TIL https://til.simonwillison.net/llms/openclaw-docker
Running OpenClaw in Docker
I'm not brave enough to run OpenClaw (aka Clawdbot aka Moltbot) directly on my Mac, so I decided to try running it in a Docker instead container.
til.simonwillison.net
February 2, 2026 at 12:19 AM
I wrote about Clawdbot/Moltbot/OpenClaw and Moltbook, the fascinating, weird and sometimes even useful social network for digital assistants to swap tips and gossip with each other https://simonwillison.net/2026/Jan/30/moltbook/
Moltbook is the most interesting place on the internet right now
The hottest project in AI right now is Clawdbot, renamed to Moltbot, renamed to OpenClaw. It’s an open source implementation of the digital personal assistant pattern, built by Peter Steinberger …
simonwillison.net
January 30, 2026 at 4:46 PM
I wrote about a localStorage trick I've been using to add dynamic per-user features to my blog despite it being served behind a 15 minute Cloudflare cache meaning everyone gets the exact same HTML https://simonwillison.net/2026/Jan/28/dynamic-features-static-site/
Adding dynamic features to an aggressively cached website
My blog uses aggressive caching: it sits behind Cloudflare with a 15 minute cache header, which guarantees it can survive even the largest traffic spike to any given page. I’ve …
simonwillison.net
January 28, 2026 at 10:13 PM
@Edent my favorite open JSON API is the iNaturalist one, we used that for https://www.owlsnearme.com/
Owls Near Me
www.owlsnearme.com
January 28, 2026 at 3:46 PM
@Edent take a look at the "GitHub repository" tab on https://tools.simonwillison.net/sloccount for an example of something I built on their API
SLOCCount - Count Lines of Code
tools.simonwillison.net
January 28, 2026 at 3:44 PM
@Edent GitHub is worth a mention - a thing I really care about is open CORS headers, so that I can hit the API from my own client-side JavaScript - and GitHub serve *every public static file on the site* with open CORS headers via their CDN, including content in Gists

The GitHub API itself […]
Original post on fedi.simonwillison.net
fedi.simonwillison.net
January 28, 2026 at 3:43 PM
The latest entrant in the coding-agent-constructed web browsers is here, this one by @emsh.cat, and it's REALLY impressive - 3 days of development, 20,000 lines of Rust, no Cargo dependencies and it renders HTML+CSS extremely well […]
Original post on fedi.simonwillison.net
fedi.simonwillison.net
January 27, 2026 at 5:00 PM
Notes and a pelican for the new Kimi K2.5 - a multi-modal (image input) model from Moonshot AI which also claims a "self-directed agent swarm paradigm" https://simonwillison.net/2026/Jan/27/kimi-k25/
Kimi K2.5: Visual Agentic Intelligence
Kimi K2 landed in July as a 1 trillion parameter open weight LLM. It was joined by Kimi K2 Thinking in November which added reasoning capabilities. Now they've made it …
simonwillison.net
January 27, 2026 at 3:15 PM
OpenAI shipped a HUGE upgrade to ChatGPT Code Interpreter and failed to document it (even in the release notes) - but ChatGPT can now pip/npm install packages and run code in Python, Node.js, Bash, Ruby, Perl, PHP, Go, Java, Swift, Kotlin, C and C++! […]
Original post on fedi.simonwillison.net
fedi.simonwillison.net
January 26, 2026 at 7:23 PM
I had a fascinating conversation with @wilsonzlin about FastRender, the browser rendering engine he built with the help of 2,000+ coding agents over the past few weeks. It's 47m on YouTube or you can read my highlights here: https://simonwillison.net/2026/Jan/23/fastrender/
Wilson Lin on FastRender: a browser built by thousands of parallel agents
Last week Cursor published Scaling long-running autonomous coding, an article describing their research efforts into coordinating large numbers of autonomous coding agents. One of the projects mentioned in the article …
simonwillison.net
January 23, 2026 at 9:53 PM
TIL on how I use Claude Code on my iPhone with GitHub Pages to preview Claude's changes while it's still working on them https://til.simonwillison.net/claude-code/preview-github-pages
Previewing Claude Code for web branches with GitHub Pages
I'm a big user of Claude Code on the web , Anthropic's poorly named cloud-based version of Claude Code which can be driven via the web or their native mobile and desktop applications.
til.simonwillison.net
January 22, 2026 at 5:56 PM