Nostr notes by Simon Willison

Shared some notes on Python 3.15, using it with uv, and features ...

2026-10-12T18:22:38Z

Shared some notes on Python 3.15, using it with uv, and features from Python 3.11 I'm excited to use now that 3.10 is no longer the minimum supported version for my own projects https://simonwillison.net/2026/Oct/12/python-3-15/

Just published this post about how we’re going to need default ...

2026-10-03T23:36:19Z

Just published this post about how we’re going to need default hard budget caps on pretty much everything https://simonwillison.net/2026/Oct/3/default-hard-budget-caps/

Big model release today - I wrote about Claude Opus 5.5, GPT-6 ...

2026-09-22T23:50:58Z

Big model release today - I wrote about Claude Opus 5.5, GPT-6 Sol, and GPT-6 Luna - plus comparison grids of pelicans by the different model families at different reasoning levels https://simonwillison.net/2026/Sep/22/opus-and-sol-and-luna/

My conclusions from the end if the post ...

2026-08-16T23:09:32Z

In reply to nevent1q…76vk
_________________________

My conclusions from the end if the post

Fun bonus: I set Pi up with Qwen 3.8 27B and had it build a ...

2026-08-16T22:41:25Z

In reply to nevent1q…sxvg
_________________________

Fun bonus: I set Pi up with Qwen 3.8 27B and had it build a script for transforming its own .jsonl transcripts to Markdown... which it did!

Here's the transcript of it building the tool I then used to share that transcript https://gist.github.com/simonw/491e55ac9d741202ea0af5d9d93775d4

Here’s my review of Qwen 3.8 27B - I can't remember the ...

2026-08-16T22:20:23Z

Here’s my review of Qwen 3.8 27B - I can't remember the last time I've had this much fun playing with a local model that runs on my own computers https://simonwillison.net/2026/Aug/16/qwen-38-27b/

The new Qwen 3.7 27B, running as a 17GB GGUF in LM Studio on my ...

2026-08-14T20:28:46Z

The new Qwen 3.7 27B, running as a 17GB GGUF in LM Studio on my M5 Max MacBook Pro, just drew me the best pelican riding a bicycle I've seen from any model that runs on my laptop

It did take nearly 21 minutes to generate, and used 22,276 reasoning tokens to produce 3,223 tokens of output. Here's the full transcript: https://tools.simonwillison.net/markdown-svg-renderer#url=https%3A%2F%2Fgist.github.com%2Fsimonw%2Ffc909bea4fecf752c7bf9bad0e9dbf2a

Big new release of my LLM CLI tool and Python library for talking ...

2026-08-05T00:03:28Z

Big new release of my LLM CLI tool and Python library for talking to hundreds of different LLMs - reasoning traces, OpenAI Responses support, server-side tools, smarter logging and a whole lot more
https://simonwillison.net/2026/Aug/4/new-release-of-llm/

Hugging Face just published a highly detailed technical account ...

2026-07-28T21:31:25Z

Hugging Face just published a highly detailed technical account of OpenAI's accidental cyberattack on their systems - it's wild how sophisticated this was: https://huggingface.co/blog/agent-intrusion-technical-timeline

Wrote up some of my own notes here: https://simonwillison.net/2026/Jul/28/anatomy-of-a-frontier-lab-agent-intrusion/

Ruff 0.16.0 - Astral's fast Python linter - came out a few ...

2026-07-25T23:05:29Z

Ruff 0.16.0 - Astral's fast Python linter - came out a few days ago and increased the number of default-enabled rules from 59 to 413, which highlighted all sorts of problems across my projects (1618 in sqlite-utils alone) https://simonwillison.net/2026/Jul/25/ruff/

I wrote about the completely wild incident where OpenAI were ...

2026-07-22T23:53:33Z

I wrote about the completely wild incident where OpenAI were testing a new model and it broke out of its sandbox and broke INTO Hugging Face to steal the answers to the benchmark https://simonwillison.net/2026/Jul/22/openai-cyberattack/

My notes on Kimi K3, plus some thoughts on what we can still ...

2026-07-16T20:25:12Z

My notes on Kimi K3, plus some thoughts on what we can still learn from the pelican benchmark even while it becomes further detached from how good the models are at the things that matter (like agentic tool calling across longer conversations) https://simonwillison.net/2026/Jul/16/kimi-k3/

New TIL: Using uvx in GitHub Actions in a cache-friendly way I ...

2026-07-14T01:08:15Z

New TIL: Using uvx in GitHub Actions in a cache-friendly way

I finally found a recipe that I like for running `uvx tool-name` in GitHub Actions without downloading a fresh copy of the package every time https://til.simonwillison.net/github-actions/uvx-github-actions-cache

... and if you want to see some of OpenAI's own pelicans they ...

2026-07-09T19:50:38Z

In reply to nevent1q…rks9
_________________________

... and if you want to see some of OpenAI's own pelicans they featured a 3D pelican riding a tricycle, bicycle, pony, and another pelican in their livestream this morning: https://www.youtube.com/live/Wq45rvPGNHs?t=1070s

Notes on GPT-5.6, which includes some interesting new additions ...

2026-07-09T19:49:00Z

Notes on GPT-5.6, which includes some interesting new additions to the API (programmatic tool calling and multi-agent in particular) - plus 18 pelicans for the 6 reasoning levels and 3 new models: https://simonwillison.net/2026/Jul/9/gpt-5-6/

Since this is a slightly backwards-incompatible change here's ...

2026-07-07T19:54:06Z

In reply to nevent1q…fyy8
_________________________

Since this is a slightly backwards-incompatible change here's a detailed upgrade guide - which you can read, or feed into your coding agent and have it apply the upgrades for you https://sqlite-utils.datasette.io/en/stable/upgrading.html

I released sqlite-utils 4.0, the 124th release but the first ...

2026-07-07T19:38:20Z

I released sqlite-utils 4.0, the 124th release but the first major version bump since 3.0 back in 2020

I managed to keep things backwards-compatible all the way up to version 3.39 before the accumulated design mistakes forced me to bump that number! https://simonwillison.net/2026/Jul/7/sqlite-utils-4/

I've added video support to my "shot-scraper" browser ...

2026-06-30T16:55:54Z

I've added video support to my "shot-scraper" browser automation tool - you (or your coding agent) can now create a storyboard YAML file and use that to record a video demo of new web application features https://simonwillison.net/2026/Jun/30/shot-scraper-video/

My parallel agent side-project today was having Claude Code port ...

2026-06-22T23:52:18Z

My parallel agent side-project today was having Claude Code port the new Moebius image pinpointing model to ONNX in order to run it entirely in the browser
https://simonwillison.net/2026/Jun/22/porting-moebius/

I just released the first release candidate for sqlite-utils v4, ...

2026-06-21T23:36:44Z

I just released the first release candidate for sqlite-utils v4, adding a migrations system (previously released independently as sqlite-migrate) and support for nested transactions: https://simonwillison.net/2026/Jun/21/sqlite-utils-40rc1/

Lots more information in this post on the Datasette project blog, ...

2026-06-19T00:03:55Z

In reply to nevent1q…amc5
_________________________

Lots more information in this post on the Datasette project blog, including details on our live demo and uv one-liners you can use to try this out on your own machine https://datasette.io/blog/2026/datasette-apps/

Think of this as Claude Artifacts reimagined for Datasette - you ...

2026-06-19T00:03:02Z

In reply to nevent1q…54qx
_________________________

Think of this as Claude Artifacts reimagined for Datasette - you get all the power of artifacts but with a JSON API to a full relational database, allowing your HTML+JS apps to access and store data in all shapes and sizes

Just launched Datasette Apps - a plugin for Datasette that lets ...

2026-06-19T00:01:07Z

Just launched Datasette Apps - a plugin for Datasette that lets you host full HTML+JS apps in an iframe sandbox that can query your database and do interesting things with your data
https://simonwillison.net/2026/Jun/18/datasette-apps/

It's now possible to compile Python extensions (C, C++, Rust ...

2026-06-14T00:08:11Z

It's now possible to compile Python extensions (C, C++, Rust etc) to WebAssembly and distribute them through PyPI such that Pyodide can install them directly https://simonwillison.net/2026/Jun/13/publishing-wasm-wheels/

After two days with Claude Fable 5 the best way I can describe it ...

2026-06-11T23:37:21Z

After two days with Claude Fable 5 the best way I can describe it is "relentlessly proactive" - here's an example where I dropped in a screenshot of a bug and it span up custom CORS Python servers and used pyobjc-framework-Quartz to capture screenshots https://simonwillison.net/2026/Jun/11/fable-is-relentlessly-proactive/

Since the JSON extras API is a little hard to explain without an ...

2026-06-11T18:05:24Z

In reply to nevent1q…q9em
_________________________

Since the JSON extras API is a little hard to explain without an example I also had Fable 5 and GPT-5.5 collaborate on this custom API explorer tool for trying out the new feature https://tools.simonwillison.net/datasette-extras-explorer#url=https%3A%2F%2Flatest.datasette.io%2Ffixtures%2Ffacetable.json%3F_size%3D1%26_facet%3Dstate&extras=count%2Ccount_sql%2Cexpandable_columns%2Cfacet_results

New Datasette release: 1.0a33, which finally brings documents the ...

2026-06-11T18:02:55Z

New Datasette release: 1.0a33, which finally brings documents the ?_extra= JSON API mechanism and brings it to the row and query pages in addition to the table pages

(Most of the code in this release was built with the help of Claude Fable 5) https://datasette.io/blog/2026/api-extras/

Wrote up my initial impressions of Claude Fable 5 - it has a big ...

2026-06-10T00:15:10Z

Wrote up my initial impressions of Claude Fable 5 - it has a big model smell: slow, expensive and capable of crunching through pretty much everything I threw at it https://simonwillison.net/2026/Jun/9/claude-fable-5/

You can try it out like this: uvx micropython-wasm -c ...

2026-06-06T04:33:45Z

In reply to nevent1q…ed5n
_________________________

You can try it out like this:

uvx micropython-wasm -c 'print("Hello world")'

I may have finally found the Python-in-a-sandbox solution ...

2026-06-06T04:32:09Z

I may have finally found the Python-in-a-sandbox solution I've been looking for... here's my latest experiment, this time running MicroPython in WebAssembly inside my Python applications https://simonwillison.net/2026/Jun/6/micropython-in-a-sandbox/

Uber reportedly now caps coding agents at $1,500/month per ...

2026-06-03T12:03:52Z

Uber reportedly now caps coding agents at $1,500/month per employee per tool - seems sensible to me, but it's also an interesting hint at the value Uber thinks these tools are providing https://simonwillison.net/2026/Jun/3/uber-caps-usage/

@nprofile…xqr8 I had it do a NORTH VIRGINIA OPOSSUM ON AN ...

2026-05-29T00:27:31Z

In reply to nevent1q…5ruk
_________________________

nprofile1qy2hwumn8ghj7un9d3shjtnyd968gmewwp6kyqpq4czglsted9rqpntj3xsxyv0chze7vcds95v8y3pvw6zzhn2ewqvqk5xqr8 (nprofile…xqr8) I had it do a NORTH VIRGINIA OPOSSUM ON AN E-SCOOTER too - it made this: https://gist.github.com/simonw/68560eddb0b268a8417f80ceb7304dc6?permalink_comment_id=6172972#gistcomment-6172972

Pales in comparison to GLM-5.1 though https://simonwillison.net/2026/Apr/7/glm-51/#opossum

Notes on Claude Opus 4.8, which Anthropic call "a modest but ...

2026-05-29T00:19:22Z

Notes on Claude Opus 4.8, which Anthropic call "a modest but tangible improvement" - plus pelicans riding bicycles for each of the five different thinking efforts https://simonwillison.net/2026/May/28/claude-opus-4-8/

Given the recent burst of activity around enterprise pricing and ...

2026-05-27T16:39:49Z

Given the recent burst of activity around enterprise pricing and contracts, I think April 2026 was the month when both OpenAI and Anthropic found product-market fit https://simonwillison.net/2026/May/27/product-market-fit/

When I woke up this morning I didn't think I'd be ...

2026-05-26T00:15:09Z

When I woke up this morning I didn't think I'd be spending a bunch of time today getting familiar with Catholic theology, but here we are. Notes on Pope Leo XIV's encyclical on AI. https://simonwillison.net/2026/May/25/encyclical-on-ai/

Plugins can also affect the empty state of the new menu - the ...

2026-05-25T00:23:15Z

In reply to nevent1q…vd94
_________________________

Plugins can also affect the empty state of the new menu - the latest datasette-agent adds a form for kicking off a new agent conversation - live demo (if you sign in with GitHub) on https://agent.datasette.io/

Fun new feature in Datasette 1.0a30 - a "jump to" menu, ...

2026-05-25T00:21:28Z

Fun new feature in Datasette 1.0a30 - a "jump to" menu, also available by the "/" keyboard shortcut, which lets you type to jump to a database, table or canned query. It offers a hook so plugins can extend it with additional content too https://datasette.io/blog/2026/jump-menu/

I released the first alpha of Datasette Agent - a conversational ...

2026-05-21T20:11:42Z

I released the first alpha of Datasette Agent - a conversational AI assistant for Datasette that can answer questions about data in SQLite databases, and can be extended with plugins to add extra tools and features

You can watch a demo video or try it out yourself on https://agent.datasette.io/

Read more on my blog https://simonwillison.net/2026/May/21/datasette-agent/ or in the Datasette project blog announcement https://datasette.io/blog/2026/datasette-agent/

I don't have much to say about this year's Google I/O ...

2026-05-20T15:39:50Z

I don't have much to say about this year's Google I/O because I prefer to write about products that have shipped, not just "coming soon" announcements - but here are some notes on Gemini Spark and Antigravity https://simonwillison.net/2026/May/20/google-io/

My notes on Gemini 3.5 Flash - 3x the price of Gemini 3 Flash but ...

2026-05-19T22:41:07Z

My notes on Gemini 3.5 Flash - 3x the price of Gemini 3 Flash but Google are planning to use it for many of their own products https://simonwillison.net/2026/May/19/gemini-35-flash/

Wrote about today's GitLab restructuring / "workforce ...

2026-05-12T00:17:33Z

Wrote about today's GitLab restructuring / "workforce reduction" announcement, and ended up digging around in version control for both the GitLab and the 37signals public employee handbooks to help illustrate my thoughts https://simonwillison.net/2026/May/11/gitlab-act-2/

New TIL: I figured out how to use my LLM CLI tool in a shebang ...

2026-05-11T19:06:30Z

New TIL: I figured out how to use my LLM CLI tool in a shebang line, which means you can write executable scripts in English, or hook up more complex scripts with a snippet of YAML template - https://til.simonwillison.net/llms/llm-shebang

Oh, and Elon said "We reserve the right to reclaim the ...

2026-05-07T17:21:36Z

In reply to nevent1q…qvd5
_________________________

Oh, and Elon said "We reserve the right to reclaim the compute if their AI engages in actions that harm humanity."

Under-reported details of the xAI/Anthropic Colossus data center ...

2026-05-07T17:13:43Z

Under-reported details of the xAI/Anthropic Colossus data center deal: Anthropic get Colossus 1 but xAI keep using the larger Colossus 2, Colossus 1 has a REALLY bad environmental record, and xAI just shut down a bunch of older models on 2 weeks' notice https://simonwillison.net/2026/May/7/xai-anthropic/

I added a new feature to my blog (built entirely on my phone with ...

2026-05-02T17:30:04Z

I added a new feature to my blog (built entirely on my phone with Claude code for web) that imports my iNaturalist photos and adds them to my site's overall timeline https://simonwillison.net/2026/May/2/sightings/

I particularly appreciate how this rationale isn't based on ...

2026-04-30T01:40:09Z

In reply to nevent1q…eksq
_________________________

I particularly appreciate how this rationale isn't based on the idea that LLM code is of poor quality compared to code written by hand - the quality of the code isn't the deciding factor at all here

The Zig project's rationale for their blanket ban on ...

2026-04-30T01:26:54Z

The Zig project's rationale for their blanket ban on AI-assisted contributions makes a lot of sense to me - for them, time spent reviewing PRs isn't about the code, it's about growing new contributors for the future of the project https://simonwillison.net/2026/Apr/30/zig-anti-ai/

I released LLM 0.32a0 this morning, a major backwards-compatible ...

2026-04-29T19:13:47Z

I released LLM 0.32a0 this morning, a major backwards-compatible refactor of my LLM Python library and CLI tool for working with language models - the new changes should help LLM work better with reasoning models and other new frontier capabilities https://simonwillison.net/2026/Apr/29/llm/

It didn't quite manage to draw me a pelican riding a bicycle, ...

2026-04-28T03:22:27Z

In reply to nevent1q…08d8
_________________________

It didn't quite manage to draw me a pelican riding a bicycle, but I still appreciated its era-appropriate response

Some notes on talkie, a new "vintage language model" from ...

2026-04-28T02:49:41Z

Some notes on talkie, a new "vintage language model" from a team including Alec Radford (yes, that Alec Radford) "trained on 260B tokens of historical pre-1931 English text" https://simonwillison.net/2026/Apr/28/talkie/

Here's a uv one-liner that downloads and runs the MLX model ...

2026-04-27T23:53:15Z

In reply to nevent1q…r602
_________________________

Here's a uv one-liner that downloads and runs the MLX model against a local mp3 file

uv run --with mlx-audio python -m mlx_audio.stt.generate \
--model mlx-community/VibeVoice-ASR-4bit \
--audio lenny.mp3 --output-path lenny \
--format json --verbose --max-tokens 32768

Microsoft's MIT licensed VibeVoice speech-to-text model ...

2026-04-27T23:48:17Z

Microsoft's MIT licensed VibeVoice speech-to-text model (think Whisper with speaker diarization) is really good - my notes on running the 5.71GB 4bit MLX conversion on an M5 MacBook, using about 60GB of RAM at peak and transcribing 1hr of audio in ~9 mins https://simonwillison.net/2026/Apr/27/vibevoice/

Couldn't resist capping that off with my all-time favorite ...

2026-04-27T19:01:14Z

In reply to nevent1q…hdwv
_________________________

Couldn't resist capping that off with my all-time favorite quote from Matt Levine

Today OpenAI announced that "Revenue share payments from ...

2026-04-27T18:39:46Z

Today OpenAI announced that "Revenue share payments from OpenAI to Microsoft continue through 2030, independent of OpenAI’s technology progress"

That "independent of OpenAI’s technology progress" fragment appears to mean that the weird AGI clause is now deceased https://simonwillison.net/2026/Apr/27/now-deceased-agi-clause/

DeepSeek V4 just dropped - two models, Flash and Pro, both ...

2026-04-24T06:07:00Z

DeepSeek V4 just dropped - two models, Flash and Pro, both benchmarking well, decent pelicans and prices that put them both as the cheapest in their respective categories by a solid margin https://simonwillison.net/2026/Apr/24/deepseek-v4/

This week's edition of my email newsletter features 4 ...

2026-04-24T04:06:42Z

This week's edition of my email newsletter features 4 pelicans riding bicycles, 1 possum on an e-scooter, up to 5 raccoons with ham radios hiding in crowds, 5 blog posts, 8 links, 3 quotes and a new chapter of my Agentic Engineering Patterns guide https://simonw.substack.com/p/gpt-55-chatgpt-images-20-qwen36-27b

I vibe coded a web UI to LiteParse by LlamaIndex, a neat open ...

2026-04-23T22:10:24Z

I vibe coded a web UI to LiteParse by LlamaIndex, a neat open source library for extracting text from annoying layouts PDFs https://simonw.github.io/liteparse/

More about how I built it on my blog: https://simonwillison.net/2026/Apr/23/liteparse-for-the-web/

GPT-5.5 is out but not yet in the OpenAI API - but in the ongoing ...

2026-04-23T20:06:16Z

GPT-5.5 is out but not yet in the OpenAI API - but in the ongoing battle with Anthropic over OpenClaw OpenAI made their Codex tool's private backend API a semi-approved mechanism... and that one has GPT-5.5...

So I used it to draw some pelicans https://simonwillison.net/2026/Apr/23/gpt-5-5/

The new Qwen3.6-27B just gave me definitely the best pelican ...

2026-04-22T16:50:33Z

The new Qwen3.6-27B just gave me definitely the best pelican riding a bicycle I've had from a 16.8GB model file! https://simonwillison.net/2026/Apr/22/qwen36-27b/

Wrote up Anthropic's self-own about Claude Code pricing from ...

2026-04-22T02:15:53Z

Wrote up Anthropic's self-own about Claude Code pricing from this afternoon on my blog - it turned out they'd reversed course just as I hit publish, so I've tried to update it to reflect the current state
https://simonwillison.net/2026/Apr/22/claude-code-confusion/

I came up with a somewhat foolish new benchmark for testing image ...

2026-04-21T20:36:20Z

I came up with a somewhat foolish new benchmark for testing image generation models, to exercise the new ChatGPT Images 2.0:

"Do a where's Waldo style image but it's where is the raccoon holding a ham radio"

https://simonwillison.net/2026/Apr/21/gpt-image-2/

Important to note: that 3x increase for images is entirely due to ...

2026-04-20T03:19:17Z

In reply to nevent1q…jjgz
_________________________

Important to note: that 3x increase for images is entirely due to Opus 4.7 being able to handle higher resolutions. I tried that again with a 682x318 pixel image and it took 314 tokens with Opus 4.7 and 310 with Opus 4.6, so effectively the same cost.

New TIL on fetching data from a Datasette instance into Google ...

2026-04-20T02:53:52Z

New TIL on fetching data from a Datasette instance into Google Sheets using importdata(), named custom functions or Google Apps Script https://til.simonwillison.net/google-sheets/datasette-sql

I upgraded my Claude token counter tool to compare different ...

2026-04-20T00:55:12Z

I upgraded my Claude token counter tool to compare different models and Opus 4.7 does appear to use 1.46x times the tokens for text and up to 3x the tokens for images - it's priced the same as Opus 4.6 on a per-token basis so this is actually a pretty big price bump https://simonwillison.net/2026/Apr/20/claude-token-counts/

Since Anthropic publish their system prompts we can generate a ...

2026-04-19T00:05:52Z

Since Anthropic publish their system prompts we can generate a diff between Claude Opus 4.6 and 4.7 - here are my notes on what's changed https://simonwillison.net/2026/Apr/18/opus-system-prompt/

The event is next month - talks are Friday 15th to Sunday 17th of ...

2026-04-18T00:08:31Z

In reply to nevent1q…n3me
_________________________

The event is next month - talks are Friday 15th to Sunday 17th of May, with the date before that of tutorials and two days afterwards of sprints

Californians are notoriously last-minute planners so I know that's enough time to decide to come join us!

Join us at PyCon US 2026 in Long Beach—we have new AI and ...

2026-04-18T00:03:10Z

Join us at PyCon US 2026 in Long Beach—we have new AI and security tracks this year https://simonwillison.net/2026/Apr/17/pycon-us-2026/

Pelicans for Meta's new Muse Spark models - plus I did a bit ...

2026-04-08T23:12:50Z

Pelicans for Meta's new Muse Spark models - plus I did a bit of a deep dive into the Code Interpreter and fascinating "container.visual_grounding" tools in their meta.ai chat UI https://simonwillison.net/2026/Apr/8/muse-spark/

Wrote up some thoughts on Anthropic's Project Glassing, where ...

2026-04-07T21:29:44Z

Wrote up some thoughts on Anthropic's Project Glassing, where their latest Opus-beating model is available to partnered security research organizations only. Given the recent alarm bells raised by credible security voices I think this is a justified decision.
https://simonwillison.net/2026/Apr/7/project-glasswing/

I'm a big fan of the pelican GLM-5.1 drew me today, it even ...

2026-04-07T21:27:42Z

I'm a big fan of the pelican GLM-5.1 drew me today, it even animated it! https://simonwillison.net/2026/Apr/7/glm-51/

I built this one using README-driven-development: I hand crafted ...

2026-04-05T04:20:13Z

In reply to nevent1q…hsy2
_________________________

I built this one using README-driven-development: I hand crafted a detailed README describing exactly how the tool should work... then dumped that into Claude Code and told it to build it https://gisthost.github.io/?d4b1a398bf3b6b14aade923dea69a1ac/index.html

I built a new Python CLI tool for scanning folders for secret ...

2026-04-05T04:18:47Z

I built a new Python CLI tool for scanning folders for secret strings, useful if you want to share a bunch of log files but first want to check they didn't accidentally leak API keys or similar. Run this command to learn more:

uvx scan-for-secrets --help

Blog: https://simonwillison.net/2026/Apr/5/scan-for-secrets-3/

Started a new tag on my blog to track stories about AI-powered ...

2026-04-04T00:00:34Z

Started a new tag on my blog to track stories about AI-powered security research, which is very much having a moment right now - 11 posts so far already https://simonwillison.net/tags/ai-security-research/

Warning to open source maintainers: the Axios supply chain attack ...

2026-04-03T14:55:37Z

Warning to open source maintainers: the Axios supply chain attack started with some
very sophisticated social engineering targeted at one of their developers https://simonwillison.net/2026/Apr/3/supply-chain-social-engineering/

I was a guest on @lennysan's podcast! We talked about agentic ...

2026-04-02T20:43:04Z

I was a guest on @lennysan's podcast! We talked about agentic engineering and all sorts of other LLM-related topics for 1h39m(!), plus a little bit about kākāpō parrots - here's my selection of highlights from our conversation https://simonwillison.net/2026/Apr/2/lennys-podcast/

Pelicans for Gemma 4 E2B, E4B, 26B-A4B and 31B - the first three ...

2026-04-02T18:43:56Z

Pelicans for Gemma 4 E2B, E4B, 26B-A4B and 31B - the first three generated on my laptop via LM Studio, the 31B was broken on my laptop so I ran it via the Gemini API instead https://simonwillison.net/2026/Apr/2/gemma-4/

If you have uv installed you can start a conversation (after a ...

2026-03-30T14:45:58Z

In reply to nevent1q…gtkx
_________________________

If you have uv installed you can start a conversation (after a 2GB model download) directly like this:

uvx --with llm-mrchatterbox llm chat -m mrchatterbox

Mr. Chatterbox is a new 2GB nanochat model trained from scratch ...

2026-03-30T14:33:43Z

Mr. Chatterbox is a new 2GB nanochat model trained from scratch by Trip Venturella on "28,000 Victorian-era British texts published between 1837 and 1899" - I released an llm-mrchatterbox plugin which can run it locally on my Mac https://simonwillison.net/2026/Mar/30/mr-chatterbox/

I've been vibe coding SwiftUI menu bar apps for my new Mac, ...

2026-03-27T21:01:52Z

I've been vibe coding SwiftUI menu bar apps for my new Mac, turns out Claude Opus 4.6 and GPT-5.4 are both competent at Swift programming, no need to even open Xcode! https://simonwillison.net/2026/Mar/27/vibe-coding-swiftui/

Starlette 1.0 is out! I used this as an opportunity to experiment ...

2026-03-23T00:13:05Z

Starlette 1.0 is out! I used this as an opportunity to experiment with Claude Skills, since Claude isn't yet familiar with the (minor) breaking changes in the 1.0 release compared to 0.x https://simonwillison.net/2026/Mar/22/starlette/

Still a work in progress, but I've published the first draft ...

2026-03-21T22:22:28Z

Still a work in progress, but I've published the first draft of a new chapter on "Using Git with coding agents" https://simonwillison.net/guides/agentic-engineering-patterns/using-git-with-coding-agents/

Thoughts on OpenAI acquiring Astral and uv/ruff/ty ...

2026-03-19T16:45:44Z

Thoughts on OpenAI acquiring Astral and uv/ruff/ty https://simonwillison.net/2026/Mar/19/openai-acquiring-astral/

New on Niche Museums: the John M. Mossman Lock Collection, ...

2026-03-15T23:43:34Z

New on Niche Museums: the John M. Mossman Lock Collection, available to view by appointment only at The General Society of Mechanics and Tradesmen of the City of New York https://www.niche-museums.com/118

Got excited about a brand new PostgreSQL 18 feature (for ...

2026-03-09T15:34:37Z

Got excited about a brand new PostgreSQL 18 feature (for simulating production query plan statistics locally), posted about it on the SQLite forum... and got a reply from D. Richard Hipp within minutes that SQLite has had the same ability for years https://simonwillison.net/2026/Mar/9/production-query-plans-without-production-data/

A short note that the predictions that LLMs would favor ...

2026-03-09T13:40:39Z

A short note that the predictions that LLMs would favor "boring technology" that's over-represented in the training data don't appear to be playing out as expected with the latest models - once you attach them to a good coding agent harness at least https://simonwillison.net/2026/Mar/9/not-so-boring/

The chardet open source library relicensed from LGPL to MIT two ...

2026-03-05T16:53:11Z

The chardet open source library relicensed from LGPL to MIT two days ago thanks to a Claude Code assisted "clean room" rewrite - but original author Mark Pilgrim is disputing that the way this was done justifies the change in license - my notes here: https://simonwillison.net/2026/Mar/5/chardet/

I went to the New York Earth Room! It's 280,000 pounds of ...

2026-03-04T23:00:50Z

I went to the New York Earth Room! It's 280,000 pounds of soil in a loft in SoHo that's been there mostly unchanged since 1977 https://www.niche-museums.com/117

I started a new chapter of my Agentic Engineering Patternw guide ...

2026-03-04T18:20:01Z

I started a new chapter of my Agentic Engineering Patternw guide about anti-patterns - things NOT to do

So far I only have one: Inflicting unreviewed code on collaborators, aka dumping a thousand line PR without even making sure it works first https://simonwillison.net/guides/agentic-engineering-patterns/anti-patterns/#inflicting-unreviewed-code-on-collaborators

Published some notes on the situation at Qwen - they released the ...

2026-03-04T15:53:36Z

Published some notes on the situation at Qwen - they released the Qwen 3.5 family (an outstanding family of open weight models) but now their lead researcher and several others all appear to have resigned within the past 24 hours https://simonwillison.net/2026/Mar/4/qwen/

I started a new section of my Agentic Engineering guide for ...

2026-03-02T17:20:26Z

I started a new section of my Agentic Engineering guide for annotated versions of prompts I've used for projects - the first is a prompt I used to have Claude Code for web build me a web UI for compressing GIFs using a WebAssembly build of Gifsicle https://simonwillison.net/guides/agentic-engineering-patterns/gif-optimization/

Sent the February edition of my sponsors-only newsletter - a ...

2026-03-02T14:58:42Z

Sent the February edition of my sponsors-only newsletter - a summary of my last month of blogging for people who want to pay for a shorter version

I use Claude as a proofreader and fact checker, was delighted that it called me out on this Kākāpō detail: https://simonwillison.net/2026/Mar/2/february-newsletter/

New chapter of my Agentic Engineering Patterns guide. This one is ...

2026-02-28T23:14:28Z

New chapter of my Agentic Engineering Patterns guide. This one is about having coding agents build custom interactive and animated explanations to help fight back against cognitive debt https://simonwillison.net/guides/agentic-engineering-patterns/interactive-explanations/

Built a fun prototype this morning of binary search using HTTP ...

2026-02-27T18:02:38Z

Built a fun prototype this morning of binary search using HTTP range requests, in this case to lookup characters in ~77MB of unicode data https://simonwillison.net/2026/Feb/27/unicode-explorer/

Today's chapter of Agentic Engineering Patterns is some good ...

2026-02-26T21:14:40Z

Today's chapter of Agentic Engineering Patterns is some good general career advice which happens to also help when working with coding agents: Hoard things you know how to do https://simonwillison.net/guides/agentic-engineering-patterns/hoard-things-you-know-how-to-do/

Brief notes on Claude Code Remote and Cowork scheduled tasks - ...

2026-02-25T18:37:25Z

Brief notes on Claude Code Remote and Cowork scheduled tasks - both of which overlap with OpenClaw, and both of which require you to leave your computer powered on somewhere https://simonwillison.net/2026/Feb/25/claude-code-remote-control/

I've been having good results recently asking coding agents ...

2026-02-25T16:57:30Z

In reply to nevent1q…c5dx
_________________________

I've been having good results recently asking coding agents to provide "a linear walkthrough of the code that explains how it all works in detail" - I demonstrated that against this vibe coded Swift codebase and wrote up the technique here: https://simonwillison.net/guides/agentic-engineering-patterns/linear-walkthroughs/

Wrote up a fun vibe-coding project, I had Claude Code build me a ...

2026-02-25T16:52:10Z

Wrote up a fun vibe-coding project, I had Claude Code build me a SwiftUI macOS app for presenting a talk by turning a list of URLs into a full-screen slide experience I could remote control from my phone https://simonwillison.net/2026/Feb/25/present/

"Red/green TDD" talks about how you can get much better ...

2026-02-23T17:54:51Z

In reply to nevent1q…xffq
_________________________

"Red/green TDD" talks about how you can get much better results from most coding agents by encouraging them to use test-first development where they watch the tests fail before building an implementation that lets them pass https://simonwillison.net/guides/agentic-engineering-patterns/red-green-tdd/

"Writing code is cheap now" talks about the central ...

2026-02-23T17:53:42Z

In reply to nevent1q…xhkn
_________________________

"Writing code is cheap now" talks about the central challenge of agentic engineering: the cost to churn out working code has dropped to almost nothing, how does that impact our existing intuitions about how we work, both individually and as a team? https://simonwillison.net/guides/agentic-engineering-patterns/code-is-cheap/

I've published the first two chapters of a new guide to ...

2026-02-23T17:45:43Z

I've published the first two chapters of a new guide to Agentic Engineering Patterns - coding practices and patterns to help get the best results out of coding agents like Claude Code and OpenAI Codex https://simonwillison.net/2026/Feb/23/agentic-engineering-patterns/