Simon Willison

Mojo🔥 is now open source — Mojo🔥 is now open source Mojo🔥 is now open source The Mojo programming language has been promising an open source release since May 2023 . Last week they shipped their 1.0 and today they have followed through on that original promise, releasing the compiler and toolchain under an Apache 2 license. When Mojo first launched the stated goal was to produce a superset of Python, so existing Python code could be used to bootstrap their own ecosystem. That plan changed around August 2025 : Mojo may or may not evolve into a full superset of Python, and it’s okay if it doesn’t. We’re encouraged by how well AI-assisted coding tools already help migrate Python to Mojo today, and we’re confident that future tooling and ecosystem maturity will make this evolution even smoother. Today Mojo is its own language, optimized to make GPU programming as painless as possible using syntax inspired by Python, if not 100% compatible with existing code. Via Lobste.rs Tags: open-source , python , mojo

The Mojo programming language has officially open-sourced its compiler and toolchain under an Apache 2 license.

Qwen 3.8 27B scores 52 on the Artificial Analysis Intelligence Index — Qwen 3.8 27B scores 52 on the Artificial Analysis Intelligence Index That's the same score as GPT-5.6 Luna (max), and just one point behind GLM-5.2 (max) and DeepSeek V4 Pro 0813 (max) - that GLM is 753B and that DeepSeek is 1.6B parameters, and Luna is size unknown but presumably a whole lot bigger than 27B. Qwen 3.8 27B is a truly astonishing model . Via Hacker News Tags: ai , generative-ai , llms , qwen , ai-in-china , artificial-analysis

Simon Willison highlights Qwen 3.8 27B scoring 52 on the Artificial Analysis Intelligence Index, matching much larger models.

We Tracked a Shipment of Rare Books. It Ended at an Amazon AI Training Facility — We Tracked a Shipment of Rare Books. It Ended at an Amazon AI Training Facility Excellent piece of reporting from 404 Media. For a while now there have been stories of book dealers receiving orders for large volumes of books from apparently price-insensitive anonymous customers, widely suspected to be companies looking to scan them for AI training (see my previous coverage of Anthropic's book scanning from June 2025.) 404 Media investigated with an AirTag! In July, one bookseller told me they received a very large order of around 1,000 books on Biblio, one of these marketplaces. The seller agreed to put an Apple AirTag provided by 404 Media in one of the books included in this order so we could see where the book was going. And by extension, which company, AI or otherwise, was behind this massive order. The book ended up delivered to the VGT3 corner of the LAS8 Amazon facility in the north east of Las Vegas, where the entrance carried this on-the-nose logo of a dinosaur with a book! Photo credit: 404 Media Online forum discussions between Amazon workers confirmed that VGT3 destructively scans large volumes of books. Tags: amazon , journalism , ai , training-data , ai-ethics , 404-media

Simon Willison shares a 404 Media report tracking a book shipment to an Amazon facility scanning books for AI training.

Markdown SVG upgrades — I started building my markdown-svg-renderer tool in May , but I've since added enough features to it that it's worth talking about here again. It's evolved into my ideal tool for sharing Markdown transcripts that include SVG documents. Given my proclivity for drawing pelicans riding bicycles this is a problem that I needed to solve! The tool is very simple. Navigate to markdown-svg-renderer in your browser and paste in some Markdown to see it rendered... or save that Markdown to a CORS-friendly URL or a GitHub Gist and paste in a URL to that document. The URL option will give you a bookmarkable page, for example https://tools.simonwillison.net/markdown-svg-renderer#url=https%3A%2F%2Fgist.github.com%2Fsimonw%2F6f9e48293be5c916652d29f0dc0b0657 - which bakes in the URL to this Gist . If you visit the Gist you'll see raw SVG: In the rendered tool that looks like this instead: As you can see, that SVG block in the Markdown has been transformed into a rendered SVG (in this case animated) plus several tabs. The tabs are the really fun bit. The PNG and JPEG tabs render that SVG to those image formats in the browser and lets you copy or download them - useful for sharing on platforms that don't support SVG directly. The MP4 tab is new today - it examines the SVG to see if it contains any animations, attempts to guess how long the looped video should be, then renders a whole bunch of frames of the animation and loads 30+MB of ffmpeg.wasm so it can compile those frames into an MP4 video using the full power of FFMPEG compiled to WebAssembly and running in the browser. Being able to turn an animated SVG into a MP4 again makes it easy to share on platforms that can't support SVG animation natively. It's a neat trick! Tags: svg , markdown , tools

Qwen 3.8 27B is excellent, but it defaults to wildly overthinking things — Friday's big release was Qwen 3.8 27B , an Apache 2 licensed 27B parameter vision-capable LLM from Alibaba's Qwen research lab. I've been looking forward to this one: 27B is an excellent size for running a model on a reasonably specced laptop, and its predecessor Qwen 3.6 27B was impressive. Qwen's self-reported benchmarks for this model are eye-opening. They show a boost from both Qwen 3.6 27B and the closed-weight Qwen 3.7-Plus, which was one of Qwen's strongest models of any size as recently as May this year . It will be interesting to hear what independent benchmarks have to say about the model. I've been running the model on two different machines: my 128GB M5 Max MacBook Pro, and an NVIDIA DGX Spark . On both machines I'm running LM Studio and their 17GB Q4_K_M quantized build . I also tried using llama-server directly on the Spark. The default of extra high results in spectacular over-thinking Qwen's documentation describes the model as defaulting to xhigh for the reasoning effort, and the LM Studio GGUF I've been trying preserves that default: Qwen3.8 comes with official support for reasoning_effort , which can be used to adjust reasoning depth and control cost: • xhigh (default): for complex tasks demanding thorough analysis • medium : balancing accuracy and speed • low : efficient reasoning optimizing for speed and cost This is a hilarious default. It's absolutely not a good way to run the model, especially on consumer hardware. I've been finding the results extremely entertaining. I quickly ran into problems with LM Studio's default context limit of 8,192 tokens - Qwen was using them all up thinking about even the most mundane of problems. I loaded the model with the full 262,144 maximum context length and that problem went away. Here's the pelican riding a bicycle SVG I got from my first attempt with that increased context length. It took 21 minutes to generate, using 22,276 reasoning tokens to produce 3,223 tokens of output. You can read the reasoning trace here . This is by far the best pelican SVG I've been able to generate with a model that runs on a local machine - and this Qwen is pretty small, just a 17GB file on disk. There's a lot to like about this: • The bicycle frame is the right shape • It has legs on each side of the bike - that's very rare • Good, clear pelican pouch • The wings extend to touch the handlebars! • The motion lines are behind, not in front • It has a tasteful background - nice sun, clouds, hill, flowers and grass. Was that worth waiting 21 minutes for? Absolutely not. Here's that same prompt run wi

Quoting Dario Amodei — I do agree that the public has a negative view of AI (and that this is a big problem), but I don’t think it is primarily caused by me or any other AI leader warning about AI’s risks. I think it is fundamentally a crisis of trust. I think that ordinary people don’t trust companies, governments, or the tech industry and always suspect that we are cooking up some new way to screw them over. The causes of this go back decades and AI is just the latest iteration of it. I don’t think that a glitzy marketing campaign with a positive spin (which some have advocated that Anthropic do) is the way to win back that trust — at this point, saying that AI will cure cancer is more a cliche than it is inspiring, and most people think it is deceptive. The thing that will work is actually curing cancer . I think by far the most accurate criticism of AI companies including Anthropic is that we haven’t yet delivered on our big promises to benefit the world. That is totally on us, and I think it’s the criticism you should be making, instead of all this stuff about messaging and marketing. — Dario Amodei Tags: anthropic , ai , ai-backlash

CORS Chat — Tool: CORS Chat I built this today ( with GPT-5.6-Sol xhigh ) to help test Qwen 3.8 27B running in LM Studio on both my M5 MacBook Pro and an NVIDIA DGX Spark. It provides a web UI for exercising an OpenAI-Responses-compatible chat endpoint. I've tried it against LM Studio with the --cors option and OpenRouter, and both work fine. Conversations are persisted in the browser and can be exported as copy-pasted JSON. One fun detail is that it notices SVG images that are being generated and progressively renders them in the chat while the tokens are still streaming in. Tags: svg , ai , generative-ai , llms , cors , openrouter , lm-studio

Northern Gannet — Northern Gannet, in Pillar Point Harbor, CA, US This is Morris. Morris is a local celebrity: the only known Northern Gannet ( Morus bassanus ) in the entire Pacific Ocean. They showed up in the Farallon Islands off the coast of San Francisco 14 years ago . They have since made Pillar Point harbor their home, where they are quite easy to spot: the only white bird with a yellow head, usually hanging out with the smaller black Brandt’s cormorants near the harbor sign visible from the end of the commercial pier. Tags: photography , wildlife , half-moon-bay

Don't classify. Hallucinate! — Don't classify. Hallucinate! I still have quite a bit of older content on my blog that I never got round to tagging. My blog has 1,856 tags - likely too many to feed to an LLM in one go and say "which of these tags match the following content". Doug Turnbull has a neat solution. Tell the model to output tags without any details of the existing vocabulary, then use vector embeddings against the existing corpus to find the concrete tags that are closest to the ones the model imagined might fit! His example prompt suggests including an example of the shape of your tags to help the model make a more useful guess: Your task is to create novel, never seen before, furniture, home goods, or hardware classification that best fit a search query. Product classifications might look like: Furniture / Living Room Furniture / Coffee Tables & End Tables / Coffee Tables Décor & Pillows / Decorative Pillows & Blankets / Throw Pillows Furniture / Bedroom Furniture / Dressers & Chests Kitchen & Tabletop / Kitchen Organization / Food Storage & Canisters School Furniture and Supplies / School Furniture / School Chairs & Seating / Stackable Chairs Baby & Kids / Toddler & Kids Bedroom Furniture / Kids Beds Here's the query to generate classifications for: brown coffee table Tags: search , ai , generative-ai , llms , embeddings , doug-turnbull

sqlite-utils 4.2.1 — Release: sqlite-utils 4.2.1 Fixes a crashing bug in sqlite-utils 4.2 . I'd introduced code that looks like this: from typing_extensions import Self It turned out the typing-extensions package was not listed as a dependency for sqlite-utils - it was installed by one of the other dependencies in the dev dependency group , but when you uvx sqlite-utils directly you don't get those dependencies. As part of fixing this I figured out how to run a smoke test to ensure the CLI tool still works even without those dev dependencies, which can be run from the project checkout: uv run --isolated --no-default-groups sqlite-utils --help The --no-default-groups argument prevents it from installing that default dev group, and --isolated means that even if there is a .venv/ folder containing extra dependencies they will be ignored for the duration of that uv run command. Tags: packaging , python , sqlite-utils , uv

sqlite-utils 4.2 — Release: sqlite-utils 4.2 Lots of improvements in this one relating to the table.transform() feature , which adds support for complex alter table operations by creating a fresh table, copying across the data and then dropping and replacing the old one. transform() now preserves a much larger array of edge-case schema definitions, including check constraints, unique constraints and even comments describing the columns. There are also new introspection properties for check constraints, and a whole lot of other smaller changes. Includes contributions from Bunlong Heng , ethanhawkes-gif , Rami Abdelrazzaq , nyxst4ck , and ikatyal2110 . (It later turned out 4.2 had a crashing bug , fixed in 4.2.1 .) Tags: releases , sqlite , sqlite-utils

llm-gemini 0.33 — Release: llm-gemini 0.33 It's been a while since the last llm-gemini release. This version of the plugin adds support for today's Gemini 3.7 Flash release, plus gemini-3.6-flash , gemini-3.5-flash-lite and two embedding models gemini-embedding-2 and gemini-embedding-001 . The plugin is also upgraded for compatibility with LLM 0.32, which means you can now see reasoning traces and you can also enable server-side tools using this pattern: llm -m gemini-3.7-flash -T CodeExecution \ 'use python to calculate (factorial of 13) * 3' I had Gemini 3.7 Flash draw me some pelicans riding bicycles at high, medium, and low thinking efforts (minimal, which was an option in 3.6 Flash, has been removed in 3.7.) Here's the high level one, which is pretty great: Update 14th August 2026 : I had originally said that the SVG rendered incorrectly in Chrome and Firefox, and blamed Gemini 3.7 Flash for producing invalid SVG. That was entirely incorrect: the rendering glitch was my fault, caused by a bug In my rendering tool . I've now fixed that bug. Tags: google , ai , generative-ai , llms , llm , gemini , pelican-riding-a-bicycle , llm-release