Simon Willison's Weblog

Release: llm-openai-decisions 0.1a0 OpenAI released their new Jev-style Decisions API, as previously announced at last week's DevDay.

Release: llm-mistral 0.16 Adds support for reasoning models, such as the newly released Mistral Large 4.

My comment on EmbeddingGemma 2 — Hacker News.

Introducing Mistral Large 4: Le chonk Mistral are back in the game.

TIL: Using Parseable with Datasette for OpenTelemetry traces I saw Parseable in a Show HN today - it's a new observability platform with both an open source (AGPL) Rust implementation (a single ~180MB binary), an "Enterprise" version with extra features a…

My comment on Mistral Large 4 — Hacker News. wren6991: The benchmark is saturated.

Release: datasette-atom 0.11a0 A minor fix for compatibility with the latest Datasette alphas.

Tool: Scrimshaw Jukebox I wanted to see if Claude Opus 5.5 could compose music, so I tried this: I want you to write some computer game music for me.

The "old" version of Cowork runs model inference in the cloud, executing tool calls in an Anthropic-provided VM we shipped to your computer.

Research: Qwen3.8 27B addition in words Colin Frasier posted on Bluesky about an experiment he ran over two years ago using GPT-4o to see how well it could "compute the sum but return the answer in words" across increasingly large numbers.

Here's a product feature which the world is going to need a whole lot more of over the coming months and years: default hard budget caps.

I just sent the September edition of my sponsors-only monthly newsletter.

Museum: Rex's Dino Store Located just before the turnstiles in the Grand Army Plaza subway station at the north end of Brooklyn's Prospect Park is this former newsstand which is now operated by a dinosaur.

Release: pwasm 0.2a0 pwasm is one of my folly projects - an entirely vibe-coded pure Python WebAssembly engine that I built in January during my first bout of AI mania.

[...]

I visited the Museum of the City of New York today and got to see He Built This City: Joe Macken’s Model, the 50 x27 feet model of the city built over a 21 year period from balsa wood and cardboard.

We evaluate several models on 100 tasks from the [internal Binary Exploitation benchmark] (selected at random), and find that GLM-5.3 develops full control flow hijacks in 4% of the trials; Claude Mythos Preview did so in 6%.

My comment on GPT 6.1 Sol: Near-Astra intelligence for a fifth of the price — Hacker News.

Tool: Photo Scrubber — local face blur & metadata removal I took a photograph of some protesters, then thought about how I don't like sharing photographs of strangers with identifiable faces.

I'm at OpenAI DevDay today, in Fort Mason, San Francisco.

Release: llm-anthropic 0.30 In addition to Claude Sonnet 5.5, this release adds the ability to run llm anthropic refresh to refresh the list of Anthropic models directly from their API - which means I don't need to push a new release just to add support f…

Claude Sonnet 5.5 New Sonnet model from Anthropic today.

To say that we were surprised at the jump and suddenness of the capabilities of our models when it came to “cyber” or “swarming” or “message boards” or anything else related to the incidents is an understatement.

Bad news on the MX Keys Mini pickup.

On Friday I gave the closing keynote at the WeAreDevelopers World Congress North America in San Jose.

My comment on S3 Is the Future, S3 Is the Past — Hacker News.

Tool: Bluesky reply bot checker Automated reply bots on Twitter are a scourge - as someone with a decent number of followers I attract a swarm of these, such that anything I post there attracts dozens of mindless automated replies.

Tool: Kākāpō Party I presented a closing keynote for the WeAreDevelopers World Congress North America yesterday.

Muse is getting a lot of attention — including mine — because it’s both groundbreaking technically (each user gets their own entire persistent Linux VM running in Meta’s cloud) and because it’s packaged in an easy-to-install easy-to-use way.

Northern Gannet, Great Blue Heron, California Brown Pelican, in Monterey Bay National Marine Sanctuary, CA, US, CA New 200-800mm Canon EF lens got me my best photo of Morris yet.

The more time I spend working with coding agents, the more convinced I am that they make software engineering even harder.

Release: commit-rewriter 0.2 Support for branches other than the default branch.

Release: datasette 1.0a41 Alec Garcia added support for OpenTelemetry to Datasette in this release.

My comment on We just shipped support for the ugliest part of HTTP: Vary — Hacker News.

Tool: Gemini 3.8 TTS Playground Google released two new Gemini text-to-speech models today - gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts.

Tool: Shadow roots, explained with live examples Prompt to Fable 5.1 Medium: Build an artifact to explain shadow roots in CSS with interactive examples Tags: css

SF October 14th: A Birds of a Feather Session on Agentic Engineering I'm hosting an evening event with Jesse Vincent in San Francisco on Wednesday 14th October for people who are building weird and interesting things with and on top of coding agents.

Yesterday was Grok 4.7 (pelicans) and MiMo v2.6 Flash/Pro (more pelicans).

Release: llm 0.36 New OpenAI models: gpt-6-sol for GPT-6 Sol and gpt-6-luna for GPT-6 Luna. #1702 Model plugins can now declare supports_conversation = False for models that only accept single-turn prompts.

Hey, you know it's like super obvious if you're using AI to write your scripts for TikTok and YouTube, right?

Release: llm-anthropic 0.29 Adds support for Claude Opus 5.5: llm -m claude-opus-5.5 "prompt goes here" Tags: llm, anthropic

Release: llm-typesafe 0.1a0 I built this new plugin for LLM to add support for TypeSafe AI's new Jev model.

Last week TypeSafe AI unveiled Jev, their first example of a new category of model that they are calling "System One models" (I'm with Maggie Appleton, I think "decision models" is a better name for these).

Cloudflare Python Workers are now generally available After a two year preview, Cloudflare's support for running Python code in their server-side Workers platform is now stable: "Python is now a first-class, fully supported language on the Cloudflare Deve…

It has been half a month since I started a new role at a big company.

My comment on MCP was always a bad idea?

Release: llm-keys-ui 0.1 This plugin solves a very specific problem.

Release: datasette-explain 0.2.2 Explain plans now work on read-only stored-query pages.

Release: datasette-auth-github 1.0 I run this GitHub login plugin on the agent.datasette.io demo site and I noticed that my authenticated sessions weren't lasting very long.

California Sea Lion, Brandt's Cormorant, in Pillar Point Harbor, CA, US I only noticed this after I had taken the photo: Morris the Northern Gannet is peeking out from behind the base of the sign.