Flux
Couleur d'accent
Toutes les sources

Simon Willison's Weblog

677 articles Flux RSS
IA Programmation
ChatGPT voice mode is a weaker model
IA Programmation

ChatGPT voice mode is a weaker model

I think it's non-obvious to many people that the OpenAI voice mode runs on a much older, much weaker model - it feels like the AI that you can talk to should be the smartest AI but it really isn't. If you ask ChatGPT voice mode for its knowledge cutoff date it tells you April 2024 - it's a GPT-4o era model. This thought inspired by this Andrej Karpathy tweet about the growing gap in understanding of AI capability based on the access points and domains people are using the models with: [...] It…

Simon Willison's Weblog
asgi-gzip 0.3
IA Programmation

asgi-gzip 0.3

Release: asgi-gzip 0.3 I ran into trouble deploying a new feature using SSE to a production Datasette instance, and it turned out that instance was using datasette-gzip which uses asgi-gzip which was incorrectly compressing event/text-stream responses. asgi-gzip was extracted from Starlette, and has a GitHub Actions scheduled workflow to check Starlette for updates that need to be ported to the library... but that action had stopped running and hence had missed Starlette's own fix for this…

Simon Willison's Weblog
Meta's new model is Muse Spark, and meta.ai chat has some interesting tools
IA Programmation

Meta's new model is Muse Spark, and meta.ai chat has some interesting tools

Meta announced Muse Spark today, their first model release since Llama 4 almost exactly a year ago. It's hosted, not open weights, and the API is currently "a private API preview to select users", but you can try it out today on meta.ai (Facebook or Instagram login required). Meta's self-reported benchmarks show it competitive with Opus 4.6, Gemini 3.1 Pro, and GPT 5.4 on selected benchmarks, though notably behind on Terminal-Bench 2.0. Meta themselves say they "continue to invest in areas with…

Simon Willison's Weblog
GLM-5.1: Towards Long-Horizon Tasks
IA Programmation

GLM-5.1: Towards Long-Horizon Tasks

GLM-5.1: Towards Long-Horizon Tasks Chinese AI lab Z.ai's latest model is a giant 754B parameter 1.51TB (on Hugging Face) MIT-licensed monster - the same size as their previous GLM-5 release, and sharing the same paper. It's available via OpenRouter so I asked it to draw me a pelican: llm install llm-openrouter llm -m openrouter/z-ai/glm-5.1 'Generate an SVG of a pelican on a bicycle' And something new happened... unprompted, the model decided to give me an HTML page that included both the SVG…

Simon Willison's Weblog
Anthropic's Project Glasswing - restricting Claude Mythos to security researchers - sounds necessary to me
IA Programmation

Anthropic's Project Glasswing - restricting Claude Mythos to security researchers - sounds necessary to me

Anthropic didn't release their latest model, Claude Mythos (system card PDF), today. They have instead made it available to a very restricted set of preview partners under their newly announced Project Glasswing. The model is a general purpose model, similar to Claude Opus 4.6, but Anthropic claim that its cyber-security research abilities are strong enough that they need to give the software industry as a whole time to prepare. Mythos Preview has already found thousands of high-severity…

Simon Willison's Weblog
SQLite WAL Mode Across Docker Containers Sharing a Volume
IA Programmation

SQLite WAL Mode Across Docker Containers Sharing a Volume

Research: SQLite WAL Mode Across Docker Containers Sharing a Volume Inspired by this conversation on Hacker News about whether two SQLite processes in separate Docker containers that share the same volume might run into problems due to WAL shared memory. The answer is that everything works fine - Docker containers on the same host and filesystem share the same shared memory in a way that allows WAL to collaborate as it should. Tags: docker, sqlite

Simon Willison's Weblog
Google AI Edge Gallery
IA Programmation

Google AI Edge Gallery

Google AI Edge Gallery Terrible name, really great app: this is Google's official app for running their Gemma 4 models (the E2B and E4B sizes, plus some members of the Gemma 3 family) directly on your iPhone. It works really well. The E2B model is a 2.54GB download and is both fast and genuinely useful. The app also provides "ask questions about images" and audio transcription (up to 30s) with the two small Gemma 4 models, and has an interesting "skills" demo which demonstrates tool calling…

Simon Willison's Weblog
datasette-ports 0.1
IA Programmation

datasette-ports 0.1

Release: datasette-ports 0.1 Another example of README-driven development, this time solving a problem that might be unique to me. I often find myself running a bunch of different Datasette instances with different databases and different in-development plugins, spreads across dozens of different terminal windows - enough that I frequently lose them! Now I can run this: datasette install datasette-ports datasette ports And get a list of every running instance that looks something like this:…

Simon Willison's Weblog
Eight years of wanting, three months of building with AI
IA Programmation

Eight years of wanting, three months of building with AI

Eight years of wanting, three months of building with AI Lalit Maganti provides one of my favorite pieces of long-form writing on agentic engineering I've seen in ages. They spent eight years thinking about and then three months building syntaqlite, which they describe as "high-fidelity devtools that SQLite deserves". The goal was to provide fast, robust and comprehensive linting and verifying tools for SQLite, suitable for use in language servers and other development tools - a parser,…

Simon Willison's Weblog
Esc