asgi-gzip 0.3
Release: asgi-gzip 0.3 (https://github.com/simonw/asgi-gzip/releases/tag/0.3) I ran into trouble deploying a new feature using SSE
Simon Willison's Weblog
Meta's new model is Muse Spark, and meta.ai chat has some interesting tools
Meta announced Muse Spark (https://ai.meta.com/blog/introducing-muse-spark-msl/) today, their first model release since Llama 4 almost exactly a year ago
Quoting Giles Turnbull
I have a feeling that everyone likes using AI tools to try doing someone else’s profession. They’re much less keen when someone else uses it for their profession. — Giles Turnbull
GLM-5.1: Towards Long-Horizon Tasks
GLM-5.1: Towards Long-Horizon Tasks (https://z.ai/blog/glm-5.1) Chinese AI lab Z.ai's latest model is a giant 754B parameter 1.51TB (on Hugging Face (https://huggingface.co/zai-org/GLM-5.1))
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 (https://www-cdn.anthropic.com/53566bf5440a10affd749724787c8913a2ae0841.pdf)), today. They have instead made it available
Google AI Edge Gallery
Google AI Edge Gallery (https://apps.apple.com/nl/app/google-ai-edge-gallery/id6749645337) Terrible name, really great app: this is Google's official app for running their Gemma 4 models (the E2B
datasette-ports 0.2
Release: datasette-ports 0.2 (https://github.com/datasette/datasette-ports/releases/tag/0.2) • No longer requires Datasette - running uvx datasette-ports now works as well. • Installing
scan-for-secrets 0.3
Release: scan-for-secrets 0.3 (https://github.com/simonw/scan-for-secrets/releases/tag/0.3) • New -r/--redact option which shows the list of matches, asks for confirmation and then replaces
Cleanup Claude Code Paste
Tool: Cleanup Claude Code Paste (https://tools.simonwillison.net/cleanup-claude-code-paste) Super-niche tool this. I sometimes copy prompts out of the Claude Code terminal app and they come out
datasette-ports 0.1
Release: datasette-ports 0.1 (https://github.com/datasette/datasette-ports/releases/tag/0.1) Another example (https://gisthost.github.io/?f92d8a6bdadee1c77972b5e51954144e) of README-driven
Eight years of wanting, three months of building with AI
Eight years of wanting, three months of building with AI (https://lalitm.com/post/building-syntaqlite-ai/) Lalit Maganti provides one of my favorite pieces of long-form writing on agentic
Quoting Chengpeng Mou
From anonymized U.S. ChatGPT data, we are seeing: • ~2M weekly messages on health insurance • ~600K weekly messages [classified as healthcare] from people living in “hospital deserts” (30
Syntaqlite Playground
Tool: Syntaqlite Playground (https://tools.simonwillison.net/syntaqlite) Lalit Maganti's syntaqlite (https://github.com/LalitMaganti/syntaqlite) is currently being discussed on Hacker News
scan-for-secrets 0.2
Release: scan-for-secrets 0.2 (https://github.com/simonw/scan-for-secrets/releases/tag/0.2) • CLI tool now streams results as they are found rather than waiting until the end, which is
scan-for-secrets 0.1.1
Release: scan-for-secrets 0.1.1 (https://github.com/simonw/scan-for-secrets/releases/tag/0.1.1) • Added documentation of the escaping schemes that are also scanned. • Removed unnecessary
scan-for-secrets 0.1
Release: scan-for-secrets 0.1 (https://github.com/simonw/scan-for-secrets/releases/tag/0.1) I like publishing transcripts of local Claude Code sessions using my claude-code-transcripts
research-llm-apis 2026-04-04
Release: research-llm-apis 2026-04-04 (https://github.com/simonw/research-llm-apis/releases/tag/2026-04-04) I'm working on a major change (https://github.com/simonw/llm/issues/1314) to my LLM
Quoting Kyle Daigle
[GitHub] platform activity is surging. There were 1 billion commits in 2025. Now, it's 275 million per week, on pace for 14 billion this year if growth remains linear (spoiler: it won't.) GitHub
Vulnerability Research Is Cooked
Vulnerability Research Is Cooked (https://sockpuppet.org/blog/2026/03/30/vulnerability-research-is-cooked/) Thomas Ptacek's take on the sudden and enormous impact the latest frontier models are
The cognitive impact of coding agents
A fun thing about recording a podcast (https://simonwillison.net/2026/Apr/2/lennys-podcast/) with a professional like Lenny Rachitsky is that his team know how to slice the resulting video up into