Serving the For You feed
Serving the For You feed (https://atproto.com/blog/serving-the-for-you-feed) One of Bluesky's most interesting features is that anyone can run their own custom "feed" implementation (bluesky custom
Serving the For You feed (https://atproto.com/blog/serving-the-for-you-feed) One of Bluesky's most interesting features is that anyone can run their own custom "feed" implementation (bluesky custom
LlamaIndex have a most excellent open source project called LiteParse (https://github.com/run-llama/liteparse), which provides a Node.js CLI tool for extracting text from PDFs. I got a version of
GPT-5.5 is out (https://openai.com/index/introducing-gpt-5-5/). It's available in OpenAI Codex and is rolling out to paid ChatGPT subscribers. I've had some preview access and found it to be a fast,
[...] if you ever needed another reason to learn in public (https://www.swyx.io/learn-in-public) by digital gardening (https://maggieappleton.com/garden-history) or podcasting or streaming or
Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model (https://qwen.ai/blog?id=qwen3.6-27b) Big claims from Qwen about their latest open weight model: Qwen3.6-27B delivers flagship-level agentic
As part of our continued collaboration with Anthropic, we had the opportunity to apply an early version of Claude Mythos Preview to Firefox. This week’s release of Firefox 150 includes fixes for
Changes to GitHub Copilot Individual plans (https://github.blog/news-insights/company-news/changes-to-github-copilot-individual-plans/) On the same day as Claude Code's temporary
Anthropic today quietly (as in silently, no announcement anywhere at all) updated their claude.com/pricing (https://claude.com/pricing) page (but not their Choosing a Claude plan page
OpenAI released ChatGPT Images 2.0 today (https://openai.com/index/introducing-chatgpt-images-2-0/), their latest image generation model. On the livestream
AI agents are already too human. Not in the romantic sense, not because they love or fear or dream, but in the more banal and frustrating one. The current implementations keep showing their human
scosman/pelicans_riding_bicycles (https://github.com/scosman/pelicans_riding_bicycles) I firmly approve of Steve Cosman's efforts to pollute the training set of pelicans riding bicycles. (To be
Release: llm-openrouter 0.6 (https://github.com/simonw/llm-openrouter/releases/tag/0.6) • llm openrouter refresh command for refreshing the list of available models without waiting for the
TIL: SQL functions in Google Sheets to fetch data from Datasette (https://til.simonwillison.net/google-sheets/datasette-sql) I put together some notes on patterns for fetching data from a
Claude Token Counter, now with model comparisons (https://tools.simonwillison.net/claude-token-counter) I upgraded (https://github.com/simonw/tools/pull/269) my Claude Token Counter tool to add the
Headless everything for personal AI (https://interconnected.org/home/2026/04/18/headless) Matt Webb thinks headless services are about to become much more common: Why? Because using personal AIs is
Anthropic are the only major AI lab to publish the system prompts (https://platform.claude.com/docs/en/release-notes/system-prompts) for their user-facing chat systems. Their system prompt archive
Research: Claude system prompts as a git timeline (https://github.com/simonw/research/tree/main/extract-system-prompts#readme) Anthropic publish the system prompts
Agentic Engineering Patterns (https://simonwillison.net/guides/agentic-engineering-patterns/) > Here's an example of a deceptively short prompt that got a lot of work done in a single shot.
This year's PyCon US (https://us.pycon.org/2026/) is coming up next month from May 13th to May 19th, with the core conference talks from Friday 15th to Sunday 17th and tutorial and sprint days either
Release: datasette 1.0a28 (https://github.com/simonw/datasette/releases/tag/1.0a28) I was upgrading Datasette Cloud to 1.0a27 (https://simonwillison.net/2026/Apr/15/datasette/) and discovered a