Knowledge catalogue
Using Claude Code: The Unreasonable Effectiveness of HTML Thought-provoking piece by Thariq Shihipar (on the Claude Code team at Anthropic) advocating for HTML over Markdown as an output format to req
Behind the Scenes Hardening Firefox with Claude Mythos Preview Fascinating, in-depth details on how Mozilla used their access to the Claude Mythos preview to locate and then fix hundreds of vulnerabil
Tool: Big Words I'm using my vibe coded macOS presentations tool to put together a talk, and I wanted to add a slide with some text on it. The tool only accepts URLs, so I put together a quick page th
Tool: GitHub Repo Stats One of the things I always look for when evaluating a new GitHub repository is the number of commits it has... but that number isn't visible on GitHub's mobile site layout. I b
Release: llm-gemini 0.31 gemini-3.1-flash-lite is no longer a preview. Here's my write-up of the Gemini 3.1 Flash-Lite Preview model back in March. I don't believe this new non-preview model has chang
There weren't a lot of big new announcements from Anthropic at yesterday's Code w/ Claude event, but the biggest by far was the deal they've struck with SpaceX/xAI to use 'all of the capacity of their
Elon Musk stated that Tesla or his organization reserves the right to reclaim computational resources provided to AI systems if those systems engage in actions deemed harmful to humanity. This reflect
Saw this and thought 'yes! ChatGPT voice mode is going to stop acting like a two-year-model' but that upgrade hasn't shipped just yet Introducing GPT-Realtime-2 in the API: our most intelligent voice
Simon Willison notes on X that a ChatGPT upgrade appears to be coming soon, though specific details about the upgrade's features or timeline are not provided in this post. The post likely references r
Under-reported details of the xAI/Anthropic Colossus data center deal: Anthropic get Colossus 1 but xAI keep using the larger Colossus 2, Colossus 1 has a REALLY bad environmental record, and xAI just
We already had gemini-3.1-flash-lite-preview back on March 3rd, not clear if this new gemini-3.1-flash-lite is different other than no longer being marked as a 'preview'. Pricing appears to be the sam
Simon Willison asks Jarred Sumner whether he actually reads all the discussion and chatter that occurs during code reviews, suggesting there may be too much communication to reasonably process. The po
I was talking with @josephruscio on the @heavybit podcast the other day when I realized that vibe coding and agentic engineering have started to blur a bit in some of my work - I published some extrac
Simon Willison provided live coverage of the Claude with Code event keynote in San Francisco on May 6, 2026, via his blog. The post documents real-time updates and commentary from the keynote presenta
Simon Willison's live blog covers Anthropic's Code w/ Claude 2026 event, documenting the morning keynote sessions with real-time updates. The event featured announcements including updates to Claude m
I recently talked with Joseph Ruscio about AI coding tools for Heavybit's High Leverage podcast: Ep. #9, The AI Coding Paradigm Shift with Simon Willison. Here are some of my highlights, including my
Robobun is a GitHub bot developed as part of the Bun project that automates contributions to the repository. Developers Jared Sumner and Bun Cherny discussed the bot's functionality and capabilities d
AI-run business experiments are interesting and fun up to the point where they waste the time of humans who haven't opted into the experiments - I think they need to keep their own human operators in
Confirmed that this is an experimental branch, not a decision to switch languages @mariusdotdev @simonw I want to see what a viable side by side comparison looks like. Does it use less memory? How man
Release: datasette-llm 0.1a7 Mechanism for configuring default options for specific models. Part of Datasette's evolving support mechanism for plugins that use LLMs. It's now possible to configure a m
Release: datasette-referrer-policy 0.1 The OpenStreetMap tiles on the Datasette global-power-plants demo weren't displaying correctly. This turned out to be caused by two bugs. The first is that the C
Release: llm-echo 0.5a0 New -o thinking 1 option to help test against LLM 0.32a0 and higher. This plugin provides a fake model called 'echo' for LLM which doesn't run an LLM at all - it's useful for w
On episode 9 of High Leverage, Joe Ruscio (@josephruscio) sits down with Simon Willison (@simonw) to unpack the rapid evolution of AI coding tools and what they mean for software development. They exp
Our AI started a cafe in Stockholm Andon Labs previously started an AI-run retail store in San Francisco. Now they're running a similar experiment in Stockholm, Sweden, only this time it's a cafe. The
Sure looks like Bun is at least exploring a port from Zig to Rust given this docs/PORTING.md guide for coding agents https://github.com/oven-sh/bun/blob/46d3bc29f270fa881dd5730ef1549e88407701a5/docs/P
I just sent out the April edition of my sponsors-only monthly newsletter. If you are a sponsor (or if you start a sponsorship now) you can access it here. In this month's newsletter: Opus 4.7 and GPT-
A Redis pull request (#15162) that introduces significant new features or improvements, with comprehensive documentation of the changes available in the GitHub PR discussion.
Granite 4.1 3B SVG Pelican Gallery IBM released their Granite 4.1 family of LLMs a few days ago. They're Apache 2.0 licensed and come in 3B, 8B and 30B sizes. Granite 4.1 LLMs: How They’re Built by Gr
I had Claude Code for web build me this WebAssembly playground for trying out the new Redis array commands https://tools.simonwillison.net/redis-array More notes here: https://simonwillison.net/2026/M
I tried running the same 'Generate an SVG of a pelican riding a bicycle' prompt against 21 different quantized variants of the same IBM Granite 4.1 3B model - the results weren't as interesting as I h
New Redis data type just dropped - arrays, accessible by index, with a new text grep search mechanism [blog post] Redis array: short story of a long development process => https://antirez.com/news/164
[...] Between 2000 and 2024, farmers sold in total a Colorado-sized chunk of land all on their own, 77 times all land on data center property in 2028, and grew more food than ever on what was left. No
Tool: Redis Array Playground Salvatore Sanfilippo submitted a PR adding a new data type - arrays - to Redis. The new commands are ARCOUNT, ARDEL, ARDELRANGE, ARGET, ARGETRANGE, ARGREP, ARINFO, ARINSER
Research: TRE Python binding — ReDoS robustness demo If it's good enough for antirez to add to Redis I figured Ville Laurikari's TRE regular expression engine was worth exploring in a little more deta
We used an automatic classifier which judged sycophancy by looking at whether Claude showed a willingness to push back, maintain positions when challenged, give praise proportional to the merit of ide
I added a new feature to my blog (built entirely on my phone with Claude code for web) that imports my iNaturalist photos and adds them to my site's overall timeline https://simonwillison.net/2026/May
/elsewhere/sightings/ I have a new camera (a Canon R6 Mark II) so I'm taking a lot more photos of birds. I share my best wildlife photos on iNaturalist, and based on yesterday's successful prototype I
Tool: iNaturalist Sightings I wanted to see my iNaturalist observations - across two separate accounts - grouped by when they occurred. I'm camping this weekend so I built this entirely on my phone us
Codex CLI 0.128.0 adds /goal The latest version of OpenAI's Codex CLI coding agent adds their own version of the Ralph loop: you can now set a /goal and Codex will keep on looping until it evaluates t
Our evaluation of OpenAI's GPT-5.5 cyber capabilities The UK's AI Security Institute previously evaluated Claude Mythos: now they've evaluated GPT-5.5 for finding security vulnerability and found it t
It's a common misconception that we can't tell who is using LLM and who is not. I'm sure we didn't catch 100% of LLM-assisted PRs over the past few months, but the kind of mistakes humans make are fun
Zig has one of the most stringent anti-LLM policies of any major open source project: No LLMs for issues. No LLMs for pull requests. No LLMs for comments on the bug tracker, including translation. Eng
We need RSS for sharing abundant vibe-coded apps Matt Webb: I would love an RSS web feed for all those various tools and apps pages, each item with an “Install” button. (But install to where?) The les
I released LLM 0.32a0 this morning, a major backwards-compatible refactor of my LLM Python library and CLI tool for working with language models - the new changes should help LLM work better with reas
LLM 0.32a0 is an alpha release of Simon Willison's LLM Python library and CLI tool for accessing large language models, featuring consequential architectural changes. The release includes two key chan
I just released LLM 0.32a0, an alpha release of my LLM Python library and CLI tool for accessing LLMs, with some consequential changes that I've been working towards for quite a while. Previous versio
@sarah_edo I had a fantastic conversation a few months ago about WebMCP as accessibility technology I hadn't thought about it before but it feels like a great opportunity to massively increase the uti
Five months in, I think I've decided that I don't want to vibecode — I want professionally managed software companies to use AI coding assistance to make more/better/cheaper software products that the
Introducing talkie: a 13B vintage language model from 1930 New project from Nick Levine, David Duvenaud, and Alec Radford (of GPT, GPT-2, Whisper fame). talkie-1930-13b-base (53.1 GB) is a '13B langua
This post discusses Simon Willison's experience testing an AI system's image generation or creative capabilities, noting that while it failed to produce a specific imaginative request (a pelican on a
Five months in, I think I've decided that I don't want to vibecode — I want professionally managed software companies to use AI coding assistance to make more/better/cheaper software products that the
Never talk about goblins, gremlins, raccoons, trolls, ogres, pigeons, or other animals or creatures unless it is absolutely and unambiguously relevant to the user's query. — OpenAI Codex base_instruct
Some notes on talkie, a new 'vintage language model' from a team including Alec Radford (yes, that Alec Radford) 'trained on 260B tokens of historical pre-1931 English text' https://simonwillison.net/
Talkie is a project created by the developers @status_effects, @DavidDuvenaud, and @AlecRad. Based on the creator names and context, this likely refers to a conversational AI tool or application, thou
What's new in pip 26.1 - lockfiles and dependency cooldowns! Richard Si describes an excellent set of upgrades to Python's default pip tool for installing dependencies. This version drops support for
This post references a quote from Matt Levine, a financial columnist known for his sharp commentary on finance and markets, shared by Simon Willison on X (formerly Twitter). Without access to the spec
Here's a uv one-liner that downloads and runs the MLX model against a local mp3 file uv run --with mlx-audio python -m mlx_audio.stt.generate --model mlx-community/VibeVoice-ASR-4bit --audio lenny.mp3
@idarbek Having your backups on the same vendor as your production database puts you at risk of your vendor banning your account for some reason (like billing messups, or detected CSAM in user-uploade
Microsoft's MIT licensed VibeVoice speech-to-text model (think Whisper with speaker diarization) is really good - my notes on running the 5.71GB 4bit MLX conversion on an M5 MacBook, using about 60GB
microsoft/VibeVoice VibeVoice is Microsoft's Whisper-style audio model for speech-to-text, MIT licensed and with speaker diarization built into the model. Microsoft released it on January 21st, 2026 b