Search: “simon-willison”

Directly Responsible Individuals (DRI) I went looking for a definition of 'Directly Responsible Individuals' and the best I found was in the GitLab handbook. Apparently the term originated at Apple, w

One of the consequences of GPT-5.6 Sol being clearly a Fable/Mythos class model is that Anthropic have, once again, bumped the date that Fable stops being available in their Claude Max plans: We're ex

More interesting is the difference between 'Chat' and 'Work' modes in the ChatGPT mobile app It looks like Work mode can run code that talks to the Internet! I just tried having both modes use yt-dlp

Anyone know if ChatGPT Codex (in the new ChatGPT desktop app) is a strict superset of ChatGPT Work? Liked if you're a software engineer who isn't intimidated by Git features is there any reason you'd

OpenAI insiders have indicated that differences between their products are purely UI-based rather than reflecting actual capability differences. This suggests that what may appear to be distinct produ

One of the most confusing aspects of GPT-5.6 is figuring out which model to use at which reasoning effort - sounds like Sol on Medium might be a good new default for coding work, if it's an upgrade fr

The reality is to make augmented reality glasses, you need to put a camera next to your eyes that is continuously recording everything you see and processing that to put information over it. There is

[...] Work on web and mobile runs in the cloud. Work in the desktop app can also use local files and desktop apps with your permission. At launch, cloud Work conversations do not appear in desktop Wor

'We’re bringing chats and projects back into the sidebar in a more familiar and customizable way' - hopefully that means the ChatGPT app won't hide classic chat away in that weird little floating wind

With Atlas being retired in favor of the browser embedded in the ChatGPT app I wonder if the whole category of AI-enhanced browsers is coming to a close The security/privacy issues remain unsolvable I

... and if you want to see some of OpenAI's own pelicans they featured a 3D pelican riding a tricycle, bicycle, pony, and another pelican in their livestream this morning: https://www.youtube.com/live

Introducing Muse Spark 1.1 Following Muse Spark in April, here's Muse Spark 1.1 - the first Spark model to offer an API. Meta claim significant improvements in agentic tool calling and computer use. T

Release: llm 0.31.1 Fix for a bug with OpenAI Chat Completion endpoints where a tool call with empty arguments could result in a JSON error from some providers. #1521 This bug came up when I was testi

Notes on GPT-5.6, which includes some interesting new additions to the API (programmatic tool calling and multi-agent in particular) - plus 18 pelicans for the 6 reasoning levels and 3 new models: htt

OpenAI's latest flagship model hit general availability this morning, and comes in three sizes: Luna, Terra, and Sol (from smallest to largest). The new models are priced per 1M input/output tokens as

Introducing GPT‑Live OpenAI finally upgraded the model used by ChatGPT voice mode! I've had preview access for a few weeks in the iPhone app, and the new model is very impressive. It also has the abil

I've been letting Claude and GLT-5.5 write almost all of my commit messages recently, but I don't feel great about it 'omitting the higher-level framing needed to understand broadly what the code is d

I just declared a moratorium against AI-written change descriptions (e.g. PR and commit messages, also issues/tickets) from my team. AI was writing change descriptions that were worse than useless to

Rewriting Bun in Rust Jarred Sumner has been promising this blog post (since May 9th) about his Zig to Rust rewrite of Bun for significantly longer than it took him to finish the rewrite. Honestly, it

Sometimes they DO attempt to do that but guess the rationale incorrectly, which is worse than not adding no a rationale at all I do try to link commits back to issues though, which are written by me a

Tool: github-code Web Component An experimental Web Component built using GPT-5.5 and the following prompt: let's build a Web Component for embedding code from GitHub <github-code href='https://github

I had Claude Fable 5 run a final review of the release using this prompt and it kicked up another four release blockers! https://simonwillison.net/2026/Jul/7/sqlite-utils-4/#claude-fable-5-helped-a-lo

I released sqlite-utils 4.0, the 124th release but the first major version bump since 3.0 back in 2020 I managed to keep things backwards-compatible all the way up to version 3.39 before the accumulat

Now I'm regretting having carefully blasted through 100% of my Fable allotment in time for being cut off at the end of today! (Presumably 'Wed 12:00 PM' means I get it back at noon on Wednesday, not a

Since this is a slightly backwards-incompatible change here's a detailed upgrade guide - which you can read, or feed into your coding agent and have it apply the upgrades for you https://sqlite-utils.

sqlite-migrate is a simple database migration system for SQLite, based on sqlite-utils. Version 0.2 represents sqlite-migrate as a database migrations system for SQLite, loosely inspired by Django mig

sqlite-utils 4.0 introduces three major new features: database migrations for schema evolution, nested transaction support via db.atomic(), and support for compound foreign keys. The release includes

This morning I released sqlite-utils 4.0, the 124th release of that project and the first major version bump since 3.0 in November 2020. In addition to some small but significant breaking changes (des

Release: sqlite-utils 4.0rc3 I hoped to release sqlite-utils 4.0 stable this weekend, but as I worked through the backlog of issues and PRs with a combination of Claude Fable 5 and GPT-5.5 the changel

tencent/Hy3 New Apache 2.0 licensed model from Tencent in China: Hy3 is a 295B-parameter Mixture-of-Experts (MoE) model with 21B active parameters and 3.8B MTP layer parameters, developed by the Tence

Somewhat humbling to have Claude Fable do a final review of some software that you're about to release and have it then find (and fix) FIVE release blockers, for an estimated (unsubsidized) cost of $1

I wrote about the sqlite-utils 4.0rc1 release a couple of weeks ago. Since we only have Claude Fable on our Max subscriptions for a few more days, I decided to see if it could help me get to a 4.0 sta

Better Models: Worse Tools Armin reports on a weird problem he ran into while hacking on Pi: The short version is that newer Claude models sometimes call Pi’s edit tool with extra, invented fields in

Building a World Map with only 500 bytes Iwo Kadziela (assisted by Codex) figured out a way to generate a credible ASCII world map using 445 bytes of data: The key trick is to use deflate compression,

'At least this felt ambitious until fable chewed through each of my requests like it was nothing...' @simonw I made this 3D video infographic explaining the AuthaGraph map projection, with population

One of the most interesting tips I got from the Fireside Chat I hosted with Cat Wu and Thariq Shihipar from the Claude Code team at AIE on Wednesday was to let Fable (and to a certain extent Opus) use

I absolutely hate how I'm getting to be suspicious of ANY reply to my posts here, especially ones that pose a question, as they are so often from bot accounts If you're running a bot like this please

The June edition of my sponsors-only monthly newsletter is out. If you are a sponsor (or if you start a sponsorship now) you can access it here. This month: Claude Fable 5, GPT-5.6, and US export rest

Simon Willison shares additional notes and commentary on his blog regarding judgment and decision-making processes. The post likely explores practical considerations or philosophical perspectives on h

Open Source AI Gap Map Current AI is 'a global partnership building a public option for AI', founded as a non-profit at the AI Action Summit in Paris in February 2025 and backed by serious capital ($4

I just launched my third course, Whimsical Animations, and so far, it’s on track to sell roughly ⅓ as many copies as a typical course launch. It’s a similar story with my two existing courses. Sales a

Sent out my sponsors-only monthly newsletter for June, which means the May newsletter is now available here https://github.com/simonw/monthly-newsletter-archive/blob/main/2026-05-may.md - you can spon

The most interesting Fable tip I've heard so far is to let the model use its own judgement as much as possible I told it 'For all coding tasks use your judgement to decide an appropriate lower power m

Simon Willison discusses the relationship between understanding and participation, exploring how comprehension of a topic or system is fundamental to meaningful engagement or contribution. The blog po

I really like this 'understand to participate' framing of the cognitive debt problem when working with coding agents That's where another answer comes in: we can understand to participate. You can lea

I've been blogging a few of my Fable experiments today, most recently I had it more-or-less one-shot a CLI coding agent on top of my LLM Python library https://simonwillison.net/2026/Jul/2/llm-coding-