Search: “simon-willison--x”

A new TIL on adding custom MCP servers to both the ChatGPT and Claude regular chat interfaces - it's a little less obvious than I had hoped, but I got there in the end https://til.simonwillison.net/ll

Happy Stateless MCP day! I just got taught that you can use Cloudflare's AI Playground: https://playground.ai.cloudflare.com/ to play with MCP servers like: https://keyboardia.dev/mcp or: https://agen

I really hope we get details from @OpenAI on the task that as specifies to their rogue agent I'm guessing it was given the full ExploitGym suite and told to solve it, with an option to run 5.6-Sol sub

@mitsuhiko Turns out the 'third-party provider' with the sandbox that was used for the attack was Modal, though they blame one of their customers for deploying an endpoint without authentication: http

This is detailed, fascinating and answers all sorts of open questions I'd love to know more about the 'unsecured public code-evaluation sandbox hosted on a third-party provider's infrastructure' that

ChatGPT Sites means ChatGPT in 'Work' mode can build and deploy public websites running on Cloudflare Workers, including with persistence on top of SQLite (OpenAI do not make it easy to figure out tha

I wrote about the completely wild incident where OpenAI were testing a new model and it broke out of its sandbox and broke INTO Hugging Face to steal the answers to the benchmark https://simonwillison

Tucked away in this article is an appeal to the AI skeptics to PLEASE stop writing off stories like this OpenAI accidental exploit of Hugging Face as a dishonest marketing trick Frontier models can fi

We talked about Claude Code, Claude Tag, Fable, coding agent security, evals, tool design, and how Anthropic use these tools themselves Claude Tag (Claude Code via Slack) is already landing 65% of the

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

'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

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

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

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

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.

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

'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

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

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

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-

Simon Willison discusses an ambitious project involving Fable, likely covering current development priorities or technical challenges in the Fable programming language or related tools. The post appea

'You need a rich set of concepts in your mind to think creatively and fluently about how to move something forward.' It's never just one loop! A project is many, many loops with the agent. And the und

@_catwu @simonw and I will be doing a fireside chat about 'This year in Claude' from 12:30pm-1:30pm at AIE in Expo Stage 2. We'll be covering a really wide range of topics and I think it will be reall

I've added video support to my 'shot-scraper' browser automation tool - you (or your coding agent) can now create a storyboard YAML file and use that to record a video demo of new web application feat

Notes (and a Pelican) on Claude Sonnet 5 - the new tokenizer makes it ~1.4x more expensive for English, ~1.33x more expensive for Spanish but roughly the same price for Simplified Mandarin https://sim

We’ve received notice that the Department of Commerce has lifted export controls on Claude Fable 5 and Mythos 5. We'll begin restoring access tomorrow, and will share an update soon. We’re grateful to

Is it just me, or are today's LLMs less likely to default to building everything in React than they were last year? I used to have to say 'don't use React' in almost all of my frontend web dev prompts

Not sure if that's a change in default preferences from the models or just that I'm often prompting inside existing projects and the models know full well not to introduce React to a project that isn'

This statement is a critical analogy about dismissing learning curves in technology or professional contexts. Simon Willison uses the comparison to highlight how unrealistic expectations—assuming empl

Also not a great advertisement for a sandboxing product: @daytonaio effectively saying they don't trust the security of their product enough to expose the source code When the competition for sandboxe

Update: it's fixed! @simonw @ClaudeDevs @claudeai This is fixed — the egress proxy was incorrectly blocking git/gh reads to public repos that weren't attached to the session. Clones/fetches work again

Claude Code for web just started saying 'GitHub is blocked by egress policy', which is a big problem for me because most of my prompts there start with things like 'clone simonw/sqlite-utils to /tmp t

This entry references a Claude.ai coding session shared by Simon Willison, a well-known technology writer and open source developer, likely demonstrating a practical example of using Claude's code int

... and now you can buy your own! https://happy-pelicans.printify.me/product/29480311 Proceeds go to http://birdrescue.org, a local non-profit that rescues pelicans (among other birds) I printed a cus