Release: datasette-agent 0.1a2

• Tool availability can now be attached to a required_permission. The default background agent tools now require the new datasette-agent-background permission. #10

Tags: datasette, datasette-agent

This Mitchell Hashimoto quote about Bun migrating from Zig to Rust reminded me of a similar conversation I had at a conference last week. I was talking to someone who worked for a medium sized technology company with a pair of legacy/legendary iPhone and Android apps. They t...

[...] On the interesting side is how fungible programming languages are nowadays. Programming languages used to be LOCK IN, and they're increasingly not so. You think the Bun rewrite in Rust is good for Rust? Bun has shown they can be in probably any language they want in roughly a week or two. Rust is expendable. Its useful until its not then it can be thrown out. That's interesting!

— Mitchell Hashimoto, on Bun porting from Zig to Rust

Tags: zig, ai, mitchell-hashimoto, llms, rust, generative-ai, agentic-engineering, bun

Release: datasette-agent 0.1a1

• Now uses the execute-sql permission when deciding which tables to list to the user. #8

Tags: datasette, datasette-agent

Release: datasette-ip-rate-limit 0.1a0

The datasette.io site was being hammered by poorly-behaved crawlers, so I had Codex (GPT-5.5 xhigh) build a configurable rate limiting plugin to block IPs that were hammering specific areas of the site too quickly.

Here's the production configuration I'm using on that site for the new plugin:

  datasette-ip-rate-limit:
    header: Fly-Client-IP
    max_keys: 10000
    exempt_paths:
    - "/static/*"
    - "/-/turnstile*"
    rules:
    - name: public-demo-multi-parameter-table-pages
      paths:
      - "/global-power-plants/*"
      - "/legislators/*"
      window_seconds: 60
      max_requests: 60
      block_seconds: 20

Tags: datasette, rate-limiting, codex

Welcome to the Datasette blog

We have a bunch of neat Datasette announcements in the pipeline so we decided it was time the project grew an official blog.

I built this using OpenAI Codex desktop, which turns out to have the Markdown session transcript export feature I've always wanted. Here's the session that built the blog. See also issue 179.

Tags: ai, datasette, generative-ai, llms, ai-assisted-programming, codex-cli

“11 AI agents” is meaningless as a phrase.

If I said “I have 11 spreadsheets” or “I have 11 browser tabs” to do my work, it means about the same thing.

— Boris Mann

Tags: ai-agents, ai, agent-definitions

Tool: CSP Allow-list Experiment

An experiment that shows that you can load an app in a CSP-protected sandboxed iframe (see previous note) and have a custom fetch() that intercepts CSP errors and passes them up to the parent window... which can then prompt the user to add that domain to an allow-list and then refresh the page.

I built this one with GPT-5.5 xhigh running in the Codex desktop app.

Tags: content-security-policy, iframes, security

Release: datasette 1.0a29 New TokenRestrictions.abbreviated(datasette) utility method for creating "_r" dictionaries. #2695 Table headers and column options are now visible even if a table contains zero rows. #2701 Fixed bug with display of column actions dialog ...

Release: llm 0.32a2

A bunch of useful stuff in this LLM alpha, but the most important detail is this one:

Most reasoning-capable OpenAI models now use the /v1/responses endpoint instead of /v1/chat/completions. This enables interleaved reasoning across tool calls for GPT-5 class models. #1435

This means you can now see the summarized reasoning tokens when you run prompts against an OpenAI model, displayed in a different color to standard error. Use the -R or --hide-reasoning flags if you don't want to see that.

Tags: llm, projects, openai, generative-ai, annotated-release-notes, ai, llms

Now, if your CEO has never heard the phrase Ralph Loop, oh man, you are less than 30 days away from your next promotion. I'm not even exaggerating. Walk into his office, close the door, and say, hey chief, been experimenting with something. It's called Ralph Loops. And I th...

The thing about 90% of TDMs [Technical Decision Makers] is that they're motivated primarily by NOT GETTING FIRED. These aren't people who browser Lobsters or push to GH on the weekend. These are people that work 9 to 5, get paid, go home, and NEVER THINK ABOUT WORK AGAIN. So to achieve all that, they follow secular trends supported by analysts and broad public sentiment. Oh, Gartner said that "AI strategy" is most important? McKinsey said "context" needs to be managed? Well, "Context Engine for AI Apps" is going to be defensible. Buy it.

— Mitchell Hashimoto, in a conversation about the design of the Redis homepage

Tags: marketing, mitchell-hashimoto, redis

GitLab Act 2 There's a lot going on in this announcement from GitLab about the "workforce reduction" and "structural and strategic decisions" they are making with respect to the agentic era. They're "planning to reduce the number of countries by up to 30% where we have smal...

Your AI coding agent, the one you use to write code, needs to reduce your maintenance costs. Not by a little bit, either. You write code twice as quick now? Better hope you’ve halved your maintenance costs. Three times as productive? One third the maintenance costs. Otherwi...

Your AI Use Is Breaking My Brain Excellent, angry piece by Jason Koebler on how AI writing online is becoming impossible to avoid, filtering it is mentally exhausting and it's even starting to distort regular human writing styles. I particularly liked his use of the term "Zo...

TIL: Using LLM in the shebang line of a script Kim_Bruning on Hacker News: But seriously, you can put a shebang on an english text file now (if you're sufficiently brave) [...] This inspired me to look at patterns for doing exactly that with LLM. Here's the simples...

Learning on the Shop floor Tobias Lütke describes Shopify's internal coding agent tool, River, which operates entirely in public on their Slack: River does not respond to direct messages. She politely declines and suggests to create a public channel for you and her to start...

This article was updated after The Times learned that a remark attributed to Pierre Poilievre, the Conservative leader, was in fact an A.I.-generated summary of his views about Canadian politics that A.I. rendered as a quotation. The reporter should have checked the accuracy of what the A.I. tool returned. The article now accurately quotes from a speech delivered by Mr. Poilievre in April. [...] He did not refer to politicians who changed allegiances as turncoats in that speech.

— New York Times Editors’ Note

Tags: ai-ethics, hallucinations, generative-ai, new-york-times, journalism, ai, llms

One could say in the first quarter-century of my life, that while I was always fascinated by programming, I could never overcome the guilt of not really knowing whether the tool I am building right now isn’t already superceded by some much better implementation someone else ...

WebRTC is designed to degrade and drop my prompt during poor network conditions. wtf my dude WebRTC aggressively drops audio packets to keep latency low. If you’ve ever heard distorted audio on a conference call, that’s WebRTC baybee. The idea is that conference calls depen...

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 request from Claude. The article is crammed with interesting examples (collect...

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 changed since then.

Tags: llm-release, gemini, llm, google, generative-ai, ai, llms

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 that accepts query string arguments and turns them into a simple slide.

Here's an example: https://tools.simonwillison.net/big-words?text=simonwillison.net&gradient=1&size=9.5

Double click or double tap the page to access a form for modifying the different options.

Tags: vibe-coding, tools

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 built this tool to fix that, using this prompt:

Given a GitHub repo URL or foo/bar repo ID show information about that repo absorbed via wither REST or graphql CORS fetch() including the number of commits in the repo and other useful stats

Example output for simonw/datasette and simonw/llm.

Tags: github

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 vulnerabilities in Firefox: Suddenly, the bugs are very good Just a few months ago, ...

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 Colossus data center". As I mentioned in my live blog of the keynote, that...

I'm at Anthropic's Code w/ Claude event in 2026, and I'll be live blogging the keynote and a few other notes throughout the day.

Tags: ai, generative-ai, llms, anthropic, claude, live-blog

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 disturbing realization that vibe coding and agentic engineering have starte...

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 CAPTCHA I added to that site a few weeks ago was triggering for the .json fetch requests used by the map plugin, and since those weren't HTML the user was not being asked to solve them. Here's the fix.

The second was that OpenStreetMap quite reasonably block tile requests from sites that use a Referrer-Policy: no-referrer header.

Datasette does this by default, and I didn't want to change that default on people without warning - so I had Codex + GPT-5.5 build me a new plugin to help set that header to another value.

Tags: openstreetmap, http, datasette

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. These experiments are interesting, and often throw out amusing anecdotes: Dur...