Latest entries
-
In reversal, American Cancer Society urges routine prostate cancer screening
Men aged 50–69 and at average risk should get PSA screening every two years.
Ars Technica — Published
-
llm-gemini 0.37
Release: llm-gemini 0.37 Google launched Gemini 4 Hydrogen today - the lowest cost member of the Gemini 4 family. It's actually not too far off the price of its much bigger siblings, Carbon and Argon. I'm finding Gemini 4's pricing really confusing. Here's the pricing scheme: Model Dates Input ($/M)…
Simon Willison — Published
-
FAA expands AI advice to manage air traffic congestion across entire US airspace
Airlines praised the AI tool, but the air traffic controllers’ union wasn’t involved.
Ars Technica — Published
-
Ars Live: What drone attacks on data centers mean for modern life in the cloud
A livestream Ars discussion is happening on November 17 at 1 pm Eastern Time.
Ars Technica — Published
-
The Elder Scrolls' most obscure adventure gets a 4K PC makeover
N-Gage exclusive Shadowkey gets an AI-coded glow-up with plenty of new features.
Ars Technica — Published
-
Google rolls out Gemini 4 Hydrogen, finally replacing 3.8 Flash
Gemini 4 Hydrogen isn't getting a slow, security-conscious release like Carbon and Argon.
Ars Technica — Published
-
Ukraine says it can’t stop Russian strikes because Starshield is limited again
Report: Ukraine suspects speeds limits are intended to help Russia in peace talks.
Ars Technica — Published
-
Google faces calls for AI moratoriums in schools after Gemini pilot backlash
Families confront Google after teen’s lawsuit labels Gemini a “suicide coach.”
Ars Technica — Published
-
Netflix releases new trailer for Ray Gunn
"It's hard being the only honest players in a crooked game."
Ars Technica — Published
-
Building a rocket is hard. AST SpaceMobile thinks it's "simple."
"We're not doing this thing because we like rockets."
Ars Technica — Published
-
Man's secret use of synthetic testosterone for cows nearly destroyed his heart
Doctors warn that such life-threatening cases are becoming more common.
Ars Technica — Published
-
The amazing disappearing exoplanet
An exoplanet seems to have stopped transiting in front of its host star.
Ars Technica — Published
-
Google pushes privacy angle as Gemini-powered smartglasses debut starting at $395
The first Gemini smartglasses are a collab between Google, Samsung, Gentle Monster, and Warby Parker.
Ars Technica — Published
-
Nvidia CEO Jensen Huang has resigned
Nvidia CEO also had an affair with a senior executive at the firm.
Ars Technica — Published
-
Hundreds of streaming services and nothing to watch
Most viewers wish there was a TV Guide for streaming.
Ars Technica — Published
-
Review: Apple's M6 iMac is pricey, but it's still a good choice for a clean desk
Apple's M6 keeps the iMac current without shaking things up much.
Ars Technica — Published
-
Creating Your Own Gaming Backlog Yields Behavioural Insights
At the end of 2024, I made my own video game Top 100 page, resulting in a cool grid-based list available at https://jefklakscodex.com/top100/. While writing A Huge Pile Called The Ongoing Backlog, I discovered even more websites dedicated to categorising and indexing your backlog: Giant Bomb’s Video…
Wouter Groeneveld — Published
-
Contra "Glue work considered harmful"
Sean Goedecke, Glue work considered harmful (emphasis here, and in the rest of the quotes, in original): So why doesn’t glue work get you promoted, if it’s so crucial to shipping projects? Are companies stupid? Are they deliberately leaving value on the table? No, I don’t think so. Companies don’t reward…
Rain — Published
-
Français: La sincérité de l’effort
J'ai la préférence de tester mes idées.
Protesilaos Stavrou — Published
-
Gemini Decisions API
Gemini Decisions API Google join Jev and OpenAI in the decision model category with "Gemini Decision 1". This new model API is almost identical to Jev: it supports the same three types of questions (yes/no, choice, and rubric-scoring) and even reuses Jev's term "Noul" for a yes/no question. It's priced…
Simon Willison — Published
-
aws-emulator
aws-emulator Finally, an official emulator from AWS to run tests against a local clone of their many different services without having to provision a paid API key to do so. It's written in Rust by a huge swarm of agents - 29,684 commits in the first three weeks of the project. Swaminathan (Swami) Sivasubramanian…
Simon Willison — Published
-
T-Mobile illegally imposed 50GB cap on low-income home Internet plan, NY says
Law requires 25Mbps home Internet. T-Mobile lowers speed to 600Kbps after 50GB cap.
Ars Technica — Published
-
Anduril says its first satellite can see adversaries maneuver in orbital night
"What's unique is it's got a huge dynamic range. We can see things in full dark."
Ars Technica — Published
-
NASA's secret weapon in the lunar space race may be ... procurement reform?
"The pace that's occurring, and the nature of the procurements, is unprecedented."
Ars Technica — Published
-
Browse tools.simonwillison.net by tag
Browse tools.simonwillison.net by tag I've been wanting a better way to browse my collection of vibe-coded tools (244 and counting) for a while. I had a few Fable 5.2 credits left over before my weekly reset so I set it to work using tree-sitter to analyze the code for JavaScript APIs, libraries, and…
Simon Willison — Published
-
Taiwan’s chipmaking giant TSMC to invest $1B in Anthropic, OpenAI
Latest example of the AI boom’s circular financing comes as AI trade wobbles.
Ars Technica — Published
-
Who Runs the Ransomware Group Qilin?
The cybercrime group Qilin has emerged as the world's most active ransomware affiliate program, claiming at least 365 victim organizations in the past three months alone. But even top Russian hackers make operational security mistakes, and the administrator of Qilin has made a few key missteps over the…
Brian Krebs — Published
-
Trump admin loses fight to spy on random journalists’ LinkedIn DMs
Confidential sources “lifeblood” of free press, court rules in LinkedIn fight.
Ars Technica — Published
-
llm 0.37.2
Release: llm 0.37.2 Fixes a security issue reported by Daniel de Araujo in GHSA-v9h7-jj4g-f862 and GHSA-r639-rr7r-x72w. LLM has a mechanism called extra-openai-models.yaml - now managed by the new-in-0.37 llm openai endpoint add command - for using LLM with OpenAI-compatible API endpoints from other…
Simon Willison — Published
-
Anthropic's IPO roadshow video
Anthropic's IPO roadshow video Anthropic kicked off their IPO roadshow yesterday, and their roadshow video has some previously unreleased information about how their business works. The section on "Approach to compute" with co-founder Tom Brown is particularly interesting, describing how Anthropic train…
Simon Willison — Published
-
Herdr and the Meta-harness
I see a lot of discussion around “TUI vs. GUI” for coding agents. This discussion is often of the form: “the more I use Claude Code/Codex/Pi, the more I’ve outgrown the TUI and want to use a GUI app”. The comment that nudged me to write this is in this recent HN discussion: I used to use ChatGPT/Claude…
Ben Congdon — Published
-
Better Day, Sunshine
I haven’t driven a car in decades (New Yorker). But from my pre-New York life, I remember how sun glare could turn a pleasant road trip into a blinding gauntlet. Enter “Sunward,” a uniquely specific demo app my Automattic colleague Peter Westwood just whipped up in Spacefast. Spacefast – for your next…
Jeffrey Zeldman — Published
-
How Can You Be Responsible for Code You Don't Understand, Especially When You Can No Longer Program?
If AI is writing all the code and no one is reviewing it, how the heck can anyone be responsible or accountable for code they not only don’t understand and eventually can never understand? AI's primary purpose is to deskill its operators. The short answer is that programmers become responsible for outcomes…
David Bryant Copeland — Published
-
Emacs live ‘pub trivia’ package from scratch today 2026-11-11 at 14:00 Europe/Athens
I will develop a new package from scratch: pub quiz for Emacs.
Protesilaos Stavrou — Published
-
Candidate Statement for the 2026 W3C TAG Election
Group photo of the W3C TAG in July 2022 with me to the left of Sir Tim Berners-Lee (inventor of the Web and TAG chair emeritus). Photo credit: Dan Appelquist I had the great honor of being elected to the TAG by the W3C membership in 2020 and again in 2022, serving two terms from 2021 to 2025. After a…
Lea Verou — Published
-
Microsoft Fixes Nearly 1,100 Security Vulnerabilities
Microsoft did another four-digit patch drop today, releasing updates to fix almost 1,100 security vulnerabilities in its Windows operating systems and supported software. This month's Patch Tuesday addresses 63 critical flaws -- including a zero-day in Microsoft Outlook -- and comes amid important security…
Brian Krebs — Published
-
Finally, Payment by Bank Transfer Comes to Have I Been Pwned
This is simultaneously the most boring yet exciting blog title I've written in a long time. How you pay for services isn't exactly a sexy topic, but it solves a problem that's been a massive bugbear for a long time.Here's a
Troy Hunt — Published
-
llm-gemini 0.36
Release: llm-gemini 0.36 Gemini 4 Carbon was announced two weeks ago for "a subset of cyber defenders", but today it's available to everyone else. This is Google's best ever Gemini, priced at $2/million input and $10/million output at launch (that's GPT-6.1 Sol / Claude Sonnet 5.5 prices) but scheduled…
Simon Willison — Published
-
My Interop 2027 Picks
Interop 2027 is gathering votes and the deadline is 19 November 2026. For the second year now, Firefox made a page to let you rank your Interop 2027 choices. Which I’ve now done. I narrowed it down to fifteen, though getting there was oddly difficult. It seems the top three…
Adrian Roselli — Published
-
Making a Website in 2026
Pete Millspaugh has a great post over on the Val Town blog where he documents his attempt at making generating the same website across a variety of AI tools. I love the post. Here are a couple of thoughts that come to mind. The Space Is Ripe for Referral Fees Pete decided to make a website for his conference…
Jim Nielsen — Published
-
Just don't lie 2
It's been 5 months since I posted about the Steam AI score idea and its ramifications (#345, #436, #459, #480, #594, #595, #628), and the discourse around AI usage and gaming has progressed enough that I feel confident about how the future will play out. It seems clear to me that the vast majority of…
a327ex — Published
-
Introducing Our Smallest, Most Efficient Model: Muse Ember
Introducing Our Smallest, Most Efficient Model: Muse Ember Meta AI just launched their entry in the Claude Haiku/GPT Luna category: Muse Ember, which they describe as: [...] our smallest and most efficient model designed for complex reasoning execution and the work agents repeat all day: tool calls,…
Simon Willison — Published
-
Quoting Prompting Claude Fable 5.2
Claude Fable 5.2 pays close attention to who owns the code it works on. In Anthropic’s testing on small coding tasks, the model tended to add to the existing structure when the prompt said nothing about ownership or presented the code base as someone else’s, even when that duplicated existing code. When…
Simon Willison — Published
-
Yonkers Rises
Tool: Yonkers Rises I realized I didn't know where Yonkers was, so I looked it up on Google Maps and then, to help embed its location and shape in my head (and to try out Claude Fable 5.2's 3D modeling and animation skills), I prompted Fable 5.2 Medium to: Make a three js animation where yonkers stands…
Simon Willison — Published
-
Weekly Update 529: Kids Social Media Bans (and Everything Else)
The kids-and-social-media discussion is just dumb. It's not the premise of delaying their access until 16, but the inability of those who should know better to grasp where the responsibility for enforcement lies. Here's our PM's explainer after the laws passed
Troy Hunt — Published
-
LinkedIn for AI
My corner of the web was atwitter lately as a few prominent members of the Apple/iOS developer community decided to announce they were spending time on X again; people got mad. And it’s kind of bothering me how people seem to be talking past each other...
Ash Furrow — Published
-
llm-anthropic 0.31
Release: llm-anthropic 0.31 Anthropic released Fable 5.2 and Mythos 5.2 today. Fable 5.2 is currently ranked first on Artificial Analysis. Anthropic say it "solved two open problems in the physics of black holes", so clearly their internal benchmarks have become more ambitious! I've added the new models…
Simon Willison — Published
-
Locating the source of a mysterious beep with Claude
Our house has a box room, full of boxes that we still haven't unpacked from our last move. A couple of weeks ago something in that room started intermittently beeping. The beeps were far enough apart that standing in the room and trying to determine the source of the noise was frustrating, and I really…
Simon Willison — Published
-
lunarpunk
I recently learned about lunarpunk and I can’t stop thinking about it. It’s solarpunk’s nocturnal brethren, cyberpunk’s more utopian twin. I’ve always been a fan of solarpunk ethos and aesthetic. It has this mix of sun-drenched anarchy and verdant optimism. Sustainability, solar panels, solutions for…
Lee Byron — Published — Updated
-
On Receiving Letters
In my beginners guide to writing snail mail, I hand out a few tips for getting started with letter writing as a lovely way of conversing with friends and strangers. I’ve sent 21 letters since then, but the fun doesn’t stop there: receiving a reply is just as exciting. Many people dismiss letter writing…
Wouter Groeneveld — Published
-
The Web Is More Than Enough, by Paul Ford
My comment on The Web Is More Than Enough, by Paul Ford — Hacker News.OK, this comment convinced me to give that a shot. Here's a thing I made in Three.js this morning - a Nudibranch themed Faberge Egg: https://static.simonwillison.net/static/2026/Hidden-Reef-Egg... (77KB) I just asked Claude (Opus 5.5…
Simon Willison — Published
-
Hide your slop PR descriptions behind
Most of the changes I make to my projects these days come in the form of PRs opened for me by Claude Code or Codex. The PR is my unit of work - I use them to bundle commits together, iterating on them until a feature is complete, document decisions and then merge the finished result. Today's coding agents…
Simon Willison — Published
-
Photo Blog Migration
In 2013, when it was still in beta, I signed up for Exposure. This is a web publishing tool for photographers, to organize their work into photo blog posts. It does a lot more than that, especially as they’ve added new features over the years, but I’ve...
Ash Furrow — Published
-
Agency
I’ve been writing more lately, as I work through my feelings about changes to the software development industry. After Cory Doctorow was eviscerated about his use of a local for spellcheck I shut my mouth about them. And I’m tired of that. This post is...
Ash Furrow — Published
-
On the trade-conquest continuum, Western empire, and the political centre
Analysis on strategy with a focus on Western politics that covers geopolitics, history, economics, and insights into human nature.
Protesilaos Stavrou — Published
-
parse_number() as a SQLite extension: C vs Rust
Research: parse_number() as a SQLite extension: C vs Rust I was out walking the dog when I got curious about how easy/difficult it would be to write a SQLite C extension that adds a parse_number() function for turning strings like -$1,234.56 or '12.5%' into numeric values that could be summed and sorted…
Simon Willison — Published
-
RIP, Harvest
I’ve been a self-employed contractor for about a decade now, and I’m bummed about Harvest. Harvest was a time-tracking and invoicing service. You’d track how many hours or weeks you spent on a project, put together an invoice, email it to the client, and close it out when they paid. There was a little…
Kyle Kingsbury — Published
-
Addition By Subtraction
I still think saying no is important. In that vein, here’s something I shipped by removing functionality (and I think my site is better for it). For the longest time on my icon gallery sites, you could view a list of icons in four pixel dimensions: 56×56 128×128 256×256 512×512 Each of these sizes could…
Jim Nielsen — Published
-
Corruption Is A Cost-of-Living Issue: App Store Edition
While I'm not shy about my pro-democracy, anti-authoritarian politics, this blog has kept to a more technical lane, veering into policy only out of necessity. As the scale of the web's setbacks at the hands of proprietary forces became clear, it became urgent to explain them and raise the alarm. But…
Alex Russell — Published
-
EmacsConf 2026 community panel comments I made
Recollection of comments I made during the EmacsConf 2026 community panel.
Protesilaos Stavrou — Published
-
datasette #3046: Don't serve link: rel=next HTTP headers to Firefox for HTML pages
datasette #3046: Don't serve link: rel=next HTTP headers to Firefox for HTML pages I was looking at the Firefox network panel today when I noticed that requests to a Datasette table page were triggering an HTTP prefetch to the next page of rows in that table. This was happening because Datasette pages…
Simon Willison — Published
-
Terry Pratchett's Study
My comment on Terry Pratchett's Study — Hacker News.Terry Pratchett once wrote about the concept of "horizontal wealth". Vertical wealth is where you spend money on rich people stuff - yachts and suchlike. Horizontal wealth is where you spend more money on the things you liked before you got rich: https…
Simon Willison — Published
-
Wealthsimple Native App Rebuild
Last week, at Wealthsimple Presents, my employer announced the project I’ve been working on: a new native app! Here’s a timestamped link. I’m really excited for this! Expect big things. At times, I’ve told an iOS developer that Wealthsimple’s app is...
Ash Furrow — Published
-
About effort and contentment
An entry from my journal in which I comment about the sincerity of effort and the resulting emotional stability.
Protesilaos Stavrou — Published
-
Quoting Nilay Patel
The products aren't good enough to sell people on the costs. You cannot tell people that you have to listen to the whine of a data center in their backyard for AI overviews and some of the most hilarious deep fake slop in history. It's not worth it. It just isn't worth it to anyone. And agents aren't…
Simon Willison — Published
-
We Know 15,579 Websites Are Infected. How Do We Tell Them?
We've identified 15,579 websites that are currently infected with malicious JavaScript and between them, we conservatively estimate that they receive more than 135 million visits every month.We know they're infected, and we have the evidence to back that up, but there's a
Scott Helme — Published
-
*sshole, or when are we finally going to get rid of C?
Original art by Genildo Ronchi. Yet another day, yet another vulnerability in core C code. This one happened due to two different conditions using the same sentinel value: On Unix, a password hash of "*" has meant a locked account since the very early days. Since 2012, musl libc’s crypt function has…
Rain — Published
-
Fançais: Comme d’habitude
J'aime faire des choses avec patience e persistance.
Protesilaos Stavrou — Published
-
Quoting Paul Ford
The web browser is very, very, very powerful software for applications, and the cost of accessing that power is going down seemingly every day. — Paul Ford, The Web Is More Than Enough Tags: browsers, paul-ford, web-development
Simon Willison — Published
-
♫ You Can’t Always Get What You Want by Rolling Stones
♫ You Can’t Always Get What You Want by Rolling StonesBut if you try sometimes, you’ll find you get what you need.
Paul Robert Lloyd — Published
-
Sometimes, Look at the Keys
I wrote a post several years ago called Don’t Look at the Keys. I wrote it after having a minor breakthrough when starting to get back into a regular piano practice. When I was quite young, my first piano teacher used to tell me: “Don’t look at the keys when you’re playing the piano.” At the time I wrote…
Ben Congdon — Published
-
Want to Rent an Internet Address at the White House?
Several staffers at the White House are using computers or mobile devices equipped with residential proxy services that render their internet address available for others to rent, security experts warned today. One of the proxy services is a Russian company whose founder's web hosting business was ground…
Brian Krebs — Published
-
Untitled
10 long months of torturing myself. Enough. Enough now.
Paul Robert Lloyd — Published
-
We can do better than line-buffered output
Buffered output typically comes in two flavors: fully buffered and line buffered. If output goes to a terminal then the implementation automatically selects line buffering, flushing its buffer when a line is completed so that it reaches the user immediately. Otherwise it fully buffers, holding output…
Chris Wellons — Published
-
Français: Pour toi et moi
Un petit note en sujet de communication.
Protesilaos Stavrou — Published
-
“It Gives Great Demo”
There’s that famous video of Steve Jobs explaining why they don’t didn’t make touchscreen MacBooks: We thought about [a touch screen MacBook] years ago. We’ve done tons of user testing on this and it turns out it doesn’t work! Touch surfaces don’t want to be vertical. It gives great demo. But after a…
Jim Nielsen — Published
-
datasette-llm 0.1a10
Release: datasette-llm 0.1a10 Fixes a bug that affected my agent.datasette.io demo site, where the set of available LLM models was not correctly restricted to just those in the configuration. Tags: llm, datasette
Simon Willison — Published
-
Favourites of October 2026
Boo! Happy Halloween. See you next year for another scare. In the meantime, life slogs, and sometimes rushes, on. We’ve had the pleasure to experience the grand opening of the flu season resulting in more sleep deprivation whilst trying to take care of the sick kids. As you can imagine, dodging sickness…
Wouter Groeneveld — Published
-
Voice is Underutilized
Speech is a useful medium for communicating with AI, both as an input/output channel and as back-and-forth. Over 2026 I’ve been increasing the amount of speech I/O and have collected a fair number of use cases. Input Voice is, of course, great for rambling at coding agents. Oftentimes the transactional…
Ben Congdon — Published
-
#1's smell
All attempts in It Follows were based on real encounters I had in real life. Most of them were changed to serve the story better and fit the curse's rules, but I tried to keep them as close to reality as possible. For example, attempt #17, which I believe was the rape, happened in real life up to the…
a327ex — Published
-
datasette-apps 0.3a0
Release: datasette-apps 0.3a0 Datasette Apps adds support for hosting and editing custom HTML applications inside of Datasette. These can be created by hand, but it's easier to create them using LLMs via Datasette Agent. This release improves that integration: Apps can now be tagged in Datasette Agent…
Simon Willison — Published
-
Fortune Telling and Speculative Design
Practical tools for design engineers to explore possible futures through speculative design
Maggie Appleton — Published
-
From European austerity to warmongering
Analysis of the politics of the Euro Area and how those create incentives for Europe to go to war with Russia and other countries.
Protesilaos Stavrou — Published
-
Reply to Emacs questions about configuration, Evil, and more
A detailed response to questions about my Emacs configuration and various preferences thereof.
Protesilaos Stavrou — Published
-
datasette-agent 0.5a0
Release: datasette-agent 0.5a0 This is a significant release of Datasette Agent. The most notable new feature is called the panel - it lets the agent chat open and then sit next to pages from Datasette, for example a table or query page. When combined with datasette-apps this means you can prompt a database…
Simon Willison — Published
-
llm 0.37.1
Release: llm 0.37.1 A bugfix release for LLM, with contributions from Steven Huang, Tao An, Arjan Mossel, and XQ. Tags: llm
Simon Willison — Published
-
AI is destroying my CS degree
My comment on AI is destroying my CS degree — Hacker News.I don't envy educators right now. AI clearly means you need to change how you teach and evaluate students. We are only a few years in though, and it's still extremely unclear what effective teaching with these tools looks like. The worst part…
Simon Willison — Published
-
Qwen 3.8 27B on my laptop can interpret model weights, too
Yesterday's hot paper was Sparks of Weight-Space Programming: LLMs can natively read & write neural network weights by Rikiya Takehi, Jayden Teoh, Alex Zhang, and Omar Khattab. The paper (OK, the authors classify is as a "blog post", but it's paper-shaped) found that frontier models, in particular GPT…
Simon Willison — Published
-
Why this Obscure Audio Codec is a Perfect Fit for the N64
Sorry for the clickbait title. I promise this post delivers: 44100 Hz stereo with near-Opus bitrates using about 4% of the N64’s CPU time. But first, some history: The options for playing and storing audio data on the N64 were dire. The PlayStation could just stream uncompressed redbook audio straight…
Dominic Szablewski — Published
-
Why Review AI-Generated Code?
AI can generate a lot of code quickly. There’s a thought that we can catch its mistakes or other issues by reviewing that code. In theory, this may be true; code review can catch bugs. In practice, it only works if the reviewer knows what to look for, has some context and, well, gives a shit. There's…
David Bryant Copeland — Published
-
I discovered a sound that leaks your exact location (and it's everywhere) - YouTube
I discovered a sound that leaks your exact location (and it's everywhere) - YouTube Genius piece of OSINT by Colsto, who demonstrates how you can take almost imperceptible background noise of planes from a video soundtrack, figure out their Doppler curves, then cross reference them against ADS-B data…
Simon Willison — Published
-
October sponsors-only newsletter
I sent out the October edition of my sponsors-only monthly newsletter. If you are a sponsor (or start a sponsorship now) you can access it here. This month: The October inflection point for vibe game development The vulnerability apocalypse gets hot LLM releases API credits for $100+/month subscriptions…
Simon Willison — Published
-
Interpolative Software
Much of the excitement around AI coding is downstream of the fact that a lot of software is interpolative. This has become especially true as of late, with the release of Opus 5.5, which is, I’d argue, superhumanly good at generating mass amounts of high-quality interpolative software.1 This post is…
Ben Congdon — Published
-
Tech Firms Dismantle Botnet That Turned 1.3M TV Boxes Into Proxies
Google said today it worked with industry partners to dismantle a botnet made up of more than 1.3 million Android TV set-top boxes that ship with malicious software which secretly rents the user's Internet connection out to strangers and conducts advertising fraud. Experts involved in the takedown say…
Brian Krebs — Published
-
Welfare versus warfare considerations in Europe
Essay on the trade-offs that are involved in policy orientations between welfare and warfare.
Protesilaos Stavrou — Published
-
llm 0.37
Release: llm 0.37 There's a lot of stuff in this new release of my LLM CLI tool and Python library, representing around two months of accumulated features and fixes. I added gpt-6.1-sol and gpt-6.1-terra, plus a new llm openai endpoint add command to make it easier to configure additional models that…
Simon Willison — Published
-
Making features generic in CSS
CSS has two new positional alignment keywords as part of CSS Box Alignment Level 3: flow-start and flow-end. These are defined as aliases for the existing flex-start and flex-end keywords. Therefore, in a supporting browser, the following two lines should align flex items to the end of the flex container…
Rachel Andrew — Published
-
The U.S. Census Bureau and “Super Intelligence”
I was reminded today of AI Adoption Rate Trending Down for Large Companies, a chart produced by Apollo Global Management in September 2025, which appeared to show a slowdown in U.S. corporate AI adoption based on numbers collected by the U.S. Census Bureau. At the time I used that chart to demonstrate…
Simon Willison — Published
-
Test and verification technique effectiveness with GPT-6 Astra
When we looked at how well agents used test/verification techniques in August1, we saw that GPT-5.6 Sol generally did what you might call a caricature of various techniques when asked to use a technique or library such as TDD, QuickCheck, Lean 4, etc.; not specifying any particular test method (which…
Dan Luu — Published
-
If in doubt, delete the uv.lock file
I've been getting the occasional confusing Python dependency error since switching over to Python 3.15 and the rule I'm having to remember is: If in doubt, delete the uv.lock file Most of my projects are libraries which don't include a uv.lock file, since it's rude for a library dependency to lock versions…
Simon Willison — Published