LLMs work best when the user defines their acceptance criteria first
One of the simplest tests you can run on a database:
Every blog post that took off on Hacker News, ranked by the votes of its best submission. 5,939 posts.
One of the simplest tests you can run on a database:
Philosophy - Sciences - Geekery - Art - Life - Coaching - Fun < Simplify Everything
I’m coming down from spending a few days at Usenix Security, right here in my hometown of Baltimore. This means that my days have been taken up with two kinds of conversation: first, explaini…
Expensive lessons
Today, we’re excited to announce the Preview of Containers in Firefox version 153, which lets you keep separate parts of your online life (work, shopping
Why I believe the Model Context Protocol (MCP) is a better architectural pattern than the emerging “Skills” trend for LLM tool integration.
A more circular economy is not only important for the environment. It can also strengthen consumer rights and improve societal resilience. In this report, we show how consumer policy can make circular choices easier, safer and more attractive for consumers.
If you're giving me e-paper, I'm going to make an e-printer.
When the Apollo astronauts returned from the Moon, the dust that clung to their spacesuits made their throats sore and their eyes water. Lunar dust is made of sharp, abrasive and nasty particles, but how toxic is it for humans?
You know what's funnier than 24?
A bungled Assetnote scan
One of the questions of the 2026 acx prediction contest is whether Nvidia’s stock price will close below $100 on any day in 2026. At the time of writing, it trades at $184 and a bit, so going down to $100 would be a near halving of the stock value of the highest valued company in the world.
Working with lots of changes in parallel on git can be painful. You end up juggling branches and commits, and running scary rebase -i commands that can leave your tree in a half-broken state if you so …
Customize the look and feel of tmux
Railway experienced a platform-wide disruption after Google Cloud incorrectly suspended our account, temporarily taking down all GCP-hosted infrastructure.
Nothing on the internet lasts forever. But Disney’s 10-year mismanagement of FiveThirtyEight is its own story.
I love going on wilderness adventures. I am rarely happier than when I am far off into the mountains without a soul in sight. As a result, I have spent a lot of time learning how to safely explore and navigate when I’m away from civilization. The most important habit I’ve found for not getting lost is to be very…
Table of Contents Intro Contest in short Problem intro Why this problem is auto-research-able Learning Enough to Ask Better Questions (Optional) Math f...
This case involves Apple’s handling of user-uploaded files hosted in private iCloud storage. Instead of adopting PhotoDNA to scan hosted files for CSAM, Apple created its own proprietary alternative, NeuralHash, which apparently wasn’t as good. So Apple U-turned on its...
Some thoughts on Astra and newfangled long-horizon models.
A technical deep dive into the Codex agent loop, explaining how Codex CLI orchestrates models, tools, prompts, and performance using the Responses API.
We knew this day would come. Some of us have known for decades, have been writing and pontificating about this since Ken Jennings lost at Jeopardy and Kasparov lost at chess. The writing was on the wall, and now the writing is everywhere. Literally. Artificial Intelligence is writing about as well as humans — at […]
Imagine, just for a moment, that the Government wanted to keep a record of everyone's sexuality. They need to know this detailed demographic data because it will be highly useful in civic planning. It will help them work out what provision needs to be made for sexual health services, how many children are likely to be…
Core PHP engine flaws enable remote code execution and Heartbleed-style memory disclosure across the web.
I have been interested in machine-assisted ways to do and teach mathematics from as far back as 1999, when I started coding several applets in Java 1.0, both for my complex analysis and linear alge…
In early February 2011 Egypt was in the middle of a political revolution. One morning, everyone's phones suddenly pinged with an alert. The Armed Forces asks Egypt's honest and loyal men to confront the traitors and criminals and protect our people and honour and our precious Egypt. A series of messages arrived all…
Lawyers should be able to read a statute as it stood on any date and see which law wrote each phrase. A history of nine titles of the US Code, built by replaying every amendment, as the example.
An overview of Google’s eighth generation TPUs, built for the agentic era.
A seven-month-old arbitrary code execution vulnerability remains present in Cursor, leaving 1 million daily users to rely on public disclosure after months of unsuccessful attempts to obtain remediation updates.