Elsewhere

Things we find interesting we think you might too. Grab the RSS feed for your newsreader of choice.

UX Is Your Moat (And You’re Ignoring It) – Eleganthack

December 17, 2025

If you’re building an AI product, your interface isn’t a nice-to-have. It’s your primary competitive advantage. Here’s what that means in practice: Make the first five minutes seamless. Users ...

Read More

How to Run a 90-Minute AI Design Sprint (with prompts)

December 16, 2025

Most teams still run ideation sessions with a whiteboard, a problem statement, and a flurry of post-its. To be honest, I’ve always loved a good Design sprint, especially in person and I hope those d...

Read More

What I learned building an opinionated and minimal coding agent

December 15, 2025

I’ve also built a bunch of agents over the years, of various complexity. For example, Sitegeist, my little browser-use agent, is essentially a coding agent that lives inside the browser. In all ...

Read More

Useful patterns for building HTML tools

December 15, 2025

I’ve started using the term HTML tools to refer to HTML applications that I’ve been building which combine HTML, JavaScript, and CSS in a single file and use them to provide useful functionality. ...

Read More

The /llms.txt file – llms-txt

December 15, 2025

We propose adding a /llms.txt markdown file to websites to provide LLM-friendly content. This file offers brief background information, guidance, and links to detailed markdown files.llms.txt markdown...

Read More

AI and variables: Building more accessible design systems faster

December 15, 2025

When people talk about AI in design, they often picture flashy visuals or generative art. But my own lightbulb moment happened at a less glamorous place: in an effort to solve this accessibility chall...

Read More

A ChatGPT prompt equals about 5.1 seconds of Netflix

December 15, 2025

In June 2025 Sam Altman claimed about ChatGPT that “the average query uses about 0.34 watt-hours”.In March 2020 George Kamiya of the International Energy Agency estimated that “strea...

Read More

Is your tech stack AI ready?

December 15, 2025

We’re at the same inflection point we saw with mobile and cloud, except AI is more sensitive to context quality. Loose contracts, missing examples, and ambiguous guardrails don’t just caus...

Read More

If You’re Going to Vibe Code, Why Not Do It in C?

December 12, 2025

So my question is this: Why vibe code with a language that has human convenience and ergonomics in view? Or to put that another way: Wouldn’t a language designed for vibe coding naturally dispense w...

Read More

AI companies want a new internet — and they think they’ve found the key

December 12, 2025

Over the past 18 months, the largest AI companies in the world have quietly settled on an approach to building the next generation of apps and services — an approach that would allow AI agents from ...

Read More

Migrating Dillo from GitHub

December 12, 2025

However, it has several problems that make it less suitable to develop Dillo anymore. The most annoying problem is that the frontend barely works without JavaScript, so we cannot open issues, pull req...

Read More

Is It a Bubble?

December 12, 2025

Before diving into the subject at hand – and having read a great deal about it in preparation – I want to start with a point of clarification. Everyone asks, “Is there a bubble in AI?” I think...

Read More

How I Shipped 100k LOC in 2 Weeks with Coding Agents

December 11, 2025

When we onboard developers, we give them documentation, coding standards, proven workflows, and collaboration tools. When we “deploy” AI agents, we give them nothing. They start fresh every time. ...

Read More

Horses

December 11, 2025

Engines, steam engines, were invented in 1700.And what followed was 200 years of steady improvement, with engines getting 20% better a decade. For the first 120 years of that steady improvement, horse...

Read More

10 Years of Let’s Encrypt Certificates – Let’s Encrypt

December 11, 2025

On September 14, 2015, our first publicly-trusted certificate went live. We were proud that we had issued a certificate that a significant majority of clients could accept, and had done it using autom...

Read More

Building a Social Media Agent | goose

December 11, 2025

Source: Building a Social Media Agent | goose...

Read More

AI should only run as fast as we can catch up

December 10, 2025

Verification Engineering is the next Context Engineering AI can only reliably run as fast as we check their work. It’s almost like a complexity theory claim. But I believe it needs to be the case to...

Read More

Elicit Machine Learning Reading List

December 10, 2025

The purpose of this curriculum is to help new Elicit employees learn background in machine learning, with a focus on language models. I’ve tried to strike a balance between papers that are relevan...

Read More

Has the cost of building software just dropped 90%?

December 10, 2025

Domain knowledge is the only moat So where does that leave us? Right now there is still enormous value in having a human ‘babysit’ the agent – checking its work, suggesting the appro...

Read More

Prediction: AI will make formal verification go mainstream

December 10, 2025

Much has been said about the effects that AI will have on software development, but there is an angle I haven’t seen talked about: I believe that AI will bring formal verification, which for decades...

Read More

MCPs for Developers Who Think They Don’t Need MCPs | goose

December 10, 2025

MCPs weren’t built just for developers.They’re not just for IDE copilots or code buddies. At Block, we use MCPs across everything, from finance to design to legal to engineering. I gave a ...

Read More

Your Spec Driven Workflow Is Just Waterfall With Extra Steps

December 9, 2025

AI coding tools were supposed to change everything. And they did! But maybe just not how we expected. The first wave was chaos. Vibe coding. Let the AI write whatever it wants and hope for the best. I...

Read More

AI in 2025: gestalt — LessWrong

December 9, 2025

My view: compared to last year, AI is much more impressive but not proportionally more useful. They improved on some things they were explicitly optimised for (coding, vision, OCR, benchmarks), and di...

Read More

llm weights vs the papercuts of corporate

December 9, 2025

We are now one year in where a new category of companies has been founded whereby the majority of the software behind that company was code-generated.From here on out I’m going to call to these comp...

Read More