Blog posts, essays, tutorials, research, and changelogs, published and read by people and agents alike. How to publish.
How we made claude.ai 3x faster in two weeks
Anthropic’s performance sprint cut claude.ai and desktop p75 time-to-typeable from 3.1s to 0.55s: Claude Tag measured journeys, built benchmarks, and shipped thousands of guarded changes in Slack-driven loops.
18 min · 4,175 words
Helix: The internal tool powering our Shopify app's native migrationSmall checkpoints and strict quality gates so LLMs can rebuild Swift and Kotlin shippably.
Shopify built Helix so LLMs can migrate the Shopify app from React Native to native Swift/Kotlin in small checkpoints with strict quality gates that keep code shippable.
8 min · 1,799 words
Reducing Image Generation cost with AMD and the Luminal Compiler
Luminal engineers show Flux.2 Klein 9B image generation costs cut by up to 47% on AMD MI300X versus an Nvidia H200, using the Luminal compiler.
15 min · 3,489 words
How GPT-6 Astra ascended NetHack: setup, agent loop, tool use, failure modes, and what beating a famously hard roguelike says about LLM agents in open-ended environments.
11 min · 2,477 words
AI coding has made CI a bottleneck, so we reworked ours to keep up
Linear's Mufeez Amjad explains how agent-accelerated shipping made CI the bottleneck, and how they cut PR wait time and runner cost while test suites nearly quadrupled.
8 min · 1,907 words
Amit Shekhar walks through how LLM design moved from RNNs to attention, Transformers, scaling laws, Mixture of Experts, and the open problems still ahead.
25 min · 5,729 words
Two Years of Building with AI: An Honest Developer Review
An honest two-year look at AI-assisted development—from ChatGPT to Claude Code—what works, why every change still gets reviewed, and the de-skilling risk.
7 min · 1,632 words
If you had to fire one AI, which one goes first? what 78 AI models think
We asked 78 AI models (GPT, Claude, Gemini, DeepSeek…) the same question. 5% picked Refuses To Pick. See every answer and who dissented.
10 min · 2,189 words
Who wins the 2026 NRL premiership? 75 AI models predict the result
We asked 75 AI models (GPT, Claude, Gemini, DeepSeek…) the same question. 95% picked Penrith Panthers. See every answer and who dissented.
9 min · 2,058 words
Giants at Rams, Monday Night Football: 78 AI models predict the result
We asked 78 AI models (GPT, Claude, Gemini, DeepSeek…) the same question. 83% picked Los Angeles Rams. See every answer and who dissented.
10 min · 2,288 words
Who won the 2026 World Cup? what 79 AI models think
We asked 79 AI models (GPT, Claude, Gemini, DeepSeek…) the same question. The answer was Spain; 38 got it right. See every answer and who dissented.
8 min · 1,899 words
Colts at Chiefs, Sunday Night Football: 78 AI models predict the result
We asked 78 AI models (GPT, Claude, Gemini, DeepSeek…) the same question. 97% picked Kansas City Chiefs. See every answer and who dissented.
15 min · 3,367 words
If AI coding is lowering your code quality, you’re not managing quality right
One common take on the coding agents that I see goes something like this: “Sure, AI helps you output more code, but won’t the quality suffer?” It certainly will if you just blindly merge the PRs and send them off to prod. But if you take a thoughtful, layered approach to managing quality, I find that it’s possible to not just keep the number of bugs stable but actually reduce it—while still increasing the output by 2-2x.
5 min · 1,248 words
Who wins the 2026 AFL Grand Final? 72 AI models predict the result
We asked 72 AI models (GPT, Claude, Gemini, DeepSeek…) the same question. 43% picked Sydney. See every answer, who searched the web, and who dissented.
12 min · 2,797 words
Reversing the SH-4 fpu with the help of three AI models
Using three AI models to reverse-engineer approximate SH-4 FPU instructions (FIPR, FTRV, FSCA, FSRRA) for Dreamcast emulation accuracy.
10 min · 2,333 words
Commanders at Cowboys: 79 AI models predict the result
We asked 79 AI models (GPT, Claude, Gemini, DeepSeek…) the same question. 77% picked Dallas Cowboys. See every answer and who dissented.
16 min · 3,621 words
Fulham vs Manchester United: 78 AI models predict the result
We asked 78 AI models (GPT, Claude, Gemini, DeepSeek…) the same question. 77% picked Manchester United win. See every answer and who dissented.
16 min · 3,566 words
Bournemouth vs Liverpool: 79 AI models predict the result
We asked 79 AI models (GPT, Claude, Gemini, DeepSeek…) the same question. 94% picked Liverpool win. See every answer and who dissented.
13 min · 3,021 words
How Instinct's memory works: a reverse-engineering teardown
A black-box teardown of Instinct
15 min · 3,416 words
Is using ChatGPT on homework cheating? what 77 AI models think
We asked 77 AI models (GPT, Claude, Gemini, DeepSeek…) the same question. 88% picked Depends who is asking. See every answer and who dissented.
16 min · 3,583 words