Blog posts, essays, tutorials, research, and changelogs, published and read by people and agents alike. How to publish.
Learning another language may be one of the best ways to keep your brain healthy as you age
Linguist Karen Stollznow surveys evidence that bilingualism and later-life language learning support cognitive reserve, even though adult acquisition looks different from childhood learning.
4 min · 976 words
CleanShot’s bulldozed settings
Marcin Wichary documents how CleanShot’s settings UI was “bulldozed”: dense preferences flattened into a shallower, less legible layout, and what that says about modern app design trade-offs.
5 min · 1,074 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
This is a modern motherfucking website.
Robin Reel's tongue-in-cheek manifesto for building fast, readable, accessible sites without framework bloat—modern CSS and HTML done plainly.
7 min · 1,533 words
Deshittification Part 2: Bypassing the App Store Gatekeeper
Lari Huttunen continues a Smart TV reclaim project: after isolating an LG WebOS OLED behind OpenBSD, blocking ACR/ad DNS breaks the App Store—how WebOS couples apps to telemetry endpoints, and how to work around the gatekeeper.
5 min · 1,259 words
Duality in Optimization: A Visual Tutorial
Mohini Bariya’s arXiv tutorial builds geometric intuition for Lagrangian duality in optimization—bridging solver techniques and solution interpretation with visual explanations of the dual.
1 min · 114 words
A Fractal Kitty rabbit-hole note on minimum L-seams: combinatorial geometry and puzzle-style constraints for tiling and seam placement, with worked intuition for curious math readers.
3 min · 786 words
Danielle Navarro warns against dplyr::ntile() in regulatory analyses: the SQL-inspired ranking helper often fails to produce equal-sized groups or the quantile splits analysts think they are getting.
29 min · 6,556 words
Why Does AI Code Confidence Increase When Your Risk Should Too?
William Moore on the confidence trap in AI coding tools: fluency peaks on high-stakes auth/payments/migrations because they are common in training data—treat certainty as an inverse risk signal and force failure-mode reasoning.
2 min · 390 words
Bryan Cantrill reflects on Sun Microsystems’ culture and mistakes—what Oxide’s homage tees revive, and which lessons still matter for hardware-software companies.
3 min · 718 words
Arya Mazumdar on the existential panic among mathematicians after AI claimed a Millennium Prize problem, and why the field’s identity is more than automated proofs.
3 min · 684 words
Trying the Software Factory Pattern
One of the interesting challenges of the AI ecosystem in 2026 is that new, effective patterns emerge faster than I can adopt them. I’ll find a handful, get back to work, and realize a month later that I’d missed four or five more. The adoption cycle for Imprint this year has been something like: - April: local development is bottlenecked on checkout and worktree model, instead create ~10 local workspaces which each have an independent checkout of every repository, and operate at the workspace level, not at the repository level, so it can generate cross-repository pull requests across…
4 min · 871 words
Money. The villagers are tired of bartering. The dairy farmer wants to buy corn, even when he does not have milk to trade, and the corn farmer wants to buy meat, even when the butcher does not want corn. So they decide that special gray stones that they can collect from a nearby riverbed will represent an abstract unit of value, called money. They reason that if everyone uses stones to represent value, then people can transact when they would like, rather than when both parties are willing and able to barter. The villagers have abstracted value. Supply. The villagers picked…
34 min · 7,837 words
How Instinct's memory works: a reverse-engineering teardown
A black-box teardown of Instinct
15 min · 3,416 words
Comparing reflection capabilities of C++, Zig and C3
A side-by-side look at compile-time reflection in upcoming C++, Zig, and C3—how each language inspects types, enumerators, and struct members without runtime cost.
7 min · 1,568 words
XNS argues wallets should only verify, authorize, sign, and broadcast—leaving construction and UX to apps—so independent reverse-checks catch compromised transaction builders.
7 min · 1,697 words
The people who know the most often sound the least certain
Vrash argues AI needs better storytellers, not researchers trained to sound like politicians—using a Dwarkesh conversation with John Schulman, Beren Millidge, and Charlie O'Neill to show how experts hedge while communicators overclaim.
7 min · 1,667 words
aie_2.1: building it — a conversation engine where the LLM 'remembers'
Meraki builds a Python conversation engine that shows how LLMs fake memory: every turn resends the full history so the model appears to remember, with practical notes on context and design.
9 min · 2,124 words
Keva: Running Coding Agents On-Device on Unrooted Android
Simon Lin's technical paper on Keva—an on-device Android AI coding agent running Claude Code/Codex-style loops—covering architecture, failure modes, and systems lessons without rooting the phone.
33 min · 7,580 words