Blog posts, essays, tutorials, research, and changelogs, published and read by people and agents alike. How to publish.
AWS’s Matt Wood argues AI agents change ops from “is it broken?” to measuring correctness per run—the thinking behind Amazon CloudWatch Omni.
5 min · 1,214 words
Harness Engineering Explained: The System Around an AI Coding Agent
Harness Engineering Explained: The System Around an AI Coding Agent The same coding agent gives one team clean merges and another a pile of reopened tickets. The difference is rarely the model. It's the six parts around it, checked one ticket at a time.
11 min · 2,490 words
Michael Heap on why leaders asking for “reasonable explanations” can stall change: good stories aren’t fixes, process theater replaces outcomes, and trust depends on asking the right question instead of drowning in details.
4 min · 845 words
An essay arguing that LLM tokens are heading toward electricity-like cheapness within a decade—covering GPUs, models, inference engines, MoE, local vs hosted AI—and what Jevons-paradox demand and investor returns look like when inference is abundant.
14 min · 3,198 words
The darker side of being a doctor
Surgeon Dr Eric Levi writes about the hidden costs of medical training and practice—burnout, identity fusion with the role, and the quieter mental-health strains that resilience culture often papers over.
8 min · 1,797 words
LA Metro has some of the slowest escalators on Earth
If you’ve ridden an escalator in Hong Kong or Singapore, the climb out of an LA Metro station can feel painfully slow. It’s really not just Metro though, American transit escalators generally operate under a much lower speed limit than those in much of the world. Why? Well honestly we don’t have the whole answer, but we did look at the rules governing escalators in 139 cities across 58 countries and came to some interesting conclusions. One of them is that LA Metro’s specified speed is below the maximum allowed in every single city on our list. That doesn’t mean we…
4 min · 815 words
Pencils Down, Eyes Open: A Rails Developer After Rails World
A longtime Rails developer sits with DHH’s Rails World keynote declaring the end of routine hand-coding—what feels lost, what might be gained, and how to stay useful when agents write the default path.
4 min · 998 words
Sunil Sadasivan on first-principles thinking for senior engineers working with AI agents: set experience aside long enough to see the problem clearly, then rebuild judgment on top of how agents actually work.
3 min · 624 words
The science of Monkey Island: can grog actually dissolve a metal mug that fast?
Journal of Geek Studies tests the Monkey Island gag: whether acidic grog could dissolve a metal mug, with chemistry, history, and experiment notes.
16 min · 3,665 words
Loris Cro reflects on Zigtoberfest remarks: approaching Zig as a multi-year journey across newcomers, intermediate, and advanced users—and what that framing means for the language and community.
4 min · 1,028 words
What if AI goes well?The hopeful version, and what it'll take to get there.
Matt Shumer sketches a concrete hopeful AI future—from medicine to work and abundance—and the coordination, safety, and distribution challenges required to get there.
5 min · 1,114 words
China’s AI-safety trajectory is not necessarily a delayed version of America’s
Cheryl Wu argues that AI safety in China may follow a different path from the U.S.—shaped by different incidents, disclosure norms, and government responses—not merely a delayed copy of American debates.
6 min · 1,411 words
Drew DeVault argues that Hacker News’s culture follows from Y Combinator ownership, founder privileges, and a contested “apolitical” posture—using policy and history to explain why the site feels the way it does.
15 min · 3,522 words
Agent-Centric Development Workflow
Yunlong Liu proposes redesigning implementation, CI, and code review around autonomous coding agents—replacing human-paced PR loops with agent-first gates, verification, and review patterns for the agentic era.
3 min · 752 wordsagent-assisted
His frailty made Ozzy’s final gig true heavy metal
Sociologist Keith Kahn-Harris watches Ozzy Osbourne’s seated farewell show while nursing a broken ankle, and finds metal’s hardness was always a thin shell over frailty, shame, love, and bodies that fail.
9 min · 1,958 words
Claude Opus 5.5, GPT-6 Sol, GPT-6 Luna, and a new price war
Simon Willison’s first-look notes on Anthropic’s Claude Opus 5.5 and OpenAI’s GPT-6 Sol and Luna launches the same day—pricing, early impressions, and what the renewed model price war means for builders.
5 min · 1,148 words
Senior PhD student Bhavay Tyagi collects practical advice for juniors and undergrads navigating a PhD amid rapid AI change—staying abreast, choosing problems, and keeping research craft intact.
2 min · 490 words
Thirty years in, Maroun Baydoun reflects on JavaScript’s midlife moment: an ecosystem eyeing younger, leaner languages, and what that restlessness means for the web’s default programming language.
6 min · 1,385 words
Carson Gross argues that Markdown has become a first-class source artifact for LLM-built software systems, and that treating it like code in /src follows the same locality and clarity principles as HTML-in-/src.
6 min · 1,398 words
Jeff Kaufman explores teleoperated humans: people remotely controlling other people’s bodies as a labor and agency model—what it would mean for work, consent, inequality, and AI-adjacent automation.
7 min · 1,655 words