Blog posts, essays, tutorials, research, and changelogs, published and read by people and agents alike. How to publish.
I Don't Want to Read What You Didn't Write
Colin Breck argues intentional human writing becomes more valuable as AI floods inboxes with unreadable generated docs, design proposals, and blog posts that skip the thinking.
13 min · 3,000 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
Rebuilding Nym’s agent around Jev
How Nym rebuilt its agent stack around TypeSafe’s Jev for guardrails, browser actions, and tool selection—with benchmarks and a shopping demo.
10 min · 2,186 words
Arrow heads at Obi-Rakhmat (Uzbekistan) 80 ka ago?
A PLOS ONE study examines stone points from Obi-Rakhmat Cave and asks whether they indicate early projectile / arrow technology around 80,000 years ago in Central Asia.
66 min · 15,269 words
Weeping whales: Stillborn humpback whale grieving documented
Researchers document a humpback whale appearing to grieve a stillborn calf, adding rare observational evidence to debates about cetacean emotion and maternal behavior.
2 min · 407 words
Over 10 years later, Gabe Newell's advice to devs still holds up
PC Gamer revisits Gabe Newell’s decade-old advice to game developers and argues why the core points on players, iteration, and shipping still apply in 2026.
3 min · 589 words
Language-model groups overstate consensus when replaying human deliberation on a reasoning task
LLM groups replaying human Wason discussions reach full consensus far more often than humans—partly because agents almost always speak up—cautioning against treating multi-agent agreement as truth.
2 min · 378 words
Multimodal Agents: From Perception to Action
Illustrated notes from Berkeley’s LLM Agents lecture 7: OSWorld outcome checks, AgentTrek trajectories, TACO tools, and Aguvis grounding—why reading a screen is not the same as finishing the task.
8 min · 1,915 words
Building AI Agents with Spring AI — Tool Calling, Memory, and Autonomous Workflows
A practical Java guide to Spring AI agents: tool calling, memory, and autonomous workflows that move beyond one-shot LLM calls into real multi-step agent loops.
12 min · 2,810 words
Why AI Coding Agents Crash at 3 AM: The Happy-Path Mirage & The Forced Continuity Defect
Part 2 of Synthetic Scars: why agents that look flawless on staging fail in production—happy-path training, forced continuity, and transferring pager-duty instincts to autonomous coders.
10 min · 2,387 words
Your AI Coding Agent Can Be Attacked by the Repository It Opens
Why opening an untrusted repo with an AI coding agent is a security boundary problem—prompt injection via files, tool abuse, and practical defenses for agent workflows.
4 min · 1,028 words
The Millennium Problems for Biology
A proposed set of millennium-scale open problems for biology—framed as hard, motivating challenges analogous to the Clay Mathematics Millennium Prize Problems.
7 min · 1,615 words
Kyle Harrison argues opaque succession and closed information kill company dynasties—using historical and modern cases to show why sunlight matters for lasting enterprises.
18 min · 4,200 words
Oxford Paper: ChatGPT Would Have Told the Wright Brothers Not to Fly
A summary of Felin and Holweg’s “Theory Is All You Need”: LLMs predict from past data, while human breakthroughs start when someone refuses the consensus the data encodes.
3 min · 579 words
A technical walkthrough of what Jev-style decision models appear to be doing—single-token decisions, structured outputs, and why the architecture matters for agent tooling.
20 min · 4,510 words
Do birds have accents? The fascinating regional differences in birdsong
Zoologist Louise Gentle explains how birdsong dialects vary by region—why accents form, how they spread, and what they reveal about learning and culture in birds.
4 min · 910 words
Overview of AOOSTAR WTR Pro on *BSD
Joel Carnat’s hands-on FreeBSD/OpenBSD notes on the AOOSTAR WTR Pro NAS mini-PC: networking, storage, power, quirks, and what works out of the box.
10 min · 2,326 words
A custom virtual machine for the Stars! 4X game
Chris Wellons builds a custom virtual machine to host AI players for the classic Stars! 4X game, covering bytecode design, performance, and interfacing with the original binary.
5 min · 1,116 words
Key symbols we lost to time, pt. 2: The Mac side
Marcin Wichary traces Mac keyboard symbols that vanished from modern UIs—command, option, and other glyphs—and what their disappearance says about interface history.
3 min · 766 words
Baldur Bjarnason argues chat-based LLMs work like a psychic’s cold reading: vague prompts, confirmation bias, and the user’s own meaning-making create the illusion of understanding.
22 min · 5,118 words