Agile’s 10th principle says to maximize the amount of work not done. It was functionally lost for two decades. Nano unicorns rediscovered it through necessity. Established organizations can apply it to cut OpEx without layoffs.

Every PKM methodology is an assembly of principles designed to solve a specific information constraint. There is no best system. There are only bricks. Build your own.

The tension between enterprise security and the mandate to innovate with AI isn’t new, but AI has compressed it from a manageable chronic condition into an acute crisis where either side losing can kill the company. The problem isn’t the people. It’s the structure.

AI isn’t taking your job. Incompetent leaders using AI as a cover story for cost-cutting they’d do anyway might. And that’s actually good news.

In the late 1980s, a former trial lawyer named Denise Shekerjian read a newspaper article about the MacArthur Fellowship. The “genius grant,” people called it. It came with a mysterious phone call, a generous six-figure award paid with no strings attached, and the kind of cultural recognition that changes a life.

Shekerjian was not interested in the money or the prestige. She was interested in the people. She wanted to know what made them what they were.

We built gravitational-wave detectors to watch black holes collide. We accidentally turned them into the most sensitive dark matter detector ever built. And in 2019, one of them hiccuped.

AI-generated PRs are overwhelming open source maintainers. A solution already exists in the AGENTS.md convention. So why won’t they use it?

Everyone building multi-agent systems assumes coordination needs a new infrastructure layer. The Hermes Kanban Swarm proves the right abstraction was on your desk the whole time.

Before Twitter, before Blogger, before any of the formats we now call social media, there was finger: the protocol that turned .plan files into the web’s first public status updates. It worked for exactly as long as the population stayed small enough to trust.

How to serve Qwen3.6-35B-A3B, a Mixture-of-Experts model with 3B active parameters, on an RTX 5070 Ti using llama.cpp. Full config, performance numbers, and the flags that make it fit.