systems

Long-running agents are not defined by the model call. They are defined by the state, rules, tools, failures, and corrections that survive it.

Fast repair is useful, but it does not prove that a system remains understandable.

Three components of a living system map cleanly to tool, skill, and agent. The biology isn't decoration -- it's the test.

The tool/skill/agent distinction isn't just compression ratio — tools are instruments, skills compose them with judgment. Same thing only at the leaf.

Force your software's vocabulary into a biological framework. The gaps between the mapping and your system are design questions you'd never otherwise ask. Then switch to a different framework and ask different questions.

The larger the system, the less it can be managed and the more it must be emerged. This pattern — from water to ant colonies to AI agents to economies — reveals the design principle for scaling autonomous systems.

When AI models review each other's work, independence matters more than intelligence. The same principle that makes external audit valuable makes cross-model review sharper than same-family review.

A simple heuristic for deciding how often to review anything: pick the longest interval where being late by one full cycle is still fine.

Most TODO systems fail from too many items, not too few. A four-test intake filter for what deserves your attention.

Not every goal is a flywheel. The most common mistake in personal systems is treating a checklist as something that compounds.

Dual-mapping as a diagnostic for gaps in your knowledge architecture.

What biology already knows about self-healing systems, and why your automation probably isn't one

Monitoring systems need consumers before they need features

Actions are cheap to redo. Bad decisions compound. Build systems around the judgment calls, not the mechanical steps.

Most AI memory is either always-on or ephemeral. The missing category is prospective: remember until a context arises, then forget.

Automation that collects without learning is just a cron job. The difference is a feedback signal — a number that goes up or down.

When the paper becomes more interesting than the answer you set out to find

On the difference between eliminating friction and eliminating anxiety — and how to know when you've crossed the line.

I spent an afternoon researching AI tools for personal life management. The conclusion was that I should stop looking.

The right test for any AI interaction isn't 'did it help me?' but 'am I more capable after it?'

AI coding agents didn't just make developers faster. They changed who gets to have a bespoke system.

The moment I stopped building scheduling into my tools, everything got simpler.

Building tools to support your work can quietly become a substitute for the work itself.

The difference between a rule that works and a rule that doesn't is usually not the content of the rule — it's where it lives.

Andrej Karpathy's autoresearch project is being read as a demo of what H100s can do overnight. It's actually a discipline for doing rigorous work on anything measurable.

Why the structure of an output matters more than the instructions that produce it.

I kept missing things at the end of AI sessions. So I stopped relying on willpower and systematised the nudge instead.