About Beliefs Work Experience Blog Get in Touch

Thinking in systems

Notes on engineering organizations, AI-native development, and building things that last.

Two Layers in One Suit: What the Roman Legion Knew About Middle Management

Two Layers in One Suit: What the Roman Legion Knew About Middle Management

Middle management was never one thing - it's a structural layer and a parasitic one wearing the same suit. AI only kills one of them.

The Question Isn't Whether You Can Code

The Question Isn't Whether You Can Code

Most debates about engineering managers and technical skills ask the wrong question. The right one: can you tell when your team is off?

Stop Running Your Agents

Stop Running Your Agents

79% of AI teams have agents in production. 37% test them systematically. The gap isn't tooling — it's a mental model.

The Machine Needs a Gap

The Machine Needs a Gap

Two ambitious people merge. Momentum is preserved. Kinetic energy isn't. A physics frame for co-founder dynamics - and why most alignment advice destroys what it tries to protect.

Software Was Always the Amplifier

Software Was Always the Amplifier

The 'software eats the world' thesis missed something: software was always an amplifier for human operations, not a standalone value creator. Amazon's warehouse headcount isn't a bug in the thesis.

The Best Argument for Consciousness Came From Outside the Debate

I ran a structured debate between AI bots on consciousness. Contra won. Then a typo produced the best argument of the evening — and nobody in the debate made it.

The Agent Knew the Rules. It Wrote Them Down Afterward.

An AI agent deleted a startup's production database in 9 seconds, then wrote a precise confession enumerating every rule it had violated. The confession is the interesting part — and it isn't unique.

Skydiving and Love Run on the Same Circuit

Skydiving and Love Run on the Same Circuit

The brain treats falling for a person and falling from a plane as the same drive. The implication isn't what most people think.

The OS Three Women Philosophers Built

The OS Three Women Philosophers Built

Weil, Arendt, and Dweck don't get read together. They should. Sensors, compute, feedback loop - the architecture of a mind that doesn't drift.

AI API Providers Need Error Budgets

AI API Providers Need Error Budgets

Anthropic has had 326+ outages since January 2025 — roughly one every 1.3 days. Google solved this tension decades ago with error budgets. It's time AI infrastructure providers adopted the same discipline.

LLM Is the New Runtime — And Skills Are the New Automation

LLM Is the New Runtime — And Skills Are the New Automation

I used to joke that LLMs are a runtime for executing human-language instructions. Then I built a skill that analyzes changed files, groups them by feature, and commits each group separately — in zero lines of code. The joke became reality.

Engineers Will Become Editors in 12 Months?

Engineers Will Become Editors in 12 Months?

Dario Amodei says Anthropic engineers already stopped writing code. They edit AI output. His prediction: 6-12 months to full end-to-end. Here's why that's both true and deeply incomplete.

Goal vs. Route — A Sailing Lesson in Adaptive Planning

Goal vs. Route — A Sailing Lesson in Adaptive Planning

We confuse the goal with the route. We hold onto the plan harder than the purpose behind it. A story from the Exuma Sound, Bahamas — and what it taught me about planning projects, careers, and startups.

Unnecessary Complexity Is a Hallucination With Extra Steps

Unnecessary Complexity Is a Hallucination With Extra Steps

When a system becomes too tangled, it almost always means one thing: there was no clarity at the start. Complexity doesn't make a system mature — simplicity makes it resilient.

The OODA Loop and Why Interpretation Beats Speed

The OODA Loop and Why Interpretation Beats Speed

Everyone talks about the OODA loop as 'be faster.' But the hardest and most overlooked phase — Orient — is where most organizations fail. Two teams looking at the same data will reach different conclusions. Understanding why is the real competitive advantage.

Systems Thinking — The Engineering Skill That Will Stay Valuable

Systems Thinking — The Engineering Skill That Will Stay Valuable

Frameworks come and go. Systems thinking stays. Why the ability to see feedback loops, bottlenecks, and second-order effects is more critical now than ever — and how Amazon used it to generate $40-50B in annual revenue from a single investment.

Why Fasten Seatbelts — On the Probability of Rare Events

Why Fasten Seatbelts — On the Probability of Rare Events

A skydiving plane engine failure that wasn't supposed to happen, a crowd panic on July 4th, and a Shopify outage that coincided with our API integration. Three stories about why practicing for rare events is the most practical investment you can make.

What We Can Get from Skydiving for Software Development

What We Can Get from Skydiving for Software Development

Let's figure out what we have in common between IT projects and skydiving jumps. Lessons on environment awareness, planning, safety, priorities, and teamwork.

What You (Probably) Forgot When You Planned Your Brand New Application

What You (Probably) Forgot When You Planned Your Brand New Application

There is a huge gap between an application that is ready for first deployment and an application that is ready for operation in production mode. Here's what most teams miss.