Ai

Back in January I argued that AI parallelism turns clean architecture into a forcing function — coupling now has an immediate cost in blocked parallel work. After three more posts living inside this workflow, I want to come back to that argument and say what I think I underestimated. The economic shift is bigger than parallelism. AI has quietly collapsed a whole stack of tradeoffs that software engineering treated as fundamental, and the implications run further than “you can run more agents.” ...

The previous post was about when to go up a level. This one is about the operational layer underneath that decision: which model to use for which kind of work, and the harder discipline that makes the whole thing actually work — being willing to throw away expensive output. The two topics are connected. If you’re not willing to discard, your model choices don’t matter, because you’ll end up patching whatever the cheapest model produced regardless of how wrong its foundation was. ...

In the first post I argued that responsibility in AI-assisted development isn’t line-level review — it’s strategic oversight at the right altitude. This post is about what that means in practice. Specifically: how to recognize when the right move is to stop pushing at the current level and step up a layer. This is the single most useful pattern I’ve found, and it shows up at every scale. The Pattern Whenever something isn’t working — a bug AI keeps failing to fix, a feature it keeps implementing wrongly, a plan that keeps generating awkward code — the wrong response is to push harder at the same level. The right response is almost always to go up one. ...

A few months ago I wrote a post arguing that AI parallelism would force developers to take clean architecture seriously, because coupling now has an immediate cost in blocked parallel work. I still think that’s true. But I want to start this series with a confession: the elaborate workflow I built on top of that insight is mostly not what I actually do anymore. This isn’t a retraction. The economic argument holds. What I got wrong was the workflow that I thought followed from it. ...

There’s a book I’ve wanted to share with the world for years. Sha’ar HaYichud (שַׁעַר הַיִּחוּד — “The Gate of Unity”), written by the Mitteler Rebbe, Rabbi DovBer Schneuri, is a foundational Chassidic text of remarkable depth. Years ago I went through the entire book and divided it into labeled sections and subsections — a structural layer I felt would make it significantly more accessible to readers. That work sat in my notes, half-forgotten, until a few weeks ago when something clicked and I decided to finally publish it. ...

A Simple Question That Reveals Everything Do any current Angry Birds games have the same simple elegance as the original? The answer is no. And the reason why reveals something far more disturbing than the decline of a mobile game franchise. The Death of Premium Mobile Gaming In 2009, Angry Birds was a revelation. You paid $0.99 once, and you owned a complete, polished game. Pure physics puzzles that scaled through clever level design. No ads. No energy systems. No daily login bonuses. No loot boxes. ...

AI Parallelism: The New Forcing Function for Clean Architecture For decades, clean architecture has been a hard sell. Not because developers don’t understand its value—they do. The problem is incentive structure. Good architecture is a deferred investment. You pay the cost now (more files, more interfaces, more ceremony) for benefits that materialize later: maintainability, testability, onboarding speed. But “later” is abstract. The immediate reward for stuffing logic into one class was real—less context switching, faster to write, everything in view. ...

Every compulsive behavior I’d ever heard warned about had one thing in common: it was obviously a waste. Junk food, endless scrolling, the worse stuff a person can lose an evening to — the harm announces itself. You know what you’re doing while you do it. The internal argument is short because the verdict is never in question. You’re not building anything. You’re feeding a loop. The recognition that it’s destructive is what eventually lets you stop, or never start. ...