Read

In case you haven’t read the last 18 years of gear posts, my goal is to have the best possible gear with the most wide ranging capability in the smallest form factor possible.

AI is beginning to move from code completion toward engineering participation.

Modern LLMs are extraordinarily powerful distribution followers. They learn patterns across vast bodies of existing work and generate solutions near the center of that collective experience.

AI coding is therefore best understood as another step forward in automation. It dramatically lowers the cost of implementation, translation, and refinement. As those costs fall, the scarce resource shifts upward: deciding what systems should exist and how software should evolve.

As writing code is becoming easier, designing software becomes more important than ever. As custom software becomes cheaper to create, the real challenge becomes choosing the right problems and managing the resulting complexity. I also see big open questions about who is going to maintain all this software.

The limiting factor is no longer whether software can be built, but deciding what should be built and how to manage the complexity that follows. AI amplifies both good and bad structure, so we can expect to see poorly managed code scale into incomprehensible nightmares.

We should not compete with automation at mechanical work.