architecture.
9 writings found
Latest Archives
The Map That Became the Territory: AI, Specifications, and What We Mean When We Say 'I Built This'
On AI agents, observability, bespoke software, and the uncomfortable question of who actually built what when LLMs generate our code.
The Governor Is Gone: AI, Cognitive Limits, and the Mess We're Making
AI removed the natural ceiling on how much we can produce. Now the only limit is cognitive endurance, and most of us are blowing past it.
The Supervisory Programmer: Managing Agents, Context Switching, and Cognitive Debt
Senior devs thrive with LLMs while mid-level careers face challenges. But can we really manage multiple AI agents without burning out?
The Three-Tier Developer Split: How LLMs Are Reshaping Software Teams
Junior devs gain mentors, seniors gain leverage, but mid-level developers face an existential challenge as AI agents reshape programming careers.
Context Engineering: The New Frontier in AI-Assisted Development
As coding agents evolve, context engineering becomes crucial. Here's what developers need to know about rules, skills, and the art of prompt curation.
The Typography Trap: Why Bold Text is Losing Its Power
LLMs have spread the overuse of bold text everywhere. Here's why less emphasis creates more impact and how to write text that actually guides readers.
The Bold Problem: How Typography Lost Its Power
Why excessive bold text in technical writing defeats its own purpose, and what LLMs have to do with spreading this self-defeating practice.
The Code Quality Problem AI Agents Won't Tell You About
AI coding agents generate working code fast, but what about internal quality? A real experiment reveals subtle debt patterns that compound over time.
AI Coding Agents Are Fast, But They Write Like Junior Developers
I spent months testing AI agents on a real codebase. They shipped features quickly, but the code quality tells a different story about sustainable development.