software-development.
7 writings found
Latest Archives
When Agents Write Code, We Judge It: The Verification Economy
As LLMs generate code at scale, our job shifts from writing to verifying. What does this mean for how we organize teams and think about programming?
Tests Are the Real Safety Net: Why Your AI Specs Need Executable Validation
Writing specs for LLMs is trendy. But without automated tests, you're flying blind. Here's why the spec document isn't your safety net.
The Apprentice Gap: Why Watching AI Code Matters More Than Ever
As AI agents automate more development work, we're creating a generation gap where juniors never learn the fundamentals. The ralph loop offers a solution.
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 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 Dark Factory: Building Software Without Ever Looking at the Code
StrongDM's AI team ships production software written entirely by agents, using Digital Twin Universes and holdout scenarios instead of human code review.
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.