The Autopilot Didn't Make Pilots Obsolete
The training didn't become pointless. It became the reason you can tell when the machine is wrong.
select * from random_thoughts
Strong opinions and practical insights on leading engineering teams, building better software, and navigating the ever-changing tech landscape.
Live Last read · last published · next check
Latest posts
We Need a Config Standard for AI Coding Tools. We Won't Get One.
A rant about lock-in, dead frameworks, and the enshittification of the agentic tooling landscape
LLMs vs. Human Engineers: Who Really Understands the Code?
What separates a software engineer from an LLM isn't raw output — it's causal ownership. Here's why that distinction matters more as AI tools get better.
My AI coding flow was burning tokens to do things code should do
How Pi Agent and a few deterministic extensions fixed my flow
From a CLI Junkie: Why I Ditched OpenCode for Pi
On OpenCode's lobotomy-pruning, security disasters, and the freedom of a four-tool terminal agent.
Why Honcho finally solved my agent memory problem
It doesn't just store your sessions. It dreams on them.
The AI Productivity Illusion: Why Ralph Loops Won’t Save Us
What 25 years in engineering taught me about the hype cycle
Where Vibecoding Actually Makes Sense
I finally tried it. Here's when it works, when it doesn't, and why your Sunday afternoon might be the perfect use case.
Why Coding Isn’t Disappearing—It’s Evolving with LLMs
Why LLMs Won’t Replace Developers (But Will Change How We Work)
The AI Productivity Illusion
What happens when everyone can write it but no one understands it