Tags
AI
Browse all published documents tagged AI.
11 documents
Prove and Admit, Don't Just Lint
Why executable rules are the easy half, and why the checks around agent-written code must require presence, report their blind spots, and be written as a standard rather than collected as rules.
Enforce Architecture, Don't Trust Intent
Why load-bearing architecture rules must become executable checks rather than trusted intent.
Sovereignty by Proof: A Defensive Strategy for European AI
The ground to take: models that prove mathematically that code holds, against any attacker, including a stronger AI. That market is forming now, with hundreds of millions raised in the United States; Europe has an open proof model, not yet anyone selling the guarantee.
Outgrow Your Taste, Don't Defend It
Building a software solution is three distinct activities: understanding a reality, engineering a general machine, and encoding one into the other. Taste is required by none of them, which is exactly why ego hides there.
Make Feedback Loops Attribute, Don't Just Detect
Why feedback loops become more powerful when code makes its system concepts explicit.
How AI Is Changing Our Relationship to Work in Software Engineering
On the excitement of AI-assisted coding, the disappearance of friction, and the need to learn how to tame our new tools.
AI Makes It Absurd to Keep Engineers Away from Reality
When the cost of producing code falls, value shifts toward understanding the real problem.
Encode, Don't Imply
Why the implicit becomes fragile when humans and agents co-produce code.
The Brain Needs Recovery Too
What sport can teach us about effort, recovery, and intellectual work.
The Time Ideas Need
On maturation, attention, and what speed cannot replace.
How I Write the Articles Published Here
An honest explanation of my working method for writing the articles published on Le secrétaire de Fernand.