The Architecture of Forgetting
Language models have no memory. What looks like recollection is a reconstruction at every call. A comparative analysis of how six agentic CLIs solve the problem of a scarce working memory architecturally, with precise thresholds and verifiable citations from the respective codebases.
The ROI Depends on the Foundation: What Google's DORA Team Says About AI-Assisted Development
In February 2026, Google Cloud published a 60-page report on the return on investment of AI-assisted software development. In it, the DORA team and Google’s consulting unit “delta” model the first-year costs of tool adoption, learning curves, and value creation. The central lesson lies outside the tables: AI is an amplifier. Without a solid foundation, it amplifies an organization’s dysfunctions.
Agentic Coding Forces Development Teams to Adapt
Language models have left the editor and moved to the command line. They plan, write, test and deploy. Anyone working without a method loses control over the result. I have developed a training programme that outlines what a team needs to set up end-to-end to remain competitive.
Where the agent touches the wall
My experimental project AEGIS checks the actions of autonomous AI agents against a formal set of rules before they are executed.
The Algorithm: How DDIC Resolves Conflicts
Two rules contradict each other: a nurse is not allowed to read patient records, but in an emergency, she is. Which one wins? And how does the engine prove this in microseconds, without a theorem prover, without magic?
Claude Opus and AEGIS: A Dialogue
A lengthy exchange with Claude Opus 4.6 about AEGIS, 100% requirements, and the structural difference between probabilistic generators and deterministic verifiers.
When everyone suddenly wants AI
When companies want to roll out AI coding tools on a large scale, it rarely fails because of the model. More often than not, it fails due to context, habits and weak processes.
When AI Writes the Rules
How do we get from 'doctors are allowed to view patient records' to a formal rule that a computer can verify deterministically? On rule languages, translation gaps, and the question of whether an LLM should be allowed to help.
The Deterministic Gatekeeper for an LLM
Why no amount of training in the world is enough to turn a language model into a rule-based system. And what the alternative is.
Who Orchestrates the Specialists?
In 1997, I posted a link to the Cyc project on my company website. Nearly 30 years later, the same question arises—only differently. About the void at the center of AI architecture.
Context Is Everything
AI agents are only as good as the context you provide them. Anyone implementing large-scale projects with agents doesn't need a better model, they need better context management. A field report based on two years of practical experience.
Elegant Garbage
LLMs give people without expertise the tools to produce impressive-looking output. The problem is not the technology. It is the intellectual self-deception it makes easier.
Who Checks the Last 10%?
AI agents write code faster than ever before. But the ability to evaluate that code cannot be automated. And it is in danger of disappearing.
With AI, many projects are 90% complete
Why AI won't replace senior developers
A Return to the Waterfall Model?
LLM agents can write code in minutes. But who determines the architecture? Why greenfield development with AI requires more planning, not less.