Serious coding with LLMs. Lab notes 2026-11-03: If you offload your thinking, you’re onboarding risks
The 8th ‘lab note’ on serious coding with LLMs. Observations on mental load and code quality risks.
Aggregated enterprise architecture wisdom
The 8th ‘lab note’ on serious coding with LLMs. Observations on mental load and code quality risks.
The seventh ‘lab note’. Watch a teaser video of what my serious LLM-coded application is capable of.
The sixth ‘lab note’. I had the code audited. With some helpful scripts and an example from my ‘context harness’
The fifth ‘lab note’. This time on ‘tokens’ and the cost of generating them when working with LLM coding. Throttling is happening. Prepare.
The fourth ‘lab note’. More on the power and Achilles’ heel of “brute force trial and error with token pattern statistics” Goodbye, Codex. Hello, Limits.
The third ‘lab note’. More on the power and Achilles’ heel of “brute force trial and error with token pattern statistics”
The second ‘lab note’. More on the power and Achilles’ heel of “brute force trial and error with token pattern statistics”
Before publishing about my very serious LLM-coding experiment, I am publishing a few shorter ‘lab notes’. This is the first one.
Coding with LLMs (Claude Code, OpenAI Codex) is often presented as the ‘killer app’ for Generative AI. But looking at data, it seems the one piece of the puzzle missing is actual cost. A quest into getting a less muddy picture about what is going on, w…
Just copied from an earlier version on LinkedIn, a short article describing the key role of imagination in intelligence and why that may mean that self-driving cars require true intelligence and more than just reacting to sensors.
Fourth (and last) post about the ArchiMate NEXT snapshot from last summer. Summarising and then going wild on suggestions. Fasten your seatbelts, ArchiMate-geeks!
A new version of ArchiMate is coming. Last summer a snapshot of “ArchiMate NEXT” was published. Third of a few articles with my thoughts on the development, like the previous one focusing on an aspect that did not change (but maybe should)