Serious coding with LLMs. Lab notes 2026-10-27: A code audit of LLM-generated code: improving from ‘sludge’ to ‘vakwerk’
The sixth ‘lab note’. I had the code audited. With some helpful scripts and an example from my ‘context harness’
Aggregated enterprise architecture wisdom
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.
Before publishing about my very serious LLM-coding experiment, I am publishing a few shorter ‘lab notes’. This is the first one.
If you spend enough time in Enterprise Architecture, you will eventually encounter a curious phenomenon. Almost everyone supports the idea of Enterprise Architecture. Almost nobody agrees on what it actually is. Some executives believe Enterprise Architecture is primarily about technology standards. Others expect it to deliver target architectures within weeks. Some see it as an exercise in governance and compliance. Others imagine a group of architects who somehow possess a master plan that immediately solves organizational complexity. Interestingly, all of these perceptions contain fragments of truth, yet none of them fully captures what Enterprise Architecture actually represents.
The post EA… Wait… What? appeared first on EAWheel.
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…
We introduce a new term: “AI-slopcast”. This is a podcast that is created by Generative AI and — surprise! — is AI-slop. The victim: one of my own posts.
Why agility, reuse, and cross-domain strategy are reshaping how we…
It turns out that AI has created a whole new language. Humans do not speak it, and they may even mistake it for talk about sex. But luckily Generative AI is able to translate it to something humans can understand (and where the sex doesn’t show up).
‘Reasoning models’ such as GPT4-o3 have become a well known member of the Generative AI family. But look inside and while they add a certain depth, at the same time they add nothing at all. Not ‘reasoning’ anyway. Just another ‘level of indirection’ wh…
GPT-3o has done very well on the ARC-AGI-PUB benchmark. Sam Altman has also claimed OpenAI is confident that it can build Artificial General Intelligent (AGI). But that may be based on confusions around ‘learning’. On the difference between narrow, ge…
Google has announced ‘Willow’, a quantum computer that can calculate so fast it would take a supercomputer 10 septillion (a 10 with 25 zeros) years to do the same. But while the science is real and cool, the message is misleading. An explainer for non-…