Serious coding with LLMs. Lab notes 2026-11-17: Wait…11,000 lines generated for every line of code of my system??

The 9th 'lab note' on serious coding with LLMs. Observations on the inefficiency of coding with LLMs.

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.

Serious coding with LLMs. Lab notes 2026-10-31: Teaser Demo of the LLM-coded EACMP application, and a quiz

The seventh 'lab note'. Watch a teaser video of what my serious LLM-coded application is capable of.

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'

Serious coding with LLMs. Lab notes 2026-10-21: The throttling of subscriptions by OpenAI and Anthropic is really happening

The fifth 'lab note'. This time on 'tokens' and the cost of generating them when working with LLM coding. Throttling is happening. Prepare.

Serious coding with LLMs. Lab notes 2026-10-13: Codex vs Claude on the same coding task.

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.

Serious coding with LLMs. Lab notes 2026-10-01: Codex and Claude generate a shared analysis

The third 'lab note'. More on the power and Achilles' heel of "brute force trial and error with token pattern statistics"

Anthropic/OpenAI may be spending more than $1000 for every $100 you pay them

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, with surprising results.

AI-generated podcast AI-slopcast

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.

AI has invented a new language, and added sex to a dull office context

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).