Skip to content

2026ΒΆ

  • 5 min read

Updating my cognitive patterns with clearer evidence checks

In July, I introduced the cognitive patterns in my notes repository. Each pattern describes a reusable reasoning procedure, including when to use it, how to apply it, and where it can fail.

The collection now has 18 patterns, with three additions and focused changes to five existing patterns. The additions address evidence quality, decisions under uncertain future conditions, and causal claims. I also refined the guidance for when an AI should contribute during shared work.

The revised procedures make several previously implicit checks explicit. The checks performed during this update do not establish that an AI using them gives more accurate answers.

  • 5 min read

Documenting cognitive patterns for better human and AI collaboration

My notes repository stores sources, concepts, and investigations. Sources preserve what another author said. Concepts combine knowledge about one idea. Investigations record how I examined a specific question. I recently added a fourth kind of note that records how to reason about many different questions.

I call these notes cognitive patterns. A cognitive pattern is a reusable reasoning procedure. It contains questions, steps, failure modes, checks, and an example of how the same procedure can work in another field.

The goal is to make the reasoning between a question and an answer easier for a human and an AI to inspect together. A pattern can help them choose a suitable procedure, notice missing checks, and improve the procedure after using it. It does not make the answer true. Evidence still has to support every claim.

  • 5 min read

Running the 3B Unlimited OCR model on Apple Silicon

Baidu released Unlimited OCR in June 2026. It is a vision language model for reading complete documents. It returns text, headings, tables, formulas, reading order, and the positions of page elements. The model can also read several page images in one request.

The model is small enough to run locally. It has 3 billion parameters in total, while its mixture of experts decoder uses about 500 million parameters for each token. I can run it on a MacBook Pro with an M4 chip and 24 GB of memory.

  • 6 min read

Making my notes repository compatible with OKF

In June 2026, Google proposed the Open Knowledge Format, or OKF. I had already been keeping my notes as Markdown files in Git, so the proposal caught my attention. My setup already shared many of the same parts, but it did not follow the OKF rules. I wanted to know what I would have to change.

The adaptation required less work than I expected. I kept my notes system and defined which part of the repository is portable. I also added a clear entry point, made a few file rules explicit, and taught the existing notes skill to follow them.

  • 2 min read

Python Minimal Boilerplate: Presentation at PUG #14

I recently had the opportunity to present at the 14th Belgian Python User Group (PUG) meetup. The event was kindly hosted by Datashift at their offices in Mechelen on January 22, 2026.

It was a fantastic evening of technical deep-dives and community networking. You can view the original meeting announcement and attendee list on Meetup.