About Matrix Cognition

Matrix Cognition is an AI engineering site written, built, and maintained by one person who builds with these models for a living. There is no editorial team and no sponsor; what is here is one engineer's working notes, cleaned up enough to publish.

What is published

Four kinds of article, each with a different standard of evidence.

Tutorials build something that runs: a retrieval pipeline, an evaluation harness, a fine-tuning run, a serving setup. The code ships with the article as a complete listing, the package versions are named, and the numbers printed in the text came from running that code.

Paper readings take one paper, cited by its arXiv identifier, and separate three things that are usually blurred together: what the authors claim, what they actually measured and under which settings, and what I could reproduce or check. A result quoted from a table says which table.

News covers model releases, tooling changes, and benchmark movements, dated from the primary announcement (the lab's post, the model card, the release notes) rather than from secondary coverage, with the link.

Evaluation and systems pieces cover the parts people skip: how to measure a pipeline without fooling yourself, what quantisation does to a specific model, what inference actually costs.

What this site refuses to do

No benchmark numbers from memory. No "reportedly". No capability claims lifted from a press release and restated as fact. No invented quotes from researchers. If something could not be verified on the day of writing, the article says what is unknown instead of guessing. No exclamation marks.

How to read it

Every article ends with a Sources list; every claim worth checking is traceable to one of them. The code and data boxes link the files that produced the article's numbers. If a number here disagrees with what you measure, tell me, with your setup, and the article will be corrected with a visible updated date.