Albert Sikkema - Building Production AI Systems

Photo by Pixabay on Pexels Every time I read that Europe will “never catch up” in AI, it annoys me.

Photo by Adlan on Unsplash Almost all AI services I use with the different companies and governments I worked with are American based, mostly Azure and Anthropic.

Photo by Phill Brown on Unsplash I have been using LLMs daily for years now, mostly to code, but also for research, writing, and analysis.

Photo by Ricky Kharawala on Unsplash Most people I know put wallpaper up in their own house, do small to medium jobs in and around the house themselves and only hire out to a crafts(wo)man when the job is too big or takes too much time.

Over the past year I have been working on tooling to improve code quality.

Photo by Ingmar on Unsplash As you may have read in an earlier post, I do not like writing tests.

Photo by Jornt Hornstra on Pexels About seven months ago I wrote about zero-latency PII filtering in Python logging: how to sanitize personal data from logs without blocking your main thread.

Last month I wrote about where automated builds hit their ceiling: costs, reviewer fatigue, and models that are not smart enough for full autonomy.

Signal obscured by noise.

Photo by Martin Bennie on Unsplash This weekend I built a small CLI tool that pulls transcripts, comments, and metadata from YouTube videos.