Colouring books with local AI
One colouring book is on sale and another is finished. Next, I want to speed up production without compromising quality.
Kristian Ratia
Projects
I usually have more projects than time. Some are programs, some are research experiments, some are physical things I've built, and some are things I wanted to try simply to see whether I could.
On this page
Not every project has to be finished, commercial or even useful. Often, the most interesting part is what you learn while doing it.
Built, and still growing
Lighting the home and office
Mirrors and lights for a glass cabinet. Semi-reflective film was an interesting idea, but too dark for the final build.
In progress and being explored
AI Interview Trainer
Job adverts become interview questions; answers receive feedback and suggestions for improvement.
Cryptocurrency market analysis and algorithmic trading
My 2023 thesis and an upcoming, broader study of how well technical analysis works.
Detailed image description
The chart is headed ICX and its original caption reads Table 33, Icon value. The vertical axis runs from 0 to 3.5. Neither the vertical axis unit nor the horizontal axis time period is labelled, so no assumptions are made about them. The curve has two high peaks near the start, a smaller rise in the middle and a low level at the end. It illustrates price variation, not the returns of a trading method or findings from the new research.
Music without the singing skills
ChatGPT helps with lyrics and prompts; Suno makes the songs. Working title: Insinöörin onnellinen elämä (The Happy Life of an Engineer).
Read the story of the projectYouTube and videos
Videos of things I build, on my own channel. Making, experimenting and a little humour.
The ideas notebook
Why automatic blinds?
I could raise the blinds by hand. But why should I, if it could be automated?
Read how the idea came aboutTap Watch
A plan for a flow sensor and a Raspberry Pi alarm if a tap is left running.
Read how the idea came aboutOther experiments
Not everything I do fits into a handful of larger projects. Sometimes I try something simply because I want to understand how it works, or whether I could make it myself.
Raspberry Pi, electronics, local AI models, image generation and many smaller experiments may get their own introductions when there's something interesting to tell.
Not everything has to become a finished product. Sometimes an experiment lasts one evening. Sometimes it becomes a project that goes on for years.
Small experiments can have short write-ups. Larger projects get their own pages.