Hey, I'm Owen King.
I'm a quantitative analyst and software developer.
I use modern technology to analyse data, generate insights, communicate trends and create new products.
Some things I've created recently
Practising Chinese characters with MCP. A Model Context Protocol (MCP) server that helps learn Chinese vocabulary - equipped with tooling to create flashcards and collections of new words, test you on them and record your progress. Check out the code on GitHub.
Using text embeddings to discover more episodes of In Our Time. As a recent convert to the BBC’s long-running In Our Time podcast, picking which of the 1,000+ episodes to listen to next is often difficult. Using a set of similar techniques to a previous project on image analysis on the episode descriptions, I generated a broad categorisation of episodes and discovered some fantastic episodes on Choas Theory, Complexity and Randomness.
Playing with cellular automaton. Using a variation of cellular automaton to create a simulation of a little settlements. Rather than modelling cells as “on” or “off”, this simulation is designed to follow rules that produce a balance of different buildings and diversity of layouts. Try it out here or check out the code on GitHub.
AI for image analysis. Using OpenAI’s CLIP model, I generated embeddings for c. 500 of my own photographs. Cosine similarities were calculated for every pair of images to generate sets of ‘similar’ images - these similarity scores are the basis for the network layout. Using UMAP, the embeddings were reduced to a smaller set of features and clustered with HDBSCAN, producing seven (mostly) coherent groups of photos. Lastly, BLIP-2 was used to generate image captions.
sketchbook.ownkng.dev, a new companion site to this one to host some experiments in generative design and other creative endeavors. Check it out
A terminal UI written in Go. Made with the fantastic Charm libraries, a little terminal UI to practise Chinese characters. View on GitHub.
A few sketches. Some new generative sketches created with P5.js. Using a few techniques, including perlin noise, delaunay triangulation, poisson disk sampling and the chaikins algorithm.
Why use a Ternary plot? Visualising the UK’s energy consumption as three sides of an equilateral triangle. Check it out.