Dev Blog/Technologies

9 posts

Deriving slugs from embeddings: vec2slug

Building a tiny transformer decoder to extract URL slugs from vector embeddings

A hypergraph query language that supports multiple, independent time dimensions — enabling reasoning over how data evolves and when it was known

The graph data engine powering HASH is now available as a standalone layer

Describe things that matter in a form people, AI agents, and software can all understand

Correctly conceptualizing and handling vectorization in knowledge graphs

Techniques to improve the performance of AI on complex tasks

Improving code quality and accelerating feature delivery with a homegrown AI-powered code reviewer

Implementing an n-temporal datastore from scratch atop PostgreSQL

What's new in Wasm and what it means for running large models client-side, in-browser