Dev Blog/Technologies
11 posts
How not to build a Process Foundation Model
Why classic AI model architectures fail to handle the unique properties of process graphs
Deriving slugs from embeddings: vec2slug
Building a tiny transformer decoder to extract URL slugs from vector embeddings
HashQL: Research Preview
A hypergraph query language that supports multiple, independent time dimensions — enabling reasoning over how data evolves and when it was known
Announcing hgres
The graph data engine powering HASH is now available as a standalone layer
Announcing SemType
Describe things that matter in a form people, AI agents, and software can all understand
Embeddings as Encodings
Correctly conceptualizing and handling vectorization in knowledge graphs
AI PR Reviewer
Improving code quality and accelerating feature delivery with a homegrown AI-powered code reviewer
Multi-temporal versioning in Postgres
Implementing an n-temporal datastore from scratch atop PostgreSQL
WebAssembly’s second-order impact on AI
What's new in Wasm and what it means for running large models client-side, in-browser