COMMON. / FINDINGS

Findings.

What we tried, what worked, and what did not. Written down as we go, before we know how it ends.

Research

The graph is the reasoning layer.

We said CGLA was zero-hallucination and that more was coming. Here are the numbers from two working systems — and what that claim looks like once it is measured.

Read 3 min
Research

What breaks at the seam.

We split one job between two models and spent 1,336 runs working out where the quality went. It was not the second half being harder. It was the handover.

Read 7 min
Milestone

Prototype Decentralized Network

We have built the first internal prototype for the decentralized network and it is currently undergoing testing!

Read 1 min
Technical

CGLA System testing

We've been testing a new type of graph based SLM (Small Language Model) making it zero-hallucination, and allowing inference and training on consumer hardware. This architecture…

Read 1 min
Milestone

Website live.

Common is online. This site is the first public face of what we are building — a decentralised AI inference network that runs on the devices of its participants. We are early. We…

Read 1 min
Technical

Vector routing prototype complete.

The first real piece of the network works. We built a prototype that embeds a user query and seven domain centroids into a shared latent space using sentence transformers, then…

Read 1 min
Research

In early conversation with AIML.

We have started talking with researchers at the Australian Institute for Machine Learning at the University of Adelaide. Early conversations around causal reasoning and world…

Read 1 min
Technical

Self-routing specialists in testing.

We moved away from a dedicated router model. Instead, each specialist now has domain awareness built into its system prompt and decides for itself whether a query belongs to it…

Read 1 min