Research & announcements

We’re publishing irg-reference, an open implementation of the Iterative Reasoning Graph protocol. It runs against seven LLM providers, ships with a trace navigator that makes every reasoning step inspectable, and is licensed CC BY-SA so anyone can use it, fork it, and build on it.

The Colorado AI Act applies to deployers, not just developers, and it covers AI used in credit, employment, housing, insurance, education, healthcare, and legal services. Compliance turns on whether you can document how the system reasoned, not just what it produced.

Apply different prompt sets to the same reasoning graph and you get different convergence paths, different abstention rates, and different epistemic integrity scores. Prompt engineering isn’t cosmetic—it’s the configuration of an AI system’s epistemic personality.

Traditional validation assumes you can read a model’s mechanics, test it on holdout data, and stress-test it against known scenarios. LLMs break all three assumptions. What validation teams actually need isn’t holdout accuracy—it’s reasoning traces.

Hallucination rates aren’t evenly distributed. They increase with document complexity and input ambiguity—which means they concentrate in the domains where accuracy matters most: medicine, law, finance. The cause is architectural, and so is the fix.

Most EU AI Act coverage is written by lawyers for lawyers. But the Act’s requirements for high-risk AI systems aren’t just policy obligations—they’re architectural ones. Engineering teams need a different reading of Articles 9 through 15.