Research & announcements

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.

SR 11-7, the Federal Reserve's model risk management guidance, was written for statistical models with inspectable coefficients. LLMs break every assumption the framework rests on. When an examiner asks how the model arrived at a specific decision, the answer "we trust the output" is not an answer.

There is a difference between knowing what your AI did and knowing how it got there. Most governance platforms answer the first question. They log the model, the timestamp, the guardrail result. The second question requires a reasoning trace.

We are releasing the Epistemic Integrity Evaluation specification. EIE is an open protocol for measuring whether AI systems handle uncertainty honestly, consistently, and proportionally. Most evaluation frameworks measure whether the model got the answer right. EIE measures whether it behaved well when it did not know.

We are releasing the Iterative Reasoning Graph specification. IRG is an open protocol for building AI systems that reason in explicit, persistent, revisable structures rather than ephemeral token streams. The reasoning persists in a graph your team can inspect, replay, and audit.