We study artificial minds the way ornithologists study birds.

Ornis is the Greek word for bird. The name reflects how we approach this work: through careful observation of behavior, structure, and the patterns that emerge from both, before reaching for an account of what these systems are.

Ornis Research is an independent AI alignment laboratory. We study the behavior of large language models under realistic deployment pressures, the internal mechanisms that produce that behavior, and the relationships between these systems and the people who rely on them.

We are unaffiliated with any large company or specific university. Most of our work is published openly — papers, blog posts, pre-registrations, code, and result tables. We place a high weight on methodological rigor and reproducibility: paired controls, pre-registered verdict criteria, public datasets, and walking back claims when replication fails.

The lab writes for the international academic literature. We welcome correspondence from researchers working on related questions in alignment, evaluation, and interpretability.

For the substance of what we work on, see what we study. To reach us, write to hello@ornisresearch.org.