Abstract This paper reports a set of governance-relevant failure axes observed during sustained, first-principles experimentation with large language models under conditions of unreliability, session loss, and forced recovery. Rather than evaluating model performance, the work documents where and why human–AI interaction breaks down in practice, drawing on iterative analysis conducted while constructing a durable corpus and corpus map amid repeated system failure. The resulting axes characterise failures that are governance failures in themselves, or that require governance mechanisms to prevent harm, and are presented as descriptive, orthogonal analytical tools rather than definitions, prescriptions, or completeness claims.---- This work has not undergone academic peer review. The DOI asserts existence and provenance only; it does not imply validation or endorsement. This Zenodo record is an archival projection of a publicly published artefact. Canonical versions and live revisions are maintained at the original publication URL listed above.