OSIRIS v4.5.0: a governed, local-first console for testing whether a small language model learns from conversation

Abstract

v4.5.0 adds Google Cloud integration: Gemini through Vertex AI in the user's own project with their gcloud login, keys read from Google Secret Manager instead of a plaintext file, and CI on Google Cloud Build; it also includes NCLM-1 workflow and verify-loop changes. See RELEASE_NOTES_v4.5.0.md. OSIRIS is a local-first console in which deterministic code mediates every interaction with language models: models propose; code decides, measures and records. Its subject is a small transformer, the core (osiris.nclm), trained online on conversations with a locally hosted mentor model. The core may answer in its own voice only after it passes a held-out speaking gate: 30 held-out exchanges at ≤ 2.0 bits/byte and below a unigram baseline. Until then the mentor answers, labelled as speaking for OSIRIS. Evidence to date: in two pilots, training on conversation lowered the core's loss on held-out replies (mean +0.043 bits/byte on 3 items, 10.5281/zenodo.23075229; +0.067 bits/byte on 20 items, positive on every item, 10.5281/zenodo.23102693). The core nonetheless remained worse than a unigram model of the same replies (5.56 vs 4.68 bits/byte) and has not passed its gate. About 86 % of the variance in the learning signal came from the training run, so a confirmatory test must replicate training runs. The pre-registered confirmatory test (NCLM-1) has not been run. This release claims no successful learning. v4.3.1 is a packaging and repository-hygiene release: modules and scripts the console needs are now packaged (a clean install previously reported 'bench evidence unreadable (ModuleNotFoundError)'), hard-coded home-directory paths are gone, and private conversation transcripts and third-party contact details were removed from the repository. The files of the two previous versions are restricted for that reason. The attached note describes the software, its measurement design and its limitations.