Skip to content

Author

Devin Phillip Davis

4 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#small language model Open access Oct 2026

OSIRIS v4.5.1: a governed, local-first console for testing whether a small language model learns from conversation

v4.5.1 is a correction release. The claims register's τ-phase matcher now recognises '46.0 µs' and no longer matches unrelated 46 µs delays, and its finding states the phase definition as the code computes it. In the console, a document pasted while OSIRIS was answering could be classed as typed and trained on; held me...

Devin Phillip Davis · 0 citations
#small language model Open access Oct 2026

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

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...

Devin Phillip Davis · 0 citations
#small language model Open access Sep 2026

OSIRIS v4.2.1: a governed local console for a living language model

OSIRIS is a local-first console built around a small language model (osiris.nclm) that learns from every conversation and from the author's documents, and answers in its own voice only after passing a held-out test (30 held-out exchanges at ≤ 2.0 bits/byte and below a unigram baseline). Until then a local Ollama model...

Devin Phillip Davis · 0 citations
#small language model Open access Sep 2026

OSIRIS v4.2.1: a governed local console for a living language model

OSIRIS is a local-first console built around a small language model (osiris.nclm) that learns from every conversation and from the author's documents, and answers in its own voice only after passing a held-out test (30 held-out exchanges at ≤ 2.0 bits/byte and below a unigram baseline). Until then a local Ollama model...

Devin Phillip Davis · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.