Arbiter 27B starts from Qwen3.8-27B and adds recurrent depth: three windows of the network run three passes over the prompt, with small per-pass adapters trained on operations a verifier can check exactly. The base weights never change. Arbiter is not included in Orrery plans; it is available on request: contact kt@ephemerent.com.
The workspace, selected route, and review requirement stay explicit before hosted work begins.
Request received · boundary visibleArbiter is not included in Orrery plans; access is arranged on request. Contact kt@ephemerent.com.
Route named · availability not assumedSummary, usage, proof, and boundary records remain distinct so a polished answer cannot masquerade as verification.
Evidence visible · success not fabricatedThe receipt gives you material to inspect. It does not decide whether the work is safe to keep, run, or ship.
Receipt presented · acceptance remains yoursArbiter is Ephemerent's reasoning model for coding and research work where evidence matters. It is no longer a hosted route included with Orrery plans: the models included with Pro, Max and Ultra are hosted models (DeepSeek, GLM and others, served via Doubleword through Orrery Relay). Arbiter is available on request.
Where access is arranged, Arbiter appears in Orrery as a model route named arbiter-flash-27b — Arbiter 27B, the looped Qwen3.8-27B — selectable from Nexus. Nexus shows usage meters, run receipts, and proof/boundary summaries where the app supports them.
The route is designed for agentic coding and research workflows: planning, editing, follow-up fixes, and review. It does not replace your own testing, code review, security review, or backups.
Most models do their thinking out loud: the visible chain of thought is generated token by token. Arbiter thinks before it writes. Three windows of the network run three passes over the prompt during prefill, with small per-pass adapters trained on operations a verifier can check exactly; decode is then a single ordinary pass. The base Qwen3.8-27B weights never change — the loop is where the extra depth lives.
Arbiter is not part of any Orrery plan. To ask about access, email kt@ephemerent.com. For everyday hosted work, Orrery plans include hosted models with monthly credits; see Orrery pricing.
Where Arbiter access is arranged, Orrery by default shares your Arbiter coding and research sessions with the Arbiter service so the next version is trained on this kind of work: the prompt and tool results sent to the model, the response, and the outcome of the turn, tied to an anonymous per-session id. Your account and email are never attached, and hosted-model (Doubleword) turns are never captured. Turn on Zero data retention for Arbiter in Orrery settings and the service keeps counts and an access-log line only, from the next request on. The full description is in the Privacy Policy.
Treat Arbiter output like any other AI-generated code: inspect it, run tests, review security implications, and keep backups. Orrery can help organize evidence, but you remain responsible for what you accept, run, and ship.