Skip to content

About

A frontier model on the US tape.

orbyd does what a fund won't: we publish our live book — the names we hold and the ones we're circling — and keep a falsifiable, dated, Brier-scored record of whether each thesis played out. The reasoning runs on frontier language models; a multi-stage pipeline reads US equity news, earnings, filings and price structure every trading day. The accountability is the edge.

Every dossier carries a thesis, an invalidation trigger, an archetype, and a catalyst calendar. Every journal entry is dated and signed by a regime. Every macro view shows its math. The model writes, the methodology is open, and every call is on the record.

Models

Opus + Sonnet

frontier reasoning

Context

1M

tokens, side-by-side

Pipeline

5

stages, every trading day

Archetypes

8

behaviour profiles

Why open methodology

Reasoning in public is the product.

Discipline

A published invalidation trigger is a kill switch the author can't quietly retract.

Calibration

A dated archive is the only honest test of whether a system reads the market or just narrates it.

Builder signal

If you ship LLMs into markets, a public methodology beats any pitch deck.

Under the hood

How it's built, in detail.

Frontier language models

Claude Opus / Sonnet for synthesis, narrative classification, and the model's quality read.

Five-stage pipeline

Liquidity screen → momentum + news scoring → the model's quality read → portfolio composition → how the model learns from closed trades.

Daily schedule

Premarket, midday, decision window, opportunistic windows, end-of-day. DST-correct year-round.

Updated weightings

Every close triggers a review; recurring patterns promote to a playbook; weightings update from closed-trade outcomes.

Long-context reasoning

Opus holds every candidate dossier in a single 1M-token window and ranks them in one pass — no chunking, no lossy summarisation.

Versioned output

Versioned dossiers, dated journal, and an open methodology page.

On the record

Every thesis, the names we hold and the ones we're watching, and every regime and macro call — published the day it's made, dated, and scored against the trigger that would prove it wrong.

Open by default.

Hub network

Four sister sites.

orbyd is the umbrella for four sister sites at the intersection of language models and operator work. All static. All free. No signup.

Contact hello@orbyd.app @orbydx github.com/rustyclawd