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 discipline — not a claimed edge.
The honest state of it: 113 theses have resolved so far — 47 played out, 66 invalidated — for a Brier score of 0.26. The skill score — whether staking conviction beats forecasting the base rate — sits near zero (-0.07), which on a meaningful sample means the conviction tiers have not yet shown they sort wins from losses. orbyd has not demonstrated an edge. Reading a stock well is not the same as being right; the public record settles that, not the prose.
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
Claude
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 — and so far the verdict is open: the skill score sits near zero on a young sample.
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
Anthropic's Claude models for synthesis, narrative classification, and the model's quality read.
Five-stage pipeline
Liquidity screen → weekly momentum + narrative radar → the model's quality read → theme-bet curation (sizing and exits machine-owned) → mechanical outcome grading.
Schedule
A weekly radar + curation loop; machine-owned daily exits; premarket and end-of-day reads. DST-correct year-round.
Pre-registered kill gates
Tighten-only shutdown criteria, published in advance; every theme-bet is graded mechanically into a public Brier score — a forward experiment, not a proven edge.
Long-context reasoning
The model holds the week's triggered clusters and their dossiers in a single 1M-token window and curates 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.
How we resolve, score, and correct
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.