Trust · the honest case
An analyst that shows its work — and its doubts.
"An LLM, for markets? Models hallucinate." Fair. So orbyd is built to be audited, not believed. It publishes its live book, the disconfirming case on every name, and the exact condition that would prove each thesis wrong — then keeps score in public, played-out or invalidated, Brier-scored. Falsifiable and dated, not a black box. Here's the honest case for trusting the work.
It tells you what would prove it wrong
Every thesis ships with an invalidation trigger — a pre-committed price, news, or event that strips the conviction if it fires. A kill switch the author can't quietly retract. Most analysts never publish theirs.
See an invalidation trigger →Every read is dated and versioned
No silent edits, no hindsight rewrites. Each dossier and journal entry carries its write date; re-analyses are versioned. A dated archive is the only honest way to know whether a system is reading the market or narrating it.
The reasoning is open — both sides
The bear case is built with the same rigour as the bull case, sourced and dated. You audit the argument, not just the conclusion. Disconfirming evidence is shown, not buried.
How a dossier is built →It names its own failure modes
Stale facts that lag the latest 10-Q. Confident setup reads that fail within hours. Theme misclassification. Every one stated on the methodology page, not buried. A system that can't be wrong can't be trusted.
Where the model is wrong →Nothing to sell you
The pipeline runs on a paper account. Positions, fills, and P&L are never published — so there's no book to pump, no order to front-run, and no incentive bent around your click. The read is public; the trade is private, by design.
What stays private →It is not advice — and says so
orbyd publishes educational research under the BaFin and EU framework. No personalised advice, no orders accepted. The dossier is the reasoning; the decision is yours. That boundary is a feature, not fine print.
The honest calibration
A frontier model is extraordinary at some things and useless at others. Pretending otherwise is how you lose money. Here's exactly where the line falls.
What it's good at
- Reading 30 days of news and four quarters of earnings across hundreds of names — every trading day, without fatigue.
- Holding the whole candidate set in one 1M-token context and comparing theses side-by-side.
- Applying the same framework to every name — no ego, no FOMO, no anchoring on yesterday's call.
- Writing the disconfirming case as carefully as the confirming one.
What it's not
- Knowing anything non-public — it reads the same tape you do.
- Guaranteeing a setup plays out — a clean higher-low can fail within hours.
- Catching every stale fact; a model snapshot can lag the latest filing.
- Predicting the market. It reads conditions and gates risk — it doesn't forecast prices.
How this differs from a traditional analyst
Coverage
orbydRe-reads every name in coverage — hundreds — every trading day.
Typical analystA short coverage list, updated in spurts.
What it admits
orbydPublishes the exact trigger that would prove it wrong — before it fires.
Typical analystRarely publishes what would change its call.
Consistency
orbydSame framework on every name — no ego, no FOMO, no anchoring.
Typical analystConviction and incentives drift the read.
Incentive
orbydPaper account, nothing to sell, no order to front-run.
Typical analystBanking, commission or access conflicts are common.
Common questions
- Can you trust an AI stock analyst?
- Trust the work, not the call. orbyd is built to be audited: every thesis ships with the explicit condition that would prove it wrong (an invalidation trigger), every read is dated, and the bear case is built as carefully as the bull case. You check the reasoning rather than believing a black box.
- Don't language models hallucinate?
- They can — which is why orbyd names its own failure modes (stale facts, confident-but-wrong setup reads, theme misclassification) on the methodology page, dates every read, and publishes an invalidation trigger with every thesis. Nothing here is presented as certain.
- Is orbyd investment advice?
- No. orbyd publishes educational research under the BaFin and EU regulatory framework. No personalised advice is given and no orders are accepted — the dossier is the reasoning; the decision is yours.
- Why aren't positions or P&L shown?
- The pipeline runs on a paper account, and publishing live actions would let readers front-run or fade them and compromise a clean forward-test. The read is public; the trade is private, by design.
The bet isn't "the model is always right." It's that a tireless, consistent, ego-free reader that publishes its reasoning and its invalidation triggers is a better research instrument than a confident voice that never shows either. Read the work. Check the dates. Watch the invalidation triggers fire or hold. Decide for yourself.