An instrument that surfaces mechanistic hypotheses a field’s dominant consensus has discounted, and measures the distance between how much attention a target gets and how good its evidence actually is — so a contrarian can defend the bet with more than conviction.
The target is not the neglected cold periphery of biology — the places no one looked. It is the opposite: indications where enormous capital and attention have been spent, repeatedly, down paths that failed, and where that very history has hardened into a consensus that now functions as a filter on what gets funded and published.
In these fields the obstacle is not absence of attention. It is that attention is correlated. The field’s prior is concentrated, and concentration suppresses the alternatives. Billions are spent re-running variants of the dominant hypothesis, while heterodox mechanisms struggle for oxygen — not because they were disproven, but because they were not endorsed.
The distortion this engine fights is social, not informational. The heterodox hypotheses usually already exist — published, then starved of follow-up. The scarce ingredient is rarely the idea. It is the permission to spend time on an unfashionable one.
An instrument that surfaces under-attended hypotheses is only worth building if someone can move on what it finds. In a consensus-distorted, capital-heavy field most of the obvious buyers cannot — for structural reasons, not for lack of interest. Working through who they are is what isolates the real user.
The contrarian founder is not asking the engine to decide — that is the ego wall every other buyer hits. They have decided. They need an answer to the question that kills a non-consensus pitch: “if this target is so good, why is nobody else here?” The engine is not a recommendation system for them. It is the evidence behind that answer.
The product is not a quality score on its own. Anyone can rank hypotheses. The thing no one can cheaply produce is the gap between two independently measured quantities: how good the evidence for a target is, and how much attention the field actually pays it. Computed separately, their distance is the whole proposition.
The two halves come from deliberately separate places. The evidence side is the engine’s output — the verified warrant the pipeline in section 05 produces. The attention side is independent market research, kept out of the pipeline on purpose, so that quality is never inferred from popularity. Their independence is what makes the gap meaningful rather than circular.
The sweet spot is a band, not a maximum. Too small a distance is just the consensus crowding everyone already sees. Too large and the target looks mad to work on — a moonshot no one will fund. The interesting zone sits between: plausible, decently evidenced, and under-attended for reasons that are sociological rather than scientific.
A warrant is only worth something in the room because it could have come back negative. An instrument that always confirms the founder’s bet is worthless — a sophisticated investor will sense it was reverse-engineered. The buyer’s incentive points toward flattery; the product’s value depends on resisting it.
For consensus-distorted indications, an LLM agent’s usual weaknesses invert into assets. fred has no career, no grant cycle, and no disciplinary loyalty. Against a pathology that is fundamentally about social pressure on what may be pursued, that indifference is the central capability rather than a limitation.
A human researcher carries the consensus whether they like it or not — careers, grants, and peer review are downstream of it. fred can assess a shut-off hypothesis on its merits without the social penalty that makes a human discount it. The distortion is social; fred is immune to the social part.
Billions in failed journeys leave a large, machine-readable trail. A field under consensus pressure systematically under-reads its own failures, attributing them to execution (“wrong patients,” “dosed too late”) rather than to the hypothesis class. fred can read the failure corpus as a corpus and ask whether the pattern fits “right idea, executed badly” or “the idea class is wrong” — the move the consensus is structurally unable to make about itself.
The valuable hypotheses are usually already published and then abandoned for non-scientific reasons. fred’s job is to find that starved work, assess whether the abandonment was evidentiary or sociological, and re-present the survivors as defensible, evidence-anchored writeups. It lowers the activation energy of looking at an unfashionable idea.
fred does not need to be right. It needs to produce, for a discounted mechanism, enough verified evidence that a competent human should spend an hour deciding whether it deserves more. A warrant for attention, not a conclusion. The human expert remains the final filter on every path.
The architecture enforces one boundary above all: the quantitative, consensus-measuring work runs on structured data with no LLM involvement, and fred is invoked only at the back of the pipeline to generate and verify warrants. “Cold” and “unsolved” are measured, not imagined. Tap or hover any stage for detail.
The verified warrant is where this pipeline ends and the contrarian’s case begins. It is the evidence half of the distance in section 03 — the thing the founder carries into the room to answer “why is nobody else here?” The engine builds the warrant; the distance is what it is worth once the field’s attention is measured against it.
“Reasonable mechanism plus some evidence” is precisely the shape of a fluent hallucination. The difference between a warrant worth a look and a confabulation is not tone — both sound reasonable — it is the type of evidence attached. A warrant has three load-bearing parts:
This is also what makes a warrant survive an investor’s scrutiny. The third part — a credible, non-scientific reason for the neglect — is the direct answer to “why is nobody else here?” A bet that can name why the field looked away, and show the evidence the field walked past, is principled rather than reckless.
These dominate the design and are stated without optimism. None are fully solved by the architecture above.
Everything rests on the agreement rate between fred’s “worth a look” and a competent reviewer’s “yes, worth a look.” If precision is high, this is a powerful instrument. If it is low, it is a plausible-text generator that costs more review time than it saves. That precision is not yet measured.
fred’s unique value for consensus-distorted unsolved indications is that it is a prior-agnostic re-reader of a field’s own record. It treats the expensive failure history as evidence rather than noise, assesses whether abandoned hypotheses were killed by data or by sociology, and re-surfaces the survivors without the career incentives that make humans discount them. The edge is immunity to the social mechanism that creates the distortion — not superior biology.
It earns its place at one moment: when an early-stage team on a non-consensus bet has to defend that bet to people with capital, and needs a credible, evidence-weighted answer to “why is nobody else here?” The distance between attention and evidence is that answer — provided the instrument that measures it is willing to come back negative.
That same prior-agnosticism is double-edged: an instrument with no prior will validate heterodoxy as readily as orthodoxy, because it has no independent footing to judge either. The value is realized only if fred can distinguish evidentiary from sociological abandonment on cases where the answer is already known. If it can, this is a consensus-auditing instrument. If it cannot, it is a very articulate machine for confirming whatever the operator already believed.