Collapse Index Labs · Alex Kwon

# Collapse Index Labs > Collapse Index is a lens, not a metric. It asks whether a confident, stable-looking surface is still joined to the thing that made it true. This site is Alex Kwon's personal research page: a short, plain-language intro to the lens, plus the published papers and code. The site at https://collapseindex.org is a single page. It is a short, first-person introduction in the author's own voice: what he researches (the invisible structures inside AI models), how Collapse Index started, the fact that the metric broke when he ablated the mechanism it was tracking, and the lens the work now follows. It then links the published papers and the code. There is no signup, no demo to schedule, no product to buy, and no metric being pushed for adoption. The lens, in one sentence from the page: > Collapse happens when a system preserves the thing that sounds final and loses the thing that could make it true again. ## What Collapse Index is Collapse Index began as a metric, a per-sample measure of how a prediction's structure moves under semantics-preserving perturbation, and it did not hold as one. When the mechanism it was tracking was ablated, it broke: under its own controls, stability turned out not to be the operative variable, a robust prediction and a robust shortcut-error can be equally stable, so a system agreeing with itself under perturbation is not the same as a system joined to the truth. The metric is kept on the record as the first broken instrument, not as a working detector. What survived is the lens. The question was never stability on its own; it was attachment, whether a confident surface is still joined to the thing that made it true. The same lens recurs across substrates: a calm answer decoupled from its flipped context (Brittle Safety), a citation that kept the prestige and lost the evidence, a memory that kept the conclusion and buried the source (and so became permanently uncorrectable), a model that grew more capable without g