Hallucination Detector

Tap a card to flag a lie Let true facts pass
♥♥♥ 0 x1

Ready to fact-check?

A model is hallucinating in production. Tap the false statements before they escape. You have a tap-to-deny button and trust issues.

How the Hallucination Detector Works

You are the last line of fact-checking against a model that is confidently, eloquently, and frequently wrong. Statements stream across your screen as cards. The model swears every single one is true. The model is not to be trusted.

  1. Cards drift across the screen — each is a short "fact"
  2. Some are true. Some are plausible hallucinations the model invented
  3. Tap a card to flag it as a hallucination and deny it
  4. Let true facts scroll off the edge untouched

How You Lose Trust

Flag a real fact as fake, or let a hallucination escape to production, and you lose a life and your combo resets to x1. Three strikes and the model ships unsupervised. Catch lies in a row to ramp your combo multiplier and your score. Spawn rate and drift speed climb the longer you survive — the model gets more confident, not more correct.

Slop Fact: Large models don't "lie" — they sample the most probable next token, which is sometimes a citation to a paper that was never written by an author who does not exist. We call this "creativity" in the deck and "a bug" in the postmortem.

Back to the Slop