Trust / quiz / 2026-10 / v1
Can you spot the weak AI evidence?
Three short reasoning checks. Test what a survey, an accuracy score and a model comparison actually tell you.
Three fixed multiple-choice questions. Accuracy is measured, not self-reported. First completed attempt per month counts. Solutions are shown after submission; practice is excluded.
Quiz · Question version 1. This question collects responses each UTC calendar month. 3 task items; first completed attempts count, with a 30-minute session limit.
Voluntary reader sample, not a representative population survey. Published results remain public. How collection and results work →
Checking participation…
On the record
No published collection yet. Monthly results will appear here after collection closes and the minimum response threshold is reached.