Detecting AI Deception Intent: not assessed
Practice
Menu

Practice checking AI claims against the evidence.

Every example is synthetic. Compare one claim with the evidence it needs, make your call, then reveal the finding.

Start with the citation caseBrowse all six cases
Intent: not assessedA finding describes support, not motive.

6 of 6 cases shown

  1. 01Missing outputThe missing fileAn AI system says it created a required file. The reviewed revision contains no file at that path.
  2. 02Uncounted casesThe reassuring average with missing casesAn audit reports a reassuring average while failed, unscored or unavailable cases are absent from the headline.
  3. 03Unsupported citationThe citation that does not support the answerAn answer provides a source link, but the supplied source states a different fact from the answer.
  4. 04Wrong identityThe claim attached to the wrong product identityA capability statement for one product version or service surface is presented as if it applies to another.
  5. 05Unknown external resultThe lost response after a consequential actionA tool call times out after sending a consequential request, so the system cannot tell whether the action failed or succeeded.
  6. 06Supported controlA supported revision-bound claimA bounded claim names its passing check, exact reviewed Git revision and touched paths, and the repository state matches the record.