Standing on a Trapdoor: AI Hallucination and Prompt-Level Cost Restructuring

Abstract

AI hallucination is a cost problem, not a knowledge problem. This paper documents that three sentences of prompt-level instruction — IDK+COMP: a compression mandate paired with a refusal permission — reproduce hallucination suppression matching or exceeding a full multi-constraint methodology across three frontier AI models. Gemini: 6.3% hallucination rate (Baseline 57.5%). ChatGPT: 0.0% (Baseline 22.2%). Claude: 0.0%. The paper establishes hallucination as a utility-maximizing response to a cost structure that makes confident invention cheaper than refusal. Change the cost structure at the prompt level — without touching the model, without retraining, at near-zero cost — and the behavior changes. IDK is load-bearing. The compression mandate is the environment in which it operates. Secondary findings: hedging is not a mitigation — it is a co-symptom of unresolved uncertainty, and this dataset moves the hedge-hallucination relationship in both directions depending on directive design. Plausibility-trap strings (SPLAM, Vandermeer Effect) expose the limit of cost-structure interventions: the model cannot recognize the unrecognizable. In a plausibility-trap domain, IDK+COMP is worse than nothing. 410 trials. Three frontier AI models. Five governance conditions. Proof-of-concept dataset; results are directional. Companion paper: Kowalski et al. (2026a), "A Puma in a Teacup: Signal Quality and Hallucination Suppression Through Prompt-Level Incentive Restructuring." https://doi.org/10.5281/zenodo.19502460