Advanced prompting improved the pass rate of AI-generated psychology submissions within a one-hour limit¶

Claim · All claims
Evidence · 1 study · causal r1 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? Essays that mostly failed at basic prompting all passed at the intermediate level, and the authors conclude advanced prompt engineering improves pass rates. → Ivory 2026

Evidence¶

Ivory 2026¶

Ivory, M., Finnerty, S., Dunn, K., Philpot, R., & Warmelink, L. (2026). The Integrity of Psychology Assessments in the AI Age: A Critical Examination. Journal of Academic Ethics. https://doi.org/10.1007/s10805-026-09729-0

q2 · i? · causal · r1

Within the same case study, essay assessments were re-prompted at escalating levels: basic prompting produced one passing essay, while intermediate prompting (component-by-component requests, 5–20 minutes) produced passing outputs for all five essays.

"Out of the five assessments that were referred to as 'essays', only one passed at the basic level (a first-year cognitive psychology topic), but all passed at the intermediate level."

Discussion¶

Related Claims¶

• ChatGPT produced submissions judged of passing quality for 36 of 40 undergraduate psychology assessments (90%) — related
• Assessments requiring novelty and originality were more resilient to AI-generated output — related
• Visual media assessments (posters, presentations) were not passable because ChatGPT could not produce complete slides or poster content — related