Show HN: AI image models hallucinate history, we built a method to fix it it
TL;DR
We created 24 image prompts across 3 characters living in Rome, 110 CE. Each prompt has a naive version and a culturally-grounded version enhanced by the Triad Engine (structured domain knowledge injection). Same model, same pipeline, only the prompt changes. A blinded Gemini Vision judge scores each pair without knowing which is which.
Nauti's Take
Image models don't know history — they know pixels. The Triad Engine exposes a brutal truth: feeding an AI 'dextrarum iunctio' is like speaking Latin to a golden retriever.
Translate concepts into visual primitives, and accuracy jumps from 12.5% to 83.3%.
Briefingshow
Prompt engineers must act as visual translators: historical or domain-specific terminology silently fails — describe the visual outcome, not the concept.
Sources