Hallucination Identification

The Hallucination Identification project merges the aesthetic of a classical library with the modern need for AI literacy, creating an interactive “reading room” where users practice identifying confidently presented but incorrect AI-generated claims. Inspired by the phenomenon of AI hallucinations, the project addresses how polished language and technical jargon can obscure inaccuracies, encouraging slow, critical reading through a Victorian-style “archive” experience framed as a game of spotting falsehoods. Built using Tailwind CSS for responsive design, custom CSS effects for an immersive, dimly lit atmosphere, and JavaScript for tactile interactivity, the platform balances vintage aesthetics with modern functionality. Key challenges included maintaining readability amid complex visual design and understanding the psychology of belief, revealing that users often trust authoritative-sounding text regardless of accuracy. Ultimately, the project underscores that detecting misinformation is less about factual recall and more about developing sensitivity to the patterns and cadence of misleading information.

Built With

• css
• express.js
• gemini
• html
• javascript
• node.js