Project Info

Figaro

This project did not submit a demo video on Devpost.

Inspiration

The project is inspired by the question “human or machine?” — whether people can tell art made by humans from art made by AI. It’s a visual guessing game around that idea. Tech stack Frontend: React + Vite. Backend: Express API that calls OpenAI DALL·E 3 for AI images and uses the Met Museum Collection API (public domain) for human art. No API key needed for Met; OpenAI key required for AI generation. What is Figaro? Figaro (Human or Machine?) is a browser game where you guess if each artwork is by a human artist or by AI. Classic Mode: 10 rounds with mixed difficulty and streak bonuses. Speed Mode: 30 seconds, unlimited rounds, with a speed bonus. Challenges Above all, integrating two image sources (Met API vs OpenAI), DALL·E latency/cost, and scheduling and concurrency of prompting, and making AI prompts feel “art-like” so the game is fair and fun.

What we learned

Natural takeaways: combining public-domain art APIs with generative AI in one flow is powerful, and designing prompts so AI images blend with human art in a guessing game. Future features Obvious extensions: more art sources, difficulty levels, leaderboards, and more. Also could be interesting to incorporate human artistic ability therein, as well as possibly extend to establishing a benchmark.

Analysis

Compare with all teams

No indexed repository for this project, so there are no commit stats to show.

Technology

Found in codeNot checked

ExpressUnchecked
JavaScriptUnchecked
ReactUnchecked

No repository was indexed for this project, so these Devpost claims have not been checked against code.

AI coding agents

No repository was indexed, so agent usage could not be checked.

Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.

Codebase size

No repository was indexed, so there is no codebase to measure.