Projects

A live experiment studying how game difficulty affects player behavior. Play the memory game, contribute real data, and explore the published statistical analysis.

Analyze your Claude AI conversation history. Discover your prompting style, persona classification, and get a shareable wrapped-style report.

Evaluate local LLM accuracy on structured data extraction. Tests models' ability to extract JSON from unstructured text with ground-truth comparison, F1 scoring, and fuzzy matching. Supports MLX and Ollama backends.