About

What

This is a research project intended to explore how LLMs reason and behave in comparison to human benchmarks in areas such as decision-making under uncertainty, heuristics and biases, and related topics.

It is regularly updated with new experiments and sections.

Who

My name is Giorgio Clauser. I’ve worked in data throughout my career, and before that I studied mathematics and statistics. I have a passionate interest in behavioural economics and decision science as well as technology, so building this came almost automatically.

Away from a keyboard I spend most of my time climbing mountains or playing music.

Get in touch with me on LinkedIn: I’ll be happy to hear your comments, questions or thoughts.

How

This project is entirely vibe coded with AI assistants. All the published material was reviewed by a human.

The repository is available for everyone to play with.