An interactive tool that compares how well different LLMs rewrite Swiss government/administrative text in plain language, checking its own results.
A tool that flags suspicious financial transactions that look like money laundering, and explains why it flagged them.
With Christoph Engel and Yoan Hermstrüwer
Co-authored research asking whether AI chatbots make the same moral choices humans do in classic ethical dilemmas (like the trolley problem), and whether they can be nudged toward more human-like judgment.
Masterful artwork by me using Mac Preview
My Master's thesis: teaching a model to write more human-like text by learning what makes a good word choice, instead of hand-tuning the rules.
