Retrying the earlier Moby Dick experiment with a more varied selection, including few frontier models.
All articles
Combining procedural generation and LLMs to create a text adventure game.
An experiment testing whether LLMs can reproduce Moby Dick verbatim with mixed results.
Exploring Itô's Lemma and stochastic calculus through numerical simulations rather than complex mathematical proofs.
A simple yet effective test for weeding out unreliable LLMs using eye and hair color descriptions.
Exploring embedding space vulnerabilities through lessons learned from a recent Kaggle competition.
An introduction to tech freelancing with personal experiences from the Netherlands.