Ömer Yüksel


All articles

Infinite Zork: when procedural generation meets large language models

Combining procedural generation and LLMs to create a text adventure game.

Published:
Reconstructing Moby-Dick with large language models

An experiment testing whether LLMs can reproduce Moby Dick verbatim with mixed results.

Published:
Understanding Itô's lemma through numerical simulation

Exploring Itô's Lemma and stochastic calculus through numerical simulations rather than complex mathematical proofs.

Published:
The color memory test: a quick filter for language model quality

A simple yet effective test for weeding out unreliable LLMs using eye and hair color descriptions.

Published:
Adversarial inputs in embedding spaces

Exploring embedding space vulnerabilities through lessons learned from a recent Kaggle competition.

Published:
Going freelance in tech

An introduction to tech freelancing with personal experiences from the Netherlands.