Writing.

Long-form on AI safety, mechanistic interpretability, building things, and adjacent.

builds essays research safety sports

2025.03.31 Emotion Retrieval through Art in Latent Space essays

2024.05.12 The Benchmark Trap: Why LLM Metrics Mislead and Evals Enlighten research

2024.04.16 Behind the Curve: The Slow March of AI into Classrooms builds

2024.02.02 Artificial Misdirection: Misalignment of LLMs safety

2024.01.19 The Forgotten Lever of Neural Scaling Laws research

2019.01.23 Where Human and Artificial Intelligence meets essays

2018.11.07 Developing an intuition for better understanding of convolutional neural networks research

2017.08.15 Musings on Fate essays

2017.04.20 The United States of America vs Soccer sports

2016.12.13 A Robot Philosopher essays

1
2
»
»»