Records of the !mmortal Data Scientist
Notes on AI, math, and the long road. Live slow, die whenever.
Long-form pieces on machine learning interpretability, kernel methods, contrastive learning, and the geometry of neural network representations. Most posts ship with interactive visualisations you can play with in the browser.
2026
- Organizing Randomness: Contrastive Learning in JAX
- Untangling the Moons: A Visual History of Contrastive Learning
- What an MLP Knows, When It's a Kernel
- Attention is Explainable Because it is a Kernel
- Not All Infinities Are Equal: The Cross-Entropy Asymmetry Behind Hallucination
- Opposite Is Not Different: The Cosine-Similarity Bug in CLIP and Contrastive Learning
- Activations Are Bad for Geometry