#interpretability
7 episodes
#2883: Correlation Beyond Pearson: 5 Techniques You Need
Pearson, Spearman, Kendall, partial, distance correlation — when to use each one and why most people stop too soon.
#2405: LLM Benchmarks Are Full of Noise: Statistical Rigor in AI Evals
Why most benchmark claims in AI are statistically indefensible — and what to do about it.
#2188: Is Emergence Real or Just Bad Metrics?
The debate over whether AI models exhibit genuine emergent abilities or just appear to because of how we measure them—and why it matters for safety...
#1561: Abliteration: The High-Dimensional Lobotomy of AI
Discover how researchers are surgically removing refusal filters from AI models using a mathematical process called abliteration.
#1328: Silicon Sigils: Why We Treat AI Like an Occult Force
Is AI a tool or a digital demon? Explore why technical illiteracy is turning neural networks into a modern-day moral panic.
#1001: The Long Haulers of AI
Think AI started with ChatGPT? Discover the "long haulers" in defense, medicine, and finance who have used machine learning for decades.
#974: The Digital Gardener: Why We Don't Understand Our Own AI
We build digital cathedrals but lack the blueprints. Explore the "black box" of AI, emergent abilities, and the mystery of double descent.