#interpretability
11 episodes
#5260: eXistenZ: The Game That Never Lets You Out
A $15M film that won Berlin's Silver Bear, flopped at $2.8M, and still won't tell you if you've exited the game.
#5175: Vanilla Sky: The Movie That Makes Sense on the Third Watch
A 41% critic score, a D- CinemaScore, and $203M at the box office. How Vanilla Sky became a movie people can't stop rewatching.
#5161: How Statistics Get Misread: A Field Guide
Averages, rates, correlations — the ten categories of statistics most likely to fool a general audience, and why the number is usually right.
#4670: Why AI Weights Are Indecipherable
Can you actually read an AI model's weights like a book? We explore why the answer is mostly no — and what researchers are doing about it.
#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.