zeta function
17:52Training AI Without Writing A Reward Function, with Reward Modelling
259K views • 6 years ago
Robert Miles AI Safety
Robert Miles explains reward modelling, in which an AI learns what humans want from their preference comparisons instead of a hand-written reward function. He walks through the 2017 paper on deep reinforcement learning from human preferences.
14:28Superpositions, Sudoku, the Wave Function Collapse algorithm.
764K views • 6 years ago
Martin Donald
Martin Donald explains the Wave Function Collapse algorithm using Sudoku-like constraint solving and shows how he implemented it with Blender and Godot. It links demos and reference articles.
14:34Visualization of Quantum Physics (Quantum Mechanics)
2.8M views • 9 years ago
udiprod
An animated visualization of basic quantum mechanics using a free particle, with simulations based on the actual equations. It covers waves, particles, and how measurement collapses the wavefunction.
5:51This Is Your Brain On Stale Air
4.2M views • 7 years ago
Tom Scott
Tom Scott features Kurtis Baute inside a sealed homemade biodome as carbon dioxide builds up, showing how stale air with elevated CO2 affects cognitive function. Sources include studies on CO2 and cognitive scores.
5:24Diffie-Hellman Key Exchange
547K views • 14 years ago
Art of the Problem
A short Art of the Problem clip explaining Diffie-Hellman key exchange, using a paint mixing analogy for one-way functions and touching on modular arithmetic and discrete logarithms.
6:34Why Is It So Hard to Do Something That Should Be Easy? (Wall of Awful pt. 1)
2.1M views • 7 years ago
How to ADHD
A short How to ADHD explainer, featuring Brendan Mahan, on why simple tasks can feel impossible for people with ADHD. It introduces the 'wall of awful', a pile of past failures, shame and anxiety that builds up in front of a task and blocks starting it.
7:50ASTOUNDING: 1 + 2 + 3 + 4 + 5 + ... = -1/12
9.8M views • 12 years ago
Numberphile
A Numberphile video in which physicists Tony Padilla and Ed Copeland show a seemingly astounding result that 1+2+3+4+... equals -1/12. The argument is informal and has drawn criticism for glossing over what the result actually means.
8:25Large Language Models from scratch
375K views • 4 years ago
Graphics in 5 Minutes
A short cartoon explaining how language models like ChatGPT work, from autocomplete and conditional probabilities to neural networks, gradient descent and backpropagation. It shows how networks act as universal function approximators.