The AI Epileptic - Invidious

The AI Epileptic

Award-quality AI documentaries and in-depth courses exploring the complete history, science, and future of artificial intelligence.

AI DOCUMENTARY SERIES:
1. The Machine That Dreams - The complete history of AI
2. The Reward Signal - The untold story of reinforcement learning
3. The Reward Frontier - State-of-the-art RL
4. The Future of AI - AGI, alignment, and what comes next

THE ESSENCE OF REINFORCEMENT LEARNING (Course):
A 40-episode course covering RL from first principles to deep RL and RLHF for language models. Animated diagrams, mathematical notation, worked examples, and clear explanations in every episode.

EP1: The Learning Loop
EP2: Markov Decision Processes
EP3: Value Functions and The Bellman Equation

New episodes released regularly. Subscribe and turn on notifications.

All content features professional narration, cinematic motion graphics, and AI-generated artwork.

View channel on YouTube

Switch Invidious Instance

Videos

newest

oldest

popular

1:15:58

What Is Consciousness? | The Hard Problem of Mind | 75-Minute AI Sleep Documentary

The AI Epileptic

Shared 5 days ago

2K views

2:34

Claude Mythos — The AI Too Dangerous to Release

The AI Epileptic

Shared 1 week ago

4K views

18:16

The Urgency of Interpretability — Dario Amodei Essay Analysis

The AI Epileptic

Shared 1 week ago

3.2K views

7:20

Code: A Deep Dive — The Methodology | Claude Code Production System

The AI Epileptic

Shared 3 weeks ago

8.9K views

1:30:18

What Is Memory? | 90 Minutes of AI Philosophy for Sleep

The AI Epileptic

Shared 1 month ago

4.8K views

2:18

The Claude Code Leak — How One Missing Line Exposed 512,000 Lines of Source Code

The AI Epileptic

Shared 1 month ago

4.1K views

25:27

The Next Word — The Complete History of Large Language Models

The AI Epileptic

Shared 1 month ago

4K views

1:06:36

What Is Intelligence? | One Hour of AI Philosophy for Sleep

The AI Epileptic

Shared 1 month ago

5.3K views

12:12

Linear Function Approximation — From Tables to Weights | RL Course EP10

The AI Epileptic

Shared 1 month ago

4.3K views

1:32:36

What Is a Mind? | 90 Minutes of AI Philosophy for Sleep

The AI Epileptic

Shared 1 month ago

9K views

13:15

The Curse of Dimensionality — Why Q-Tables Fail at Scale | RL Course EP9

The AI Epileptic

Shared 1 month ago

4.7K views

2:16

10,000 Subscribers — Thank You From The AI Epileptic

The AI Epileptic

Shared 1 month ago

93 views

28:52

Is AI Making Us Dumber? | Claude vs GPT vs Gemini vs Grok Debate

The AI Epileptic

Shared 1 month ago

5.2K views

13:29

Exploration Strategies — UCB, Boltzmann & Thompson Sampling | RL Course EP8

The AI Epileptic

Shared 1 month ago

4.9K views

1:56

How Tiny AI Models Are Beating Giants | 9B vs 120B

The AI Epileptic

Shared 2 months ago

10K views

29:51

Is the AI Bubble About to Burst? | AI Roundtable EP03

The AI Epileptic

Shared 2 months ago

5K views

2:35

Anthropic vs the Pentagon -- The AI War Nobody Expected

The AI Epileptic

Shared 2 months ago

4.6K views

3:36

AI vs Human Brain — Who Wins?

The AI Epileptic

Shared 2 months ago

7.5K views

10:56

TD Control — SARSA & Q-Learning | RL Course EP7

The AI Epileptic

Shared 2 months ago

4.1K views

18:40

Will Software Engineers Exist in 2028? | 4 AI Models Debate

The AI Epileptic

Shared 2 months ago

3.9K views

19:55

Is AGI Really 5 Years Away? Claude, GPT, Gemini & Grok Debate | AI Roundtable EP01

The AI Epileptic

Shared 2 months ago

8K views

12:21

Temporal Difference Learning — The Algorithm Behind Modern AI | RL Course EP6

The AI Epileptic

Shared 2 months ago

2.3K views

36:26

Machines of Loving Grace | Dario Amodei's Radical Vision for AI (Full Analysis)

The AI Epileptic

Shared 2 months ago

320 views

25:49

The Code That Writes Itself | The Complete Story of Claude Code (2024-2026)

The AI Epileptic

Shared 2 months ago

261 views

12:30

Monte Carlo Methods — Learning from Experience | RL Course EP5

The AI Epileptic

Shared 2 months ago

631 views

14:02

Dynamic Programming — Solving MDPs from Scratch | RL Course EP4

The AI Epileptic

Shared 2 months ago

271 views

12:16

Value Functions & The Bellman Equation | RL Course EP3

The AI Epileptic

Shared 2 months ago

255 views

12:33

Markov Decision Processes — The Language of RL | RL Course EP2

The AI Epileptic

Shared 2 months ago

286 views

12:09

The Learning Loop — How Agents Learn from Rewards | RL Course EP1

The AI Epileptic

Shared 2 months ago

356 views

29:45

The Future of AI — What Comes Next Will Change Everything | Full AI Documentary 2026

The AI Epileptic

Shared 2 months ago

409 views

19:10

The Machine That Dreams | The Complete History of AI (Full Documentary)

The AI Epileptic

Shared 2 months ago

301 views

24:30

The Reward Signal: A Complete History of Reinforcement Learning | AI Documentary

The AI Epileptic

Shared 2 months ago

287 views

22:04

The Reward Frontier | The State of the Art in Reinforcement Learning (Full Documentary)

The AI Epileptic

Shared 2 months ago

294 views