top of page

RATIONAL ANIMATIONS

Could a single alien message destroy us?
The King and the Golem
That Alien Message
What Do Neural Networks Really Learn? Exploring the Brain of an AI Model
What if we could redesign society from scratch? The promise of charter cities
S-Risks: Fates Worse Than Extinction
Goal Misgeneralization: How a Tiny Change Could End Everything
What happens if AI just keeps getting smarter?
When will AI automate all mental work, and how fast?
The True Story of How GPT-2 Became Maximally Lewd
Sorting Pebbles Into Correct Heaps - A Short Story By Eliezer Yudkowsky
Predicting the future with the power of the Internet (and pissing off Rob Miles)
How to Eradicate Global Extreme Poverty
The Parable of the Dagger
How to Take Over the Universe (in Three Easy Steps)
500 Million, But Not A Single One More
The Hidden Complexity of Wishes
Will AI kill everyone? Here's what the godfathers of AI have to say
How One Career Can Save a Million Lives
How to Upload a Mind (In Three Not-So-Easy Steps)
The world is awful. The world is much better. The world can be much better.
AI Sleeper Agents: How Anthropic Trains and Catches Them
The Goddess of Everything Else
Can knowledge hurt you? The danger of infohazards (and exfohazards)
This May Be Humanity’s Hardest Challenge
What a 100-year-old horse teaches us about AI
How to Align AI: Put It in a Sandwich
AI Sleeper Agents: How Anthropic Trains and Catches Them
AI could be a tool for global control (plus other major AI risks)
The dumbest AI taught the smartest AI. Here’s how that went…
bottom of page