Videos

From Stampy's Wiki

These are all the videos we have pages for.

Intelligence and Stupidity: The Orthogonality Thesis (Questions: 260)
The OTHER AI Alignment Problem: Mesa-Optimizers and Inner Alignment (Questions: 202)
AI That Doesn't Try Too Hard - Maximizers and Satisficers (Questions: 200)
Quantilizers: AI That Doesn't Try Too Hard (Questions: 196)
Is AI Safety a Pascal's Mugging? (Questions: 166)
We Were Right! Real Inner Misalignment (Questions: 155)
10 Reasons to Ignore AI Safety (Questions: 144)
Sharing the Benefits of AI: The Windfall Clause (Questions: 133)
Why Not Just: Raise AI Like Kids? (Questions: 122)
Training AI Without Writing A Reward Function, with Reward Modelling (Questions: 107)
Intro to AI Safety, Remastered (Questions: 99)
Why Would AI Want to do Bad Things? Instrumental Convergence (Questions: 92)
A Response to Steven Pinker on AI (Questions: 86)
9 Examples of Specification Gaming (Questions: 82)
Deceptive Misaligned Mesa-Optimisers? It's More Likely Than You Think... (Questions: 71)
Why Not Just: Think of AGI Like a Corporation? (Questions: 66)
Avoiding Negative Side Effects: Concrete Problems in AI Safety part 1 (Questions: 64)
What can AGI do? I/O and Speed (Questions: 54)
Where do we go now? (Questions: 50)
How to Keep Improving When You're Better Than Any Teacher - Iterated Distillation and Amplification (Questions: 50)
Safe Exploration: Concrete Problems in AI Safety Part 6 (Questions: 47)
Experts' Predictions about the Future of AI (Questions: 45)
Reward Hacking: Concrete Problems in AI Safety Part 3 (Questions: 43)
The other "Killer Robot Arms Race" Elon Musk should worry about (Questions: 42)
What's the Use of Utility Functions? (Questions: 40)
What Can We Do About Reward Hacking?: Concrete Problems in AI Safety Part 4 (Questions: 34)
Reward Hacking Reloaded: Concrete Problems in AI Safety Part 3.5 (Questions: 33)
Are AI Risks like Nuclear Risks? (Questions: 28)
Superintelligence Mod for Civilization V (Questions: 27)
Empowerment: Concrete Problems in AI Safety part 2 (Questions: 25)
Avoiding Positive Side Effects: Concrete Problems in AI Safety part 1.5 (Questions: 20)
AI Safety Gridworlds (Questions: 19)
Predicting AI: RIP Prof. Hubert Dreyfus (Questions: 19)
Respectability (Questions: 14)
Scalable Supervision: Concrete Problems in AI Safety Part 5 (Questions: 14)
AI learns to Create ̵K̵Z̵F̵ ̵V̵i̵d̵e̵o̵s̵ Cat Pictures: Papers in Two Minutes (Questions: 13)
Friend or Foe? AI Safety Gridworlds extra bit (Questions: 11)
Channel Introduction (Questions: 10)
Status Report (Questions: 7)
AI Safety at EAGlobal2017 Conference (Questions: 5)
MAXIMUM OVERGEORGIA (Questions: 2)
PC Build Video! (Questions: 0)
Untitled2 (Questions: 0)
Reading and Commenting On Pinker's Article (Questions: 0)
"Don't Fear The Terminator" - Yann LeCun on Facebook (Questions: 0)
Much Better Stampy Test Video (Questions: 0)