45:59

AI Ruined My Year

09:24

Why Does AI Lie, and What Can We Do About It?

11:47

We Were Right! Real Inner Misalignment

18:05

Intro to AI Safety, Remastered

10:20

Deceptive Misaligned Mesa-Optimisers? It's More Likely Than You Think...

23:24

The OTHER AI Alignment Problem: Mesa-Optimizers and Inner Alignment

09:54

Quantilizers: AI That Doesn't Try Too Hard

11:44

Sharing the Benefits of AI: The Windfall Clause

16:29

10 Reasons to Ignore AI Safety

09:40

9 Examples of Specification Gaming

17:52

Training AI Without Writing A Reward Function, with Reward Modelling

10:22

AI That Doesn't Try Too Hard - Maximizers and Satisficers

13:41

Is AI Safety a Pascal's Mugging?

15:38

A Response to Steven Pinker on AI

11:32

How to Keep Improving When You're Better Than Any Teacher - Iterated Distillation and Amplification

15:27

Why Not Just: Think of AGI Like a Corporation?

13:46

Safe Exploration: Concrete Problems in AI Safety Part 6

03:47

Friend or Foe? AI Safety Gridworlds extra bit

07:23

AI Safety Gridworlds

06:47

Experts' Predictions about the Future of AI

10:36

Why Would AI Want to do Bad Things? Instrumental Convergence

01:04:40

Superintelligence Mod for Civilization V

13:03

Intelligence and Stupidity: The Orthogonality Thesis

05:03

Scalable Supervision: Concrete Problems in AI Safety Part 5

05:30

AI Safety at EAGlobal2017 Conference

05:20

AI learns to Create ̵K̵Z̵F̵ ̵V̵i̵d̵e̵o̵s̵ Cat Pictures: Papers in Two Minutes #1

10:41

What can AGI do? I/O and Speed

09:38

What Can We Do About Reward Hacking?: Concrete Problems in AI Safety Part 4

07:32

Reward Hacking Reloaded: Concrete Problems in AI Safety Part 3.5

05:51

The other "Killer Robot Arms Race" Elon Musk should worry about

06:56

Reward Hacking: Concrete Problems in AI Safety Part 3

05:51

Why Not Just: Raise AI Like Kids?

06:33

Empowerment: Concrete Problems in AI Safety part 2

03:23

Avoiding Positive Side Effects: Concrete Problems in AI Safety part 1.5

09:33

Avoiding Negative Side Effects: Concrete Problems in AI Safety part 1

10:13

Are AI Risks like Nuclear Risks?

05:04

Respectability

08:17

Predicting AI: RIP Prof. Hubert Dreyfus

07:04

What's the Use of Utility Functions?

07:45

Where do we go now?

01:26

Status Report

01:05

Channel Introduction