Все публикации

0:45:59

AI Ruined My Year

0:01:00

Apply to Study AI Safety Now! #shorts

0:09:24

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

0:00:45

Apply Now for a Paid Residency on Interpretability #short

0:01:00

$100,000 for Tasks Where Bigger AIs Do Worse Than Smaller Ones #short

0:00:52

Free ML Bootcamp for Alignment #shorts

0:01:00

Win $50k for Solving a Single AI Problem? #Shorts

0:01:00

Apply to AI Safety Camp! #shorts

0:11:47

We Were Right! Real Inner Misalignment

0:18:05

Intro to AI Safety, Remastered

0:10:20

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

0:23:24

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

0:09:54

Quantilizers: AI That Doesn't Try Too Hard

0:16:29

10 Reasons to Ignore AI Safety

0:09:40

9 Examples of Specification Gaming

0:17:52

Training AI Without Writing A Reward Function, with Reward Modelling

0:10:22

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

0:13:41

Is AI Safety a Pascal's Mugging?

0:15:38

A Response to Steven Pinker on AI

0:11:32

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

0:03:47

Friend or Foe? AI Safety Gridworlds extra bit

0:07:23

AI Safety Gridworlds

0:06:47

Experts' Predictions about the Future of AI

0:10:36

Why Would AI Want to do Bad Things? Instrumental Convergence