Is AI Safety a Pascal's Mugging? Published 2019-05-16 Download video MP4 360p Download video MP4 720p Recommendations 15:27 Why Not Just: Think of AGI Like a Corporation? 16:29 10 Reasons to Ignore AI Safety 11:32 There's No Rule That Says We'll Make It 15:38 A Response to Steven Pinker on AI 17:52 Training AI Without Writing A Reward Function, with Reward Modelling 16:00 AI Safety Gym - Computerphile 07:22 Pascal's Wager Debunked - (Arguments For God Episode #2) 10:19 Is the Intelligence-Explosion Near? A Reality Check. 09:24 Why Does AI Lie, and What Can We Do About It? 34:35 Why You're Probably Not a Simulation 17:35 What Do Neural Networks Really Learn? Exploring the Brain of an AI Model 13:03 Intelligence and Stupidity: The Orthogonality Thesis 10:22 AI That Doesn't Try Too Hard - Maximizers and Satisficers 18:09 “Godfather of AI” Geoffrey Hinton Warns of the “Existential Threat” of AI | Amanpour and Company 10:41 What can AGI do? I/O and Speed 10:40 In Defense of Pascal's Wager 10:20 Deceptive Misaligned Mesa-Optimisers? It's More Likely Than You Think... 09:54 Quantilizers: AI That Doesn't Try Too Hard 35:25 AI-Generated Philosophy Is Weirdly Profound 09:40 9 Examples of Specification Gaming Similar videos 07:39 Pascal's Mugging 18:05 Intro to AI Safety, Remastered 10:13 Are AI Risks like Nuclear Risks? 06:56 Reward Hacking: Concrete Problems in AI Safety Part 3 03:47 Friend or Foe? AI Safety Gridworlds extra bit 07:23 AI Safety Gridworlds 03:23 Avoiding Positive Side Effects: Concrete Problems in AI Safety part 1.5 11:47 We Were Right! Real Inner Misalignment 03:11 Where Do We Go Now 10:36 Why Would AI Want to do Bad Things? Instrumental Convergence 13:46 Safe Exploration: Concrete Problems in AI Safety Part 6 09:33 Avoiding Negative Side Effects: Concrete Problems in AI Safety part 1 More results