Evan Hubinger on Inner Alignment, Outer Alignment, and Proposals for Building Safe Advanced AI Published 2021-06-24 Download video MP4 360p Recommendations 2:16:12 Samuel Hammond on why AI Progress is Accelerating - and how Governments Should Respond 1:00:59 What's the future for generative AI? - The Turing Lectures with Mike Wooldridge 1:21:25 Policy Roundtable | Property Tax 1:32:25 Anton Korinek on Automating Work and the Economics of an Intelligence Explosion 1:13:48 The Alignment Problem: Machine Learning and Human Values with Brian Christian 57:18 Bill Gates Reveals Superhuman AI Prediction 53:40 Paris AI Safety Breakfast with Stuart Russell | July 2024 23:24 The OTHER AI Alignment Problem: Mesa-Optimizers and Inner Alignment 1:03:11 Anousheh Ansari on Innovation Prizes for Space, AI, Quantum Computing, and Carbon Removal 58:43 The latest developments in fusion energy - with the UKAEA 1:37:37 The Turing Lectures: The future of generative AI 25:34 How AI Is Unlocking the Secrets of Nature and the Universe | Demis Hassabis | TED 1:58:38 Geoffrey Hinton | Will digital intelligence replace biological intelligence? 44:54 Max Tegmark | On superhuman AI, future architectures, and the meaning of human existence 1:00:29 The Rise of The Machines: John Etchemendy and Fei-Fei Li on Our AI Future | Uncommon Knowledge 52:21 Should we slow down AI research? | Debate with Meta, IBM, FHI, FLI 46:02 What is generative AI and how does it work? – The Turing Lectures with Mirella Lapata 45:46 Geoffrey Hinton | On working with Ilya, choosing problems, and the power of intuition 1:04:04 Is Reality a Controlled Hallucination? - with Anil Seth Similar videos 2:06:03 6:How to Build a Safe Advanced AGI?: Evan Hubinger 2023 2:13:32 4 - Risks from Learned Optimization with Evan Hubinger 11:47 We Were Right! Real Inner Misalignment 1:22:35 4:How Do We Become Confident in the Safety of an ML System?: Evan Hubinger 2023 19:35 Anthropic - AI sleeper agents? 17:29 Alignment Newsletter #102: Meta learning by GPT-3, and a list of full proposals for AI alignment 10:20 Deceptive Misaligned Mesa-Optimisers? It's More Likely Than You Think... 1:00:21 Threat Models and Approaches for AI Alignment - Rohin Shah 31:37 What’s been happening in AI alignment? | Rohin Shah | EA Global: Virtual 2020 23:49 AI Research Considerations for Existential Safety 23:15 Artificial Intelligence Career Stories | EA Student Summit 2020 14:12 Alignment Newsletter #107: The convergent instrumental subgoals of goal-directed agents 1:33:30 How safe is AI? Red lines for protecting our fundamental rights 03:19 AI Safety: You Should Be Worried 51:16 Rohin Shah - Effective altruism, AI safety, and learning human preferences from the world's state More results