Jan Leike - AI alignment at OpenAI Published 2021-09-29 Download video MP4 360p Recommendations 11:47 We Were Right! Real Inner Misalignment 41:59 No Priors Ep. 39 | With OpenAI Co-Founder & Chief Scientist Ilya Sutskever 1:13:48 The Alignment Problem: Machine Learning and Human Values with Brian Christian 31:37 Current work in AI alignment | Paul Christiano | EA Global: San Francisco 2019 54:44 Ala Shaabana and Jacob Steeves - AI on the blockchain (it actually might just make sense) 1:08:07 Inside OpenAI | Logan Kilpatrick (head of developer relations) 18:00 Googles GEMINI 1.5 Just Surprised EVERYONE! (GPT-4 Beaten Again) Finally RELEASED! 16:18 Decentralized AI | Ben Goertzel | TEDxBerkeley 1:38:24 Yudkowsky vs Hanson — Singularity Debate 06:02 OpenAI Plays Hide and Seek…and Breaks The Game! 🤖 2:56:23 OpenAI’s huge push to make superintelligence safe | Jan Leike 47:41 Ilya Sutskever (OpenAI Chief Scientist) - Building AGI, Alignment, Spies, Microsoft, & Enlightenment 23:24 The OTHER AI Alignment Problem: Mesa-Optimizers and Inner Alignment 13:03 Intelligence and Stupidity: The Orthogonality Thesis 18:17 Can we reach AGI with just LLMs? 23:12 Two robots debate the future of humanity 42:26 Artificial intelligence and algorithms: pros and cons | DW Documentary (AI documentary) 10:20 Deceptive Misaligned Mesa-Optimisers? It's More Likely Than You Think... 21:25 Generative AI Is About To Reset Everything, And, Yes It Will Change Your Life | Forbes 04:45 ArTiFiCiAL iNtELLiGeNcE Similar videos 45:30 #23 - How to actually become an AI alignment researcher, according to Dr Jan Leike 2:56:44 80,000 Hours - Jan Leike on OpenAI’s massive push to make superintelligence safe in 4 years or less 1:06:21 Stanford CS25: V2 I Language and Human Alignment 12:25 The Exciting, Perilous Journey Toward AGI | Ilya Sutskever | TED 12:05 Will Superintelligent AI Get Out Of Control? | OpenAI's New Superalignment Team 13:35 'Show Your Working': ChatGPT Performance Doubled w/ Process Rewards (+Synthetic Data Event Horizon) 1:29:56 Eliezer Yudkowsky – AI Alignment: Why It's Hard, and Where to Start 1:30:11 Building Aligned AI 09:44 How OpenAI's Super Alignment Team Is FIGHTING With The Ethical Dilemma Of AI More results