The Alignment Problem: Machine Learning and Human Values with Brian Christian Published 2022-04-06 Download video MP4 360p Recommendations 1:30:39 Causality at the Intersection of Simulation, Inference, Science, and Learning, Conversation 1:29:56 Eliezer Yudkowsky – AI Alignment: Why It's Hard, and Where to Start 1:20:34 Yale Architecture: "Kairos, Chronos, Time, and Space: Designing for Humans in a Digital World" 25:47 Harvard Professor Explains Algorithms in 5 Levels of Difficulty | WIRED 23:24 The OTHER AI Alignment Problem: Mesa-Optimizers and Inner Alignment 1:18:10 What Kind of Computation Is Cognition? 1:40:45 What is a ‘Cause,’ and Why Does it Happen Before the Effect? Carlo Rovelli 42:30 Full interview: "Godfather of artificial intelligence" talks impact and potential of AI 1:35:09 MIT AGI: Building machines that see, learn, and think like people (Josh Tenenbaum) 31:37 Current work in AI alignment | Paul Christiano | EA Global: San Francisco 2019 54:54 The Physics and Philosophy of Time - with Carlo Rovelli 51:31 11. Introduction to Machine Learning 1:29:57 Stuart Russell, "AI: What If We Succeed?" April 25, 2024 1:27:21 CBMM10 Panel: Research on Intelligence in the Age of AI 50:41 Lectures: Exploring the Psychology of Creativity 1:09:12 Sal Khan: How AI Will Revolutionize Education 2:01:16 Max Tegmark lecture on Life 3.0 – Being Human in the age of Artificial Intelligence 46:02 What is generative AI and how does it work? – The Turing Lectures with Mirella Lapata 52:08 Connor Leahy on the State of AI and Alignment Research Similar videos 58:11 The Alignment Problem: Machine Learning and Human Values 58:26 The Alignment Problem - Brian Christian 1:32:39 BI 098 Brian Christian: The Alignment Problem 1:01:43 How Can Machines Learn Human Values? - with Brian Christian 00:42 Unwind Your AI Anxiety The Alignment Problem by Brian Christian 1:00:43 CDAC Distinguished Speaker Series - Brian Christian 01:39 What happens if AI alignment goes wrong, explained by Gilfoyle of Silicon valley. More results