Watch Queue
Queue
Watch QueueQueue
The next video is starting
Loading...
Watch Queue
Queue
__count__/__total__
-
-
Jessica Taylor – Using Machine Learning to Address AI Risk – EAG 2016 - Duration: 55 minutes.
-
Eliezer Yudkowsky – AI Alignment: Why It's Hard, and Where to Start - Duration: 1 hour, 29 minutes.
-
Andrew Critch - Logical Induction - MIRI Grad Student Seminar F2016 - Duration: 1 hour, 28 minutes.
-
Andrew Critch – Robust Cooperation of Bounded Agents – CSRBAI 2016 - Duration: 56 minutes.
-
Stuart Armstrong – Reduced Impact AI and Other Alternatives to Friendliness – CSRBAI 2016 - Duration: 1 hour, 6 minutes.
-
Stefano Albrecht – Learning to Distinguish Between Belief and Truth – CSRBAI 2016 - Duration: 45 minutes.
-
Michael Wellman – Autonomous Agents in Financial Markets: Implications and Risks – CSRBAI 2016 - Duration: 1 hour, 2 minutes.
-
Andrew Critch – Logical Induction (technical portion) - Duration: 36 minutes.
-
Andrew Critch – Logical Induction – EAG 2016 - Duration: 1 hour.
-
Bas Steunebrink – About Understanding, Meaning, and Values – CSRBAI 2016 - Duration: 1 hour, 7 minutes.
-
Jan Leike – General Reinforcement Learning – CSRBAI 2016 - Duration: 58 minutes.
-
Dylan Hadfield-Menell – The Off-Switch – CSRBAI 2016 - Duration: 1 hour, 18 minutes.
-
Tom Everitt – Avoiding Wireheading with Value Reinforcement Learning – CSRBAI 2016 - Duration: 57 minutes.
-
Stefano Ermon – Probabilistic Inference and Accuracy Guarantees – CSRBAI 2016 - Duration: 1 hour, 11 minutes.
-
Jessica Taylor – Alignment for Advanced Machine Learning Systems – CSRBAI 2016 - Duration: 57 minutes.
-
Bart Selman – Non-Human Intelligence – CSRBAI 2016 - Duration: 48 minutes.
-
Paul Christiano – Training an Aligned RL Agent – CSRBAI 2016 - Duration: 1 hour, 2 minutes.
-
Jim Babcock – The AGI Containment Problem – CSRBAI 2016 - Duration: 52 minutes.
-
Francesca Rossi – Moral Preferences – CSRBAI 2016 - Duration: 53 minutes.
-
Alan Fern – Toward Recognizing and Explaining Uncertainty – CSRBAI 2016 - Duration: 54 minutes.
-
Stuart Russell – AI: The Story So Far – CSRBAI 2016 - Duration: 1 hour, 3 minutes.
-
Risk Averse Preferences as an AGI Safety Technique - Carl Shulman & Anna Salamon - Duration: 8 minutes, 40 seconds.
-
Whole Brain Emulation as a Platform for Creating Safe AGI - Anna Salamon & Carl Shulman - Duration: 10 minutes.
-
Paul Christiano on Probabilistic Metamathematics and the Definability of Truth - Duration: 57 minutes.
-
