Machine Intelligence Research Institute | Poke

Machine Intelligence Research Institute @UCutigUZUpKrIMOte27SDmEg@youtube.com

3.4K subscribers - no pronouns :c

MIRI is a non-profit organization, based in Berkeley, CA, th

Videos Playlists

Recently Uploaded Popular Oldest

Scott Garrabrant – Finite Factored Sets

Scott Garrabrant – Cartesian Frames

Jessica Taylor – Using Machine Learning to Address AI Risk – EAG 2016

Eliezer Yudkowsky – AI Alignment: Why It's Hard, and Where to Start

Andrew Critch - Logical Induction - MIRI Grad Student Seminar F2016

Andrew Critch – Robust Cooperation of Bounded Agents – CSRBAI 2016

Stuart Armstrong – Reduced Impact AI and Other Alternatives to Friendliness – CSRBAI 2016

Stefano Albrecht – Learning to Distinguish Between Belief and Truth – CSRBAI 2016

Michael Wellman – Autonomous Agents in Financial Markets: Implications and Risks – CSRBAI 2016

Andrew Critch – Logical Induction – EAG 2016

Andrew Critch – Logical Induction (technical portion)

Bas Steunebrink – About Understanding, Meaning, and Values – CSRBAI 2016

Jan Leike – General Reinforcement Learning – CSRBAI 2016

Dylan Hadfield-Menell – The Off-Switch – CSRBAI 2016

Tom Everitt – Avoiding Wireheading with Value Reinforcement Learning – CSRBAI 2016

Stefano Ermon – Probabilistic Inference and Accuracy Guarantees – CSRBAI 2016

Jessica Taylor – Alignment for Advanced Machine Learning Systems – CSRBAI 2016

Bart Selman – Non-Human Intelligence – CSRBAI 2016

Paul Christiano – Training an Aligned RL Agent – CSRBAI 2016

Jim Babcock – The AGI Containment Problem – CSRBAI 2016

Francesca Rossi – Moral Preferences – CSRBAI 2016

Alan Fern – Toward Recognizing and Explaining Uncertainty – CSRBAI 2016

Stuart Russell – AI: The Story So Far – CSRBAI 2016

Risk Averse Preferences as an AGI Safety Technique - Carl Shulman & Anna Salamon

Whole Brain Emulation as a Platform for Creating Safe AGI - Anna Salamon & Carl Shulman

Paul Christiano on Probabilistic Metamathematics and the Definability of Truth