At 16, Eliezer Yudkowsky wanted to build a superintelligence as fast as possible. He assumed a syste
Machine Intelligence Research Institute
At 16, Eliezer Yudkowsky wanted to build a superintelligence as fast as possible. He assumed a syste
0:47
3 Reasons Why A Superintelligent AI Would Kill Us All
Machine Intelligence Research Institute
3 Reasons Why A Superintelligent AI Would Kill Us All
1:33
AI Companies Don't Know How AIs Work
Machine Intelligence Research Institute
AI Companies Don't Know How AIs Work
0:52
Signs That AI Can Lead To Human Extinction
Machine Intelligence Research Institute
Signs That AI Can Lead To Human Extinction
0:57
AIs are growing drives nobody wanted in there.
Machine Intelligence Research Institute
AIs are growing drives nobody wanted in there.
0:42
Superintelligence Should be Banned
Machine Intelligence Research Institute
Superintelligence Should be Banned
1:01
This is why AI is scary and dangerous.
Machine Intelligence Research Institute
This is why AI is scary and dangerous.
0:42
Is AI really a bubble?
Machine Intelligence Research Institute
Is AI really a bubble?
1:07
What it means for an AI to “want” something?
Machine Intelligence Research Institute
What it means for an AI to “want” something?
1:17
The Origins Of The Term "AI Alignment"
Machine Intelligence Research Institute
The Origins Of The Term "AI Alignment"
2:16
Why you should take the possibility of superhuman AI seriously.
Machine Intelligence Research Institute
Why you should take the possibility of superhuman AI seriously.
0:50
Why artificial intelligence could surpass human intelligence.
Machine Intelligence Research Institute
Why artificial intelligence could surpass human intelligence.
1:35
We Need To Track Every AI Chip
Machine Intelligence Research Institute
We Need To Track Every AI Chip
2:41
In Silicon Valley, everyone looks like they have seen a ghost.
Machine Intelligence Research Institute
In Silicon Valley, everyone looks like they have seen a ghost.
0:31
How the world could halt the AI race (part 2)
Machine Intelligence Research Institute
How the world could halt the AI race (part 2)
2:13
Why (and how) we should halt the development of superhuman AI
Machine Intelligence Research Institute
Why (and how) we should halt the development of superhuman AI
2:23
Scott Garrabrant – Finite Factored Sets
Machine Intelligence Research Institute
Scott Garrabrant – Finite Factored Sets
1:00:07
Scott Garrabrant – Cartesian Frames
Machine Intelligence Research Institute
Scott Garrabrant – Cartesian Frames
1:05:24
Jessica Taylor – Using Machine Learning to Address AI Risk – EAG 2016
Machine Intelligence Research Institute
Jessica Taylor – Using Machine Learning to Address AI Risk – EAG 2016
55:04
Eliezer Yudkowsky – AI Alignment: Why It's Hard, and Where to Start
Machine Intelligence Research Institute
Eliezer Yudkowsky – AI Alignment: Why It's Hard, and Where to Start
1:29:56
Andrew Critch - Logical Induction - MIRI Grad Student Seminar F2016
Machine Intelligence Research Institute
Andrew Critch - Logical Induction - MIRI Grad Student Seminar F2016
1:28:16
Andrew Critch – Robust Cooperation of Bounded Agents – CSRBAI 2016
Machine Intelligence Research Institute
Andrew Critch – Robust Cooperation of Bounded Agents – CSRBAI 2016
56:13
Stuart Armstrong – Reduced Impact AI and Other Alternatives to Friendliness – CSRBAI 2016
Machine Intelligence Research Institute
Stuart Armstrong – Reduced Impact AI and Other Alternatives to Friendliness – CSRBAI 2016
1:06:18
Stefano Albrecht – Learning to Distinguish Between Belief and Truth – CSRBAI 2016
Machine Intelligence Research Institute
Stefano Albrecht – Learning to Distinguish Between Belief and Truth – CSRBAI 2016
45:40
Michael Wellman – Autonomous Agents in Financial Markets: Implications and Risks – CSRBAI 2016
Machine Intelligence Research Institute
Michael Wellman – Autonomous Agents in Financial Markets: Implications and Risks – CSRBAI 2016
1:02:08
Andrew Critch – Logical Induction (technical portion)
Machine Intelligence Research Institute
Andrew Critch – Logical Induction (technical portion)
36:29
Andrew Critch – Logical Induction – EAG 2016
Machine Intelligence Research Institute
Andrew Critch – Logical Induction – EAG 2016
1:01:08
Bas Steunebrink – About Understanding, Meaning, and Values – CSRBAI 2016
Machine Intelligence Research Institute
Bas Steunebrink – About Understanding, Meaning, and Values – CSRBAI 2016
1:07:44
Jan Leike – General Reinforcement Learning – CSRBAI 2016
Machine Intelligence Research Institute
Jan Leike – General Reinforcement Learning – CSRBAI 2016
58:03
Dylan Hadfield-Menell – The Off-Switch – CSRBAI 2016
Machine Intelligence Research Institute
Dylan Hadfield-Menell – The Off-Switch – CSRBAI 2016
1:18:49
Tom Everitt – Avoiding Wireheading with Value Reinforcement Learning – CSRBAI 2016
Machine Intelligence Research Institute
Tom Everitt – Avoiding Wireheading with Value Reinforcement Learning – CSRBAI 2016
57:37
Stefano Ermon – Probabilistic Inference and Accuracy Guarantees – CSRBAI 2016
Machine Intelligence Research Institute
Stefano Ermon – Probabilistic Inference and Accuracy Guarantees – CSRBAI 2016
1:11:17
Jessica Taylor – Alignment for Advanced Machine Learning Systems – CSRBAI 2016
Machine Intelligence Research Institute
Jessica Taylor – Alignment for Advanced Machine Learning Systems – CSRBAI 2016
57:41
Bart Selman – Non-Human Intelligence – CSRBAI 2016
Machine Intelligence Research Institute
Bart Selman – Non-Human Intelligence – CSRBAI 2016
48:52
Paul Christiano – Training an Aligned RL Agent – CSRBAI 2016
Machine Intelligence Research Institute
Paul Christiano – Training an Aligned RL Agent – CSRBAI 2016
1:02:23
Jim Babcock – The AGI Containment Problem – CSRBAI 2016
Machine Intelligence Research Institute
Jim Babcock – The AGI Containment Problem – CSRBAI 2016
52:07
Francesca Rossi – Moral Preferences – CSRBAI 2016
Machine Intelligence Research Institute
Francesca Rossi – Moral Preferences – CSRBAI 2016
53:49
Alan Fern – Toward Recognizing and Explaining Uncertainty – CSRBAI 2016
Machine Intelligence Research Institute
Alan Fern – Toward Recognizing and Explaining Uncertainty – CSRBAI 2016
54:31
Stuart Russell – AI: The Story So Far – CSRBAI 2016
Machine Intelligence Research Institute
Stuart Russell – AI: The Story So Far – CSRBAI 2016
1:03:21
Risk Averse Preferences as an AGI Safety Technique - Carl Shulman & Anna Salamon
Machine Intelligence Research Institute
Risk Averse Preferences as an AGI Safety Technique - Carl Shulman & Anna Salamon
8:40
Whole Brain Emulation as a Platform for Creating Safe AGI - Anna Salamon & Carl Shulman
Machine Intelligence Research Institute
Whole Brain Emulation as a Platform for Creating Safe AGI - Anna Salamon & Carl Shulman
10:36
Paul Christiano on Probabilistic Metamathematics and the Definability of Truth
Machine Intelligence Research Institute
Paul Christiano on Probabilistic Metamathematics and the Definability of Truth
57:12