Deep Dives

Illustration of vintage diver helmet with octopus tentacles. Design element for poster, card, t shirt. Vector illustration
Youtube
Arrow-alt-circle-up Youtube Users

A collection of Technical explanations (still explained in layman terms), mainly by the one and only Robert Miles.
The list includes detailed explanations of the famous Concrete AI Safety Problems paper published in 2016 and deep explorations of some of the most important topics of the AI Alignment struggle, like the Orthogonality Thesis, Specification Gaming, Reward Hacking, Inner Misalignment and more …

Invest some time to internalise this content and it will become obvious to you, how hard… how far and deep the Alignment Problem cuts and how desperately we, collectively as a species, need to pull our act together and focus all our effort on it, before the AI Race (Moloch) storms the capabilities further ahead beyond the point of no return ….

Part 1 of a Series on AI Safety Research with Rob Miles. Rob heads away from his 'Killer Stamp Collector' example to find a more concrete example of the problem. Sneak Peak at Part 2: https://www.youtube.com/watch?v=3TYT1QfdfsM More about Rob Miles & AI Safety: http://bit.ly/Rob_Miles_YouTube Thanks to Nottingham Hackspace for providing the filming location: http://bit.ly/notthack http://www.facebook.com/computerphile https://twitter.com/computer_phile This video was filmed and edited by Sean Riley. Computer Science at the University of Nottingham: http://bit.ly/nottscomputer Computerphile is a sister project to Brady Haran's Numberphile. More at http://www.bradyharan.com 8:54
General AI Won't Want You To Fix its Code - Computerphile
YouTube Video UExTQ29YT1J1Z25sWXlvaE5kYzBfZVhOaHB5b016OWlWeS4zRDBDOEZDOUM0MDY5NEEz

General AI Won't Want You To Fix its Code - Computerphile

February 28, 2017 9:02 pm

Part 1 of a Series on AI Safety Research with Rob Miles. Rob heads away from his 'Killer Stamp Collector' example to find a more concrete example of the problem.

Sneak Peak at Part 2: https://www.youtube.com/watch?v=3TYT1QfdfsM

More about Rob Miles & AI Safety: http://bit.ly/Rob_Miles_YouTube

Thanks to Nottingham Hackspace for providing the filming location: http://bit.ly/notthack

http://www.facebook.com/computerphile
https://twitter.com/computer_phile

This video was filmed and edited by Sean Riley.

Computer Science at the University of Nottingham: http://bit.ly/nottscomputer

Computerphile is a sister project to Brady Haran's Numberphile. More at http://www.bradyharan.com ...

How do you implement an on/off switch on a General Artificial Intelligence? Rob Miles explains the perils. Part 1: https://www.youtube.com/watch?v=4l7Is6vOAOA Rob's Original Discussions on General AI: https://www.youtube.com/playlist?list=PLzH6n4zXuckquVnQ0KlMDxyT5YE-sA8Ps Stop Button Solution?: https://youtu.be/9nktr1MgS-A More from Rob Miles: http://bit.ly/Rob_Miles_YouTube Thanks to Nottingham Hackspace for providing the filming location: http://bit.ly/notthack http://www.facebook.com/computerphile https://twitter.com/computer_phile This video was filmed and edited by Sean Riley. Computer Science at the University of Nottingham: http://bit.ly/nottscomputer Computerphile is a sister project to Brady Haran's Numberphile. More at http://www.bradyharan.com 20:00
AI "Stop Button" Problem - Computerphile
YouTube Video UExTQ29YT1J1Z25sWXlvaE5kYzBfZVhOaHB5b016OWlWeS5CMEQ2Mjk5NTc3NDZFRUNB

AI "Stop Button" Problem - Computerphile

March 3, 2017 4:32 pm

How do you implement an on/off switch on a General Artificial Intelligence? Rob Miles explains the perils.

Part 1: https://www.youtube.com/watch?v=4l7Is6vOAOA
Rob's Original Discussions on General AI: https://www.youtube.com/playlist?list=PLzH6n4zXuckquVnQ0KlMDxyT5YE-sA8Ps

Stop Button Solution?: https://youtu.be/9nktr1MgS-A

More from Rob Miles: http://bit.ly/Rob_Miles_YouTube

Thanks to Nottingham Hackspace for providing the filming location: http://bit.ly/notthack


http://www.facebook.com/computerphile
https://twitter.com/computer_phile

This video was filmed and edited by Sean Riley.

Computer Science at the University of Nottingham: http://bit.ly/nottscomputer

Computerphile is a sister project to Brady Haran's Numberphile. More at http://www.bradyharan.com ...

A lot of our problems with AI seem to relate to its utility function. Why do we need one of those, anyway? Footage from The Simpsons, Copyright FOX, used under Fair Use With thanks to everyone who gave their suggestions and feedback about drafts of this video And thanks to my Patreon Supporters: Chad Jones Peggy Youell Sylvain Chevalier https://www.patreon.com/robertskmiles 7:04
What's the Use of Utility Functions?
YouTube Video UExTQ29YT1J1Z25sWXlvaE5kYzBfZVhOaHB5b016OWlWeS41Mzk2QTAxMTkzNDk4MDhF

What's the Use of Utility Functions?

April 27, 2017 9:35 pm

A lot of our problems with AI seem to relate to its utility function. Why do we need one of those, anyway?

Footage from The Simpsons, Copyright FOX, used under Fair Use

With thanks to everyone who gave their suggestions and feedback about drafts of this video
And thanks to my Patreon Supporters:
Chad Jones
Peggy Youell
Sylvain Chevalier

https://www.patreon.com/robertskmiles ...

Audible free book: http://www.audible.com/computerphile Artificial Intelligence can be thought of in terms of optimization. Robert Miles explains using the evolution's algorithm. http://www.facebook.com/computerphile https://twitter.com/computer_phile This video was filmed and edited by Sean Riley. Computer Science at the University of Nottingham: http://bit.ly/nottscomputer Computerphile is a sister project to Brady Haran's Numberphile. See the full list of Brady's video projects at: http://bit.ly/bradychannels 7:20
Hill Climbing Algorithm & Artificial Intelligence - Computerphile
YouTube Video UExTQ29YT1J1Z25sWXlvaE5kYzBfZVhOaHB5b016OWlWeS5GM0Q3M0MzMzY5NTJFNTdE

Hill Climbing Algorithm & Artificial Intelligence - Computerphile

September 9, 2014 7:13 pm

Audible free book: http://www.audible.com/computerphile
Artificial Intelligence can be thought of in terms of optimization. Robert Miles explains using the evolution's algorithm.

http://www.facebook.com/computerphile
https://twitter.com/computer_phile

This video was filmed and edited by Sean Riley.

Computer Science at the University of Nottingham: http://bit.ly/nottscomputer

Computerphile is a sister project to Brady Haran's Numberphile. See the full list of Brady's video projects at: http://bit.ly/bradychannels ...

AI Safety isn't just Rob Miles' hobby horse, he shows us a published paper from some of the field's leading minds. More from Rob Miles on his channel: http://bit.ly/Rob_Miles_YouTube Apologies for the focus issues throughout this video, they were due to a camera fault. :( Thanks as ever to Nottingham Hackspace (at least the camera fault allows you to read some of their book titles) Concrete Problems in AI Safety paper: https://arxiv.org/pdf/1606.06565.pdf AI 'Stop Button' Problem: https://youtu.be/3TYT1QfdfsM Onion Routing: https://youtu.be/QRYzre4bf7I http://www.facebook.com/computerphile https://twitter.com/computer_phile This video was filmed and edited by Sean Riley. Computer Science at the University of Nottingham: http://bit.ly/nottscomputer Computerphile is a sister project to Brady Haran's Numberphile. More at http://www.bradyharan.com 9:01
Concrete Problems in AI Safety (Paper) - Computerphile
YouTube Video UExTQ29YT1J1Z25sWXlvaE5kYzBfZVhOaHB5b016OWlWeS4zRjM0MkVCRTg0MkYyQTM0

Concrete Problems in AI Safety (Paper) - Computerphile

June 16, 2017 10:06 pm

AI Safety isn't just Rob Miles' hobby horse, he shows us a published paper from some of the field's leading minds.

More from Rob Miles on his channel: http://bit.ly/Rob_Miles_YouTube

Apologies for the focus issues throughout this video, they were due to a camera fault. :(

Thanks as ever to Nottingham Hackspace (at least the camera fault allows you to read some of their book titles)

Concrete Problems in AI Safety paper: https://arxiv.org/pdf/1606.06565.pdf

AI 'Stop Button' Problem: https://youtu.be/3TYT1QfdfsM
Onion Routing: https://youtu.be/QRYzre4bf7I

http://www.facebook.com/computerphile
https://twitter.com/computer_phile

This video was filmed and edited by Sean Riley.

Computer Science at the University of Nottingham: http://bit.ly/nottscomputer

Computerphile is a sister project to Brady Haran's Numberphile. More at http://www.bradyharan.com ...

We can expect AI systems to accidentally create serious negative side effects - how can we avoid that? The first of several videos about the paper "Concrete Problems in AI Safety". Earlier on Computerphile: https://www.youtube.com/watch?v=AjyM-f8rDpg The Stop Button Problem: https://youtu.be/3TYT1QfdfsM Read the full paper here: https://arxiv.org/abs/1606.06565 Thanks again to all my wonderful Patreon Supporters: - Chad Jones - Ichiro Dohi - Stefan Skiles - Katie Byrne - Ziyang Liu - Joshua Richardson - Fabian Consiglio - Jonatan R - Øystein Flygt - Björn Mosten - Michael Greve - robertvanduursen - The Guru Of Vision - Fabrizio Pisani - Alexander Hartvig Nielsen - Volodymyr - Peggy Youell - Konstantin Shabashov - Adam Dodd - DGJono - Matthias Meger - Scott Stevens - Emilio Alvarez - Benjamin Aaron Degenhart - Michael Ore - Robert Bridges - Dmitri Afanasjev https://www.patreon.com/robertskmiles 9:33
Avoiding Negative Side Effects: Concrete Problems in AI Safety part 1
YouTube Video UExTQ29YT1J1Z25sWXlvaE5kYzBfZVhOaHB5b016OWlWeS41NkI0NEY2RDEwNTU3Q0M2

Avoiding Negative Side Effects: Concrete Problems in AI Safety part 1

June 18, 2017 1:02 pm

We can expect AI systems to accidentally create serious negative side effects - how can we avoid that?
The first of several videos about the paper "Concrete Problems in AI Safety".

Earlier on Computerphile: https://www.youtube.com/watch?v=AjyM-f8rDpg
The Stop Button Problem: https://youtu.be/3TYT1QfdfsM

Read the full paper here: https://arxiv.org/abs/1606.06565

Thanks again to all my wonderful Patreon Supporters:
- Chad Jones
- Ichiro Dohi
- Stefan Skiles
- Katie Byrne
- Ziyang Liu
- Joshua Richardson
- Fabian Consiglio
- Jonatan R
- Øystein Flygt
- Björn Mosten
- Michael Greve
- robertvanduursen
- The Guru Of Vision
- Fabrizio Pisani
- Alexander Hartvig Nielsen
- Volodymyr
- Peggy Youell
- Konstantin Shabashov
- Adam Dodd
- DGJono
- Matthias Meger
- Scott Stevens
- Emilio Alvarez
- Benjamin Aaron Degenhart
- Michael Ore
- Robert Bridges
- Dmitri Afanasjev
https://www.patreon.com/robertskmiles ...

This is a follow-up to this earlier video: https://youtu.be/lqJUIqZNzP8 There's another problem with minimising side effects... The paper we're looking at: https://arxiv.org/pdf/1606.06565.pdf AI Safety Careers advice: https://80000hours.org/problem-profiles/positively-shaping-artificial-intelligence Thanks to my amazing Patreon Supporters: Chad Jones Ichiro Dohi Stefan Skiles Katie Byrne Ziyang Liu James McCuen Joshua Richardson Fabian Consiglio Jonatan R Øystein Flygt Björn Mosten Michael Greve robertvanduursen The Guru Of Vision Fabrizio Pisani Alexander Hartvig Nielsen Volodymyr Peggy Youell Konstantin Shabashov The Dodd DGJono Matthias Meger Scott Stevens Emilio Alvarez Benjamin Aaron Degenhart Michael Ore Robert Bridges Dmitri Afanasjev Brian Sandberg Einar Ueland Lo Rez https://www.patreon.com/robertskmiles 3:23
Avoiding Positive Side Effects: Concrete Problems in AI Safety part 1.5
YouTube Video UExTQ29YT1J1Z25sWXlvaE5kYzBfZVhOaHB5b016OWlWeS4yODlGNEE0NkRGMEEzMEQy

Avoiding Positive Side Effects: Concrete Problems in AI Safety part 1.5

June 25, 2017 11:29 am

This is a follow-up to this earlier video: https://youtu.be/lqJUIqZNzP8
There's another problem with minimising side effects...

The paper we're looking at: https://arxiv.org/pdf/1606.06565.pdf

AI Safety Careers advice: https://80000hours.org/problem-profiles/positively-shaping-artificial-intelligence


Thanks to my amazing Patreon Supporters:
Chad Jones
Ichiro Dohi
Stefan Skiles
Katie Byrne
Ziyang Liu
James McCuen
Joshua Richardson
Fabian Consiglio
Jonatan R
Øystein Flygt
Björn Mosten
Michael Greve
robertvanduursen
The Guru Of Vision
Fabrizio Pisani
Alexander Hartvig Nielsen
Volodymyr
Peggy Youell
Konstantin Shabashov
The Dodd
DGJono
Matthias Meger
Scott Stevens
Emilio Alvarez
Benjamin Aaron Degenhart
Michael Ore
Robert Bridges
Dmitri Afanasjev
Brian Sandberg
Einar Ueland
Lo Rez
https://www.patreon.com/robertskmiles ...

Maybe AI systems would be safer if they avoid gaining too much control over their environment? How might that work? This is a follow-up to this earlier video: https://youtu.be/lqJUIqZNzP8 The paper 'Concrete Problems in AI Safety': https://arxiv.org/pdf/1606.06565.pdf A book chapter about Empowerment: https://arxiv.org/pdf/1310.1863.pdf Prof Brailsford's Information Theory Videos: https://www.youtube.com/watch?v=Lto-ajuqW3w&list=PLzH6n4zXuckpKAj1_88VS-8Z6yn9zX_P6 Thanks to my amazing Patreon Supporters: Sara Tjäder Jason Strack Chad Jones Ichiro Dohi Stefan Skiles Katie Byrne Ziyang Liu Jordan Medina James McCuen Joshua Richardson Fabian Consiglio Jonatan R Øystein Flygt Björn Mosten Michael Greve robertvanduursen The Guru Of Vision Fabrizio Pisani Alexander Hartvig Nielsen Volodymyr Peggy Youell Konstantin Shabashov Almighty Dodd DGJono Matthias Meger Scott Stevens Emilio Alvarez Benjamin Aaron Degenhart Michael Ore Robert Bridges Dmitri Afanasjev Brian Sandberg Einar Ueland Lo Rez C3POehne https://www.patreon.com/robertskmiles 6:33
Empowerment: Concrete Problems in AI Safety part 2
YouTube Video UExTQ29YT1J1Z25sWXlvaE5kYzBfZVhOaHB5b016OWlWeS4wMTcyMDhGQUE4NTIzM0Y5

Empowerment: Concrete Problems in AI Safety part 2

July 9, 2017 11:24 am

Maybe AI systems would be safer if they avoid gaining too much control over their environment? How might that work?

This is a follow-up to this earlier video: https://youtu.be/lqJUIqZNzP8

The paper 'Concrete Problems in AI Safety': https://arxiv.org/pdf/1606.06565.pdf
A book chapter about Empowerment: https://arxiv.org/pdf/1310.1863.pdf

Prof Brailsford's Information Theory Videos: https://www.youtube.com/watch?v=Lto-ajuqW3w&list=PLzH6n4zXuckpKAj1_88VS-8Z6yn9zX_P6

Thanks to my amazing Patreon Supporters:
Sara Tjäder
Jason Strack
Chad Jones
Ichiro Dohi
Stefan Skiles
Katie Byrne
Ziyang Liu
Jordan Medina
James McCuen
Joshua Richardson
Fabian Consiglio
Jonatan R
Øystein Flygt
Björn Mosten
Michael Greve
robertvanduursen
The Guru Of Vision
Fabrizio Pisani
Alexander Hartvig Nielsen
Volodymyr
Peggy Youell
Konstantin Shabashov
Almighty Dodd
DGJono
Matthias Meger
Scott Stevens
Emilio Alvarez
Benjamin Aaron Degenhart
Michael Ore
Robert Bridges
Dmitri Afanasjev
Brian Sandberg
Einar Ueland
Lo Rez
C3POehne
https://www.patreon.com/robertskmiles ...

After seemingly insurmountable issues with Artificial General Intelligence, Rob Miles takes a look at a promising solution: Cooperative Inverse Reinforcement Learning Concrete Problems in AI Safety: https://youtu.be/AjyM-f8rDpg The AI 'Stop Button' Problem: https://youtu.be/3TYT1QfdfsM More from Rob Miles: http://bit.ly/Rob_Miles_YouTube Interesting filming point, as clouds cover the sun, the room not only gets darker, the colour temperature (white balance) changes too... http://www.facebook.com/computerphile https://twitter.com/computer_phile This video was filmed and edited by Sean Riley. Computer Science at the University of Nottingham: http://bit.ly/nottscomputer Computerphile is a sister project to Brady Haran's Numberphile. More at http://www.bradyharan.com 23:45
Stop Button Solution? - Computerphile
YouTube Video UExTQ29YT1J1Z25sWXlvaE5kYzBfZVhOaHB5b016OWlWeS45NDk1REZENzhEMzU5MDQz

Stop Button Solution? - Computerphile

August 3, 2017 1:27 pm

After seemingly insurmountable issues with Artificial General Intelligence, Rob Miles takes a look at a promising solution: Cooperative Inverse Reinforcement Learning

Concrete Problems in AI Safety: https://youtu.be/AjyM-f8rDpg
The AI 'Stop Button' Problem: https://youtu.be/3TYT1QfdfsM

More from Rob Miles: http://bit.ly/Rob_Miles_YouTube

Interesting filming point, as clouds cover the sun, the room not only gets darker, the colour temperature (white balance) changes too...

http://www.facebook.com/computerphile
https://twitter.com/computer_phile

This video was filmed and edited by Sean Riley.

Computer Science at the University of Nottingham: http://bit.ly/nottscomputer

Computerphile is a sister project to Brady Haran's Numberphile. More at http://www.bradyharan.com ...

Sometimes AI can find ways to 'cheat' and get more reward than we intended by doing something unexpected. The Concrete Problems in AI Safety Playlist: https://www.youtube.com/playlist?list=PLqL14ZxTTA4fEp5ltiNinNHdkPuLK4778 The Computerphile video: https://www.youtube.com/watch?v=9nktr1MgS-A The paper 'Concrete Problems in AI Safety': https://arxiv.org/pdf/1606.06565.pdf SethBling's channel: https://www.youtube.com/user/sethbling With thanks to my excellent Patreon supporters: https://www.patreon.com/robertskmiles Jordan Medina FHI's own Kyle Scott Jason Hise David Rasmussen James McCuen Richárd Nagyfi Ammar Mousali Joshua Richardson Fabian Consiglio Jonatan R Øystein Flygt Björn Mosten Michael Greve robertvanduursen The Guru Of Vision Fabrizio Pisani Alexander Hartvig Nielsen Volodymyr David Tjäder Paul Mason Ben Scanlon Julius Brash Mike Bird Peggy Youell Konstantin Shabashov Almighty Dodd DGJono Matthias Meger Scott Stevens Emilio Alvarez Benjamin Aaron Degenhart Michael Ore Robert Bridges Dmitri Afanasjev Brian Sandberg Einar Ueland Lo Rez C3POehne Stephen Paul Marcel Ward Andrew Weir Pontus Carlsson Taylor Smith Ben Archer Ivan Pochesnev Scott McCarthy Kabilan Kabilan Kabilan Kabilan Phil Philip Alexander Christopher Tendayi Mawushe Gabriel Behm Anne Kohlbrenner Jake Fish Jennifer Autumn Latham 6:56
Reward Hacking: Concrete Problems in AI Safety Part 3
YouTube Video UExTQ29YT1J1Z25sWXlvaE5kYzBfZVhOaHB5b016OWlWeS41MjE1MkI0OTQ2QzJGNzNG

Reward Hacking: Concrete Problems in AI Safety Part 3

August 12, 2017 9:24 pm

Sometimes AI can find ways to 'cheat' and get more reward than we intended by doing something unexpected.

The Concrete Problems in AI Safety Playlist: https://www.youtube.com/playlist?list=PLqL14ZxTTA4fEp5ltiNinNHdkPuLK4778
The Computerphile video: https://www.youtube.com/watch?v=9nktr1MgS-A
The paper 'Concrete Problems in AI Safety': https://arxiv.org/pdf/1606.06565.pdf

SethBling's channel: https://www.youtube.com/user/sethbling

With thanks to my excellent Patreon supporters:
https://www.patreon.com/robertskmiles

Jordan Medina
FHI's own Kyle Scott
Jason Hise
David Rasmussen
James McCuen
Richárd Nagyfi
Ammar Mousali
Joshua Richardson
Fabian Consiglio
Jonatan R
Øystein Flygt
Björn Mosten
Michael Greve
robertvanduursen
The Guru Of Vision
Fabrizio Pisani
Alexander Hartvig Nielsen
Volodymyr
David Tjäder
Paul Mason
Ben Scanlon
Julius Brash
Mike Bird
Peggy Youell
Konstantin Shabashov
Almighty Dodd
DGJono
Matthias Meger
Scott Stevens
Emilio Alvarez
Benjamin Aaron Degenhart
Michael Ore
Robert Bridges
Dmitri Afanasjev
Brian Sandberg
Einar Ueland
Lo Rez
C3POehne
Stephen Paul
Marcel Ward
Andrew Weir
Pontus Carlsson
Taylor Smith
Ben Archer
Ivan Pochesnev
Scott McCarthy
Kabilan Kabilan Kabilan Kabilan
Phil
Philip Alexander
Christopher
Tendayi Mawushe
Gabriel Behm
Anne Kohlbrenner
Jake Fish
Jennifer Autumn Latham ...

Goodhart's Law, Partially Observed Goals, and Wireheading: some more reasons for AI systems to find ways to 'cheat' and get more reward than we intended. The Concrete Problems in AI Safety Playlist: https://www.youtube.com/playlist?list=PLqL14ZxTTA4fEp5ltiNinNHdkPuLK4778 Previous Video: https://www.youtube.com/watch?v=92qDfT8pENs The Computerphile video: https://www.youtube.com/watch?v=9nktr1MgS-A The paper 'Concrete Problems in AI Safety': https://arxiv.org/pdf/1606.06565.pdf SethBling's channel: https://www.youtube.com/user/sethbling With thanks to my excellent Patreon supporters: https://www.patreon.com/robertskmiles Steef Sara Tjäder Jason Strack Chad Jones Ichiro Dohi Stefan Skiles Katie Byrne Ziyang Liu Jordan Medina Kyle Scott Jason Hise David Rasmussen James McCuen Richárd Nagyfi Ammar Mousali Scott Zockoll Charles Miller Joshua Richardson Fabian Consiglio Jonatan R Øystein Flygt Björn Mosten Michael Greve robertvanduursen The Guru Of Vision Fabrizio Pisani Alexander Hartvig Nielsen Volodymyr David Tjäder Paul Mason Ben Scanlon Julius Brash Mike Bird Taylor Winning Roman Nekhoroshev Peggy Youell Konstantin Shabashov Almighty Dodd DGJono Matthias Meger Scott Stevens Emilio Alvarez Benjamin Aaron Degenhart Michael Ore Robert Bridges Dmitri Afanasjev Brian Sandberg Einar Ueland Lo Rez C3POehne Stephen Paul Marcel Ward Andrew Weir Pontus Carlsson Taylor Smith Ben Archer Ivan Pochesnev Scott McCarthy Kabs Kabs Phil Philip Alexander Christopher Tendayi Mawushe Gabriel Behm Anne Kohlbrenner 7:32
Reward Hacking Reloaded: Concrete Problems in AI Safety Part 3.5
YouTube Video UExTQ29YT1J1Z25sWXlvaE5kYzBfZVhOaHB5b016OWlWeS4wOTA3OTZBNzVEMTUzOTMy

Reward Hacking Reloaded: Concrete Problems in AI Safety Part 3.5

August 29, 2017 12:08 pm

Goodhart's Law, Partially Observed Goals, and Wireheading: some more reasons for AI systems to find ways to 'cheat' and get more reward than we intended.

The Concrete Problems in AI Safety Playlist: https://www.youtube.com/playlist?list=PLqL14ZxTTA4fEp5ltiNinNHdkPuLK4778
Previous Video: https://www.youtube.com/watch?v=92qDfT8pENs
The Computerphile video: https://www.youtube.com/watch?v=9nktr1MgS-A
The paper 'Concrete Problems in AI Safety': https://arxiv.org/pdf/1606.06565.pdf
SethBling's channel: https://www.youtube.com/user/sethbling

With thanks to my excellent Patreon supporters:
https://www.patreon.com/robertskmiles

Steef
Sara Tjäder
Jason Strack
Chad Jones
Ichiro Dohi
Stefan Skiles
Katie Byrne
Ziyang Liu
Jordan Medina
Kyle Scott
Jason Hise
David Rasmussen
James McCuen
Richárd Nagyfi
Ammar Mousali
Scott Zockoll
Charles Miller
Joshua Richardson
Fabian Consiglio
Jonatan R
Øystein Flygt
Björn Mosten
Michael Greve
robertvanduursen
The Guru Of Vision
Fabrizio Pisani
Alexander Hartvig Nielsen
Volodymyr
David Tjäder
Paul Mason
Ben Scanlon
Julius Brash
Mike Bird
Taylor Winning
Roman Nekhoroshev
Peggy Youell
Konstantin Shabashov
Almighty Dodd
DGJono
Matthias Meger
Scott Stevens
Emilio Alvarez
Benjamin Aaron Degenhart
Michael Ore
Robert Bridges
Dmitri Afanasjev
Brian Sandberg
Einar Ueland
Lo Rez
C3POehne
Stephen Paul
Marcel Ward
Andrew Weir
Pontus Carlsson
Taylor Smith
Ben Archer
Ivan Pochesnev
Scott McCarthy
Kabs Kabs
Phil
Philip Alexander
Christopher
Tendayi Mawushe
Gabriel Behm
Anne Kohlbrenner ...

Three different approaches that might help to prevent reward hacking. New Side Channel with no content yet!: https://www.youtube.com/channel/UC4qH2AHly_RSRze1bUqSSNw Where do we go now?: https://www.youtube.com/watch?v=vYhErnZdnso Previous Video in the series: https://youtu.be/46nsTFfsBuc The Concrete Problems in AI Safety Playlist: https://www.youtube.com/playlist?list=PLqL14ZxTTA4fEp5ltiNinNHdkPuLK4778 The Computerphile video: https://www.youtube.com/watch?v=4l7Is6vOAOA The paper 'Concrete Problems in AI Safety': https://arxiv.org/pdf/1606.06565.pdf With thanks to my excellent Patreon supporters: https://www.patreon.com/robertskmiles Steef Sara Tjäder Jason Strack Chad Jones Stefan Skiles Katie Byrne Ziyang Liu Jordan Medina Kyle Scott Jason Hise David Rasmussen Heavy Empty James McCuen Richárd Nagyfi Ammar Mousali Scott Zockoll Charles Miller Joshua Richardson Fabian Consiglio Jonatan R Øystein Flygt Björn Mosten Michael Greve robertvanduursen The Guru Of Vision Fabrizio Pisani A Hartvig Nielsen Volodymyr David Tjäder Paul Mason Ben Scanlon Julius Brash Mike Bird Taylor Winning Roman Nekhoroshev Peggy Youell Konstantin Shabashov Dodd Almighty DGJono Matthias Meger Scott Stevens Emilio Alvarez Michael Ore Robert Bridges Dmitri Afanasjev Brian Sandberg Einar Ueland Lo Rez C3POehne Stephen Paul Marcel Ward Andrew Weir Pontus Carlsson Taylor Smith Ben Archer Ivan Pochesnev Scott McCarthy Kabs Kabs Kabs Phil Philip Alexander Christopher Tendayi Mawushe Gabriel Behm Anne Kohlbrenner Jake Fish Jennifer Autumn Latham Filip Bjorn Nyblad Stefan Laurie Tom O'Connor Krethys PiotrekM Jussi Männistö Matanya Loewenthal Wr4thon 9:38
What Can We Do About Reward Hacking?: Concrete Problems in AI Safety Part 4
YouTube Video UExTQ29YT1J1Z25sWXlvaE5kYzBfZVhOaHB5b016OWlWeS4xMkVGQjNCMUM1N0RFNEUx

What Can We Do About Reward Hacking?: Concrete Problems in AI Safety Part 4

September 24, 2017 2:09 pm

Three different approaches that might help to prevent reward hacking.

New Side Channel with no content yet!: https://www.youtube.com/channel/UC4qH2AHly_RSRze1bUqSSNw
Where do we go now?: https://www.youtube.com/watch?v=vYhErnZdnso
Previous Video in the series: https://youtu.be/46nsTFfsBuc

The Concrete Problems in AI Safety Playlist: https://www.youtube.com/playlist?list=PLqL14ZxTTA4fEp5ltiNinNHdkPuLK4778
The Computerphile video: https://www.youtube.com/watch?v=4l7Is6vOAOA
The paper 'Concrete Problems in AI Safety': https://arxiv.org/pdf/1606.06565.pdf

With thanks to my excellent Patreon supporters:
https://www.patreon.com/robertskmiles

Steef
Sara Tjäder
Jason Strack
Chad Jones
Stefan Skiles
Katie Byrne
Ziyang Liu
Jordan Medina
Kyle Scott
Jason Hise
David Rasmussen
Heavy Empty
James McCuen
Richárd Nagyfi
Ammar Mousali
Scott Zockoll
Charles Miller
Joshua Richardson
Fabian Consiglio
Jonatan R
Øystein Flygt
Björn Mosten
Michael Greve
robertvanduursen
The Guru Of Vision
Fabrizio Pisani
A Hartvig Nielsen
Volodymyr
David Tjäder
Paul Mason
Ben Scanlon
Julius Brash
Mike Bird
Taylor Winning
Roman Nekhoroshev
Peggy Youell
Konstantin Shabashov
Dodd Almighty
DGJono
Matthias Meger
Scott Stevens
Emilio Alvarez
Michael Ore
Robert Bridges
Dmitri Afanasjev
Brian Sandberg
Einar Ueland
Lo Rez
C3POehne
Stephen Paul
Marcel Ward
Andrew Weir
Pontus Carlsson
Taylor Smith
Ben Archer
Ivan Pochesnev
Scott McCarthy
Kabs Kabs Kabs
Phil
Philip Alexander
Christopher
Tendayi Mawushe
Gabriel Behm
Anne Kohlbrenner
Jake Fish
Jennifer Autumn Latham
Filip
Bjorn Nyblad
Stefan Laurie
Tom O'Connor
Krethys
PiotrekM
Jussi Männistö
Matanya Loewenthal
Wr4thon ...

Artificial Intelligence where neural nets play against each other and improve enough to generate something new. Rob Miles explains GANs One of the papers Rob referenced: http://bit.ly/C_GANs More from Rob Miles: http://bit.ly/Rob_Miles_YouTube https://www.facebook.com/computerphile https://twitter.com/computer_phile This video was filmed and edited by Sean Riley. Computer Science at the University of Nottingham: https://bit.ly/nottscomputer Computerphile is a sister project to Brady Haran's Numberphile. More at http://www.bradyharan.com 21:21
Generative Adversarial Networks (GANs) - Computerphile
YouTube Video UExTQ29YT1J1Z25sWXlvaE5kYzBfZVhOaHB5b016OWlWeS45NzUwQkI1M0UxNThBMkU0

Generative Adversarial Networks (GANs) - Computerphile

October 25, 2017 6:31 pm

Artificial Intelligence where neural nets play against each other and improve enough to generate something new. Rob Miles explains GANs

One of the papers Rob referenced: http://bit.ly/C_GANs

More from Rob Miles: http://bit.ly/Rob_Miles_YouTube

https://www.facebook.com/computerphile
https://twitter.com/computer_phile

This video was filmed and edited by Sean Riley.

Computer Science at the University of Nottingham: https://bit.ly/nottscomputer

Computerphile is a sister project to Brady Haran's Numberphile. More at http://www.bradyharan.com ...

Why can't we just have humans overseeing our AI systems? The Concrete Problems in AI Safety Playlist: https://www.youtube.com/playlist?list=PLqL14ZxTTA4fEp5ltiNinNHdkPuLK4778 Previous Video: https://www.youtube.com/watch?v=13tZ9Yia71c The Computerphile video: https://www.youtube.com/watch?v=9nktr1MgS-A The paper 'Concrete Problems in AI Safety': https://arxiv.org/pdf/1606.06565.pdf https://www.patreon.com/robertskmiles With thanks to my wonderful Patreon supporters: - Steef - Sara Tjäder - Jason Strack - Chad Jones - Stefan Skiles - Ziyang Liu - Jordan Medina - Jason Hise - Heavy Empty - Manuel Weichselbaum - James McCuen - Richárd Nagyfi - Ammar Mousali - Scott Zockoll - Charles Miller - Joshua Richardson - Jonatan R - Michael Greve - robertvanduursen - The Guru Of Vision - Fabrizio Pisani - Alexander Hartvig Nielsen - Volodymyr - David Tjäder - Paul Mason - Ben Scanlon - Julius Brash - Mike Bird - Taylor Winning - Ville Ahlgren - Johannes David - Andrew Pearce - Gunnar Guðvarðarson - Shevis Johnson - Erik de Bruijn - Robin Green - Alexei Vasilkov - Roman Nekhoroshev - Peggy Youell - Konsta - William Hendley - Almighty Dodd - DGJono - Matthias Meger - Scott Stevens - Emilio Alvarez - Michael Ore - Robert Bridges - Dmitri Afanasjev - Brian Sandberg - Einar Ueland - Lo Rez - Stephen Paul - Marcel Ward - Andrew Weir - Pontus Carlsson - Taylor Smith - Ben Archer - Ivan Pochesnev - Scott McCarthy - Kabs Kabs Kabs - Phil - Christopher Askin - Tendayi Mawushe - Gabriel Behm - Anne Kohlbrenner - Jake Fish - David Rasmussen - Bjorn Nyblad - Stefan Laurie - Tom O'Connor - pmilian - Jussi Männistö - Cameron Kinsel - Matanya Loewenthal - Wr4thon - Dave Tapley - Archy de Berker - Kevin - Vincent Sanders - Marc Pauly - Andy Kobre - Brian Gillespie https://www.patreon.com/robertskmiles 5:03
Scalable Supervision: Concrete Problems in AI Safety Part 5
YouTube Video UExTQ29YT1J1Z25sWXlvaE5kYzBfZVhOaHB5b016OWlWeS41MzJCQjBCNDIyRkJDN0VD

Scalable Supervision: Concrete Problems in AI Safety Part 5

November 29, 2017 11:47 pm

Why can't we just have humans overseeing our AI systems?

The Concrete Problems in AI Safety Playlist: https://www.youtube.com/playlist?list=PLqL14ZxTTA4fEp5ltiNinNHdkPuLK4778
Previous Video: https://www.youtube.com/watch?v=13tZ9Yia71c
The Computerphile video: https://www.youtube.com/watch?v=9nktr1MgS-A
The paper 'Concrete Problems in AI Safety': https://arxiv.org/pdf/1606.06565.pdf

https://www.patreon.com/robertskmiles
With thanks to my wonderful Patreon supporters:
- Steef
- Sara Tjäder
- Jason Strack
- Chad Jones
- Stefan Skiles
- Ziyang Liu
- Jordan Medina
- Jason Hise
- Heavy Empty
- Manuel Weichselbaum
- James McCuen
- Richárd Nagyfi
- Ammar Mousali
- Scott Zockoll
- Charles Miller
- Joshua Richardson
- Jonatan R
- Michael Greve
- robertvanduursen
- The Guru Of Vision
- Fabrizio Pisani
- Alexander Hartvig Nielsen
- Volodymyr
- David Tjäder
- Paul Mason
- Ben Scanlon
- Julius Brash
- Mike Bird
- Taylor Winning
- Ville Ahlgren
- Johannes David
- Andrew Pearce
- Gunnar Guðvarðarson
- Shevis Johnson
- Erik de Bruijn
- Robin Green
- Alexei Vasilkov
- Roman Nekhoroshev
- Peggy Youell
- Konsta
- William Hendley
- Almighty Dodd
- DGJono
- Matthias Meger
- Scott Stevens
- Emilio Alvarez
- Michael Ore
- Robert Bridges
- Dmitri Afanasjev
- Brian Sandberg
- Einar Ueland
- Lo Rez
- Stephen Paul
- Marcel Ward
- Andrew Weir
- Pontus Carlsson
- Taylor Smith
- Ben Archer
- Ivan Pochesnev
- Scott McCarthy
- Kabs Kabs Kabs
- Phil
- Christopher Askin
- Tendayi Mawushe
- Gabriel Behm
- Anne Kohlbrenner
- Jake Fish
- David Rasmussen
- Bjorn Nyblad
- Stefan Laurie
- Tom O'Connor
- pmilian
- Jussi Männistö
- Cameron Kinsel
- Matanya Loewenthal
- Wr4thon
- Dave Tapley
- Archy de Berker
- Kevin
- Vincent Sanders
- Marc Pauly
- Andy Kobre
- Brian Gillespie
https://www.patreon.com/robertskmiles ...

Can highly intelligent agents have stupid goals? A look at The Orthogonality Thesis and the nature of stupidity. The 'Stamp Collector' Computerphile video: https://www.youtube.com/watch?v=tcdVC4e6EV4 My other Computerphile videos: https://www.youtube.com/watch?v=GSIDS_lvRv4&list=PLqL14ZxTTA4fRMts7Af2G8t4Rp17e8MdS Katie Byrne's Channel: https://www.youtube.com/channel/UCwA5wd50HYLa-ZY80LSAg3w Chad Jones' Channel: https://www.youtube.com/user/cjone150 https://www.patreon.com/robertskmiles With thanks to my wonderful Patreon supporters: - Steef - Sara Tjäder - Jason Strack - Chad Jones - Stefan Skiles - Ziyang Liu - Jordan Medina - Jason Hise - Manuel Weichselbaum - 1RV34 - James McCuen - Richárd Nagyfi - Ammar Mousali - Scott Zockoll - Ville Ahlgren - Alec Johnson - Simon Strandgaard - Joshua Richardson - Jonatan R - Michael Greve - robertvanduursen - The Guru Of Vision - Fabrizio Pisani - Alexander Hartvig Nielsen - Volodymyr - David Tjäder - Paul Mason - Ben Scanlon - Julius Brash - Mike Bird - Tom O'Connor - Gunnar Guðvarðarson - Shevis Johnson - Erik de Bruijn - Robin Green - Alexei Vasilkov - Maksym Taran - Laura Olds - Jon Halliday - Robert Werner - Roman Nekhoroshev - Konsta - William Hendley - DGJono - Matthias Meger - Scott Stevens - Emilio Alvarez - Michael Ore - Dmitri Afanasjev - Brian Sandberg - Einar Ueland - Lo Rez - Marcel Ward - Andrew Weir - Taylor Smith - Ben Archer - Scott McCarthy - Kabs Kabs - Phil - Tendayi Mawushe - Gabriel Behm - Anne Kohlbrenner - Jake Fish - Bjorn Nyblad - Stefan Laurie - Jussi Männistö - Cameron Kinsel - Matanya Loewenthal - Wr4thon - Dave Tapley - Archy de Berker - Kevin - Vincent Sanders - Marc Pauly - Andy Kobre - Brian Gillespie - Martin Wind - Peggy Youell - Poker Chen https://www.patreon.com/robertskmiles 13:03
Intelligence and Stupidity: The Orthogonality Thesis
YouTube Video UExTQ29YT1J1Z25sWXlvaE5kYzBfZVhOaHB5b016OWlWeS4yMDhBMkNBNjRDMjQxQTg1

Intelligence and Stupidity: The Orthogonality Thesis

January 11, 2018 9:53 pm

Can highly intelligent agents have stupid goals?
A look at The Orthogonality Thesis and the nature of stupidity.

The 'Stamp Collector' Computerphile video: https://www.youtube.com/watch?v=tcdVC4e6EV4
My other Computerphile videos: https://www.youtube.com/watch?v=GSIDS_lvRv4&list=PLqL14ZxTTA4fRMts7Af2G8t4Rp17e8MdS

Katie Byrne's Channel: https://www.youtube.com/channel/UCwA5wd50HYLa-ZY80LSAg3w
Chad Jones' Channel: https://www.youtube.com/user/cjone150

https://www.patreon.com/robertskmiles
With thanks to my wonderful Patreon supporters:
- Steef
- Sara Tjäder
- Jason Strack
- Chad Jones
- Stefan Skiles
- Ziyang Liu
- Jordan Medina
- Jason Hise
- Manuel Weichselbaum
- 1RV34
- James McCuen
- Richárd Nagyfi
- Ammar Mousali
- Scott Zockoll
- Ville Ahlgren
- Alec Johnson
- Simon Strandgaard
- Joshua Richardson
- Jonatan R
- Michael Greve
- robertvanduursen
- The Guru Of Vision
- Fabrizio Pisani
- Alexander Hartvig Nielsen
- Volodymyr
- David Tjäder
- Paul Mason
- Ben Scanlon
- Julius Brash
- Mike Bird
- Tom O'Connor
- Gunnar Guðvarðarson
- Shevis Johnson
- Erik de Bruijn
- Robin Green
- Alexei Vasilkov
- Maksym Taran
- Laura Olds
- Jon Halliday
- Robert Werner
- Roman Nekhoroshev
- Konsta
- William Hendley
- DGJono
- Matthias Meger
- Scott Stevens
- Emilio Alvarez
- Michael Ore
- Dmitri Afanasjev
- Brian Sandberg
- Einar Ueland
- Lo Rez
- Marcel Ward
- Andrew Weir
- Taylor Smith
- Ben Archer
- Scott McCarthy
- Kabs Kabs
- Phil
- Tendayi Mawushe
- Gabriel Behm
- Anne Kohlbrenner
- Jake Fish
- Bjorn Nyblad
- Stefan Laurie
- Jussi Männistö
- Cameron Kinsel
- Matanya Loewenthal
- Wr4thon
- Dave Tapley
- Archy de Berker
- Kevin
- Vincent Sanders
- Marc Pauly
- Andy Kobre
- Brian Gillespie
- Martin Wind
- Peggy Youell
- Poker Chen
https://www.patreon.com/robertskmiles ...

How can we predict that AGI with unknown goals would behave badly by default? The Orthogonality Thesis video: https://www.youtube.com/watch?v=hEUO6pjwFOo Instrumental Convergence: https://arbital.com/p/instrumental_convergence/ Omohundro 2008, Basic AI Drives: https://selfawaresystems.files.wordpress.com/2008/01/ai_drives_final.pdf With thanks to my excellent Patrons at https://www.patreon.com/robertskmiles : Jason Hise Steef Jason Strack Chad Jones Stefan Skiles Jordan Medina Manuel Weichselbaum 1RV34 Scott Worley JJ Hepboin Alex Flint James McCuen Richárd Nagyfi Ville Ahlgren Alec Johnson Simon Strandgaard Joshua Richardson Jonatan R Michael Greve The Guru Of Vision Fabrizio Pisani Alexander Hartvig Nielsen Volodymyr David Tjäder Paul Mason Ben Scanlon Julius Brash Mike Bird Tom O'Connor Gunnar Guðvarðarson Shevis Johnson Erik de Bruijn Robin Green Alexei Vasilkov Maksym Taran Laura Olds Jon Halliday Robert Werner Paul Hobbs Jeroen De Dauw Konsta William Hendley DGJono robertvanduursen Scott Stevens Michael Ore Dmitri Afanasjev Brian Sandberg Einar Ueland Marcel Ward Andrew Weir Taylor Smith Ben Archer Scott McCarthy Kabs Kabs Phil Tendayi Mawushe Gabriel Behm Anne Kohlbrenner Jake Fish Bjorn Nyblad Jussi Männistö Mr Fantastic Matanya Loewenthal Wr4thon Dave Tapley Archy de Berker Kevin Vincent Sanders Marc Pauly Andy Kobre Brian Gillespie Martin Wind Peggy Youell Poker Chen Kees Darko Sperac Paul Moffat Noel Kocheril Jelle Langen Lars Scholz 10:36
Why Would AI Want to do Bad Things? Instrumental Convergence
YouTube Video UExTQ29YT1J1Z25sWXlvaE5kYzBfZVhOaHB5b016OWlWeS5ENDU4Q0M4RDExNzM1Mjcy

Why Would AI Want to do Bad Things? Instrumental Convergence

March 24, 2018 9:51 pm

How can we predict that AGI with unknown goals would behave badly by default?

The Orthogonality Thesis video: https://www.youtube.com/watch?v=hEUO6pjwFOo
Instrumental Convergence: https://arbital.com/p/instrumental_convergence/
Omohundro 2008, Basic AI Drives: https://selfawaresystems.files.wordpress.com/2008/01/ai_drives_final.pdf

With thanks to my excellent Patrons at https://www.patreon.com/robertskmiles :

Jason Hise
Steef
Jason Strack
Chad Jones
Stefan Skiles
Jordan Medina
Manuel Weichselbaum
1RV34
Scott Worley
JJ Hepboin
Alex Flint
James McCuen
Richárd Nagyfi
Ville Ahlgren
Alec Johnson
Simon Strandgaard
Joshua Richardson
Jonatan R
Michael Greve
The Guru Of Vision
Fabrizio Pisani
Alexander Hartvig Nielsen
Volodymyr
David Tjäder
Paul Mason
Ben Scanlon
Julius Brash
Mike Bird
Tom O'Connor
Gunnar Guðvarðarson
Shevis Johnson
Erik de Bruijn
Robin Green
Alexei Vasilkov
Maksym Taran
Laura Olds
Jon Halliday
Robert Werner
Paul Hobbs
Jeroen De Dauw
Konsta
William Hendley
DGJono
robertvanduursen
Scott Stevens
Michael Ore
Dmitri Afanasjev
Brian Sandberg
Einar Ueland
Marcel Ward
Andrew Weir
Taylor Smith
Ben Archer
Scott McCarthy
Kabs Kabs
Phil
Tendayi Mawushe
Gabriel Behm
Anne Kohlbrenner
Jake Fish
Bjorn Nyblad
Jussi Männistö
Mr Fantastic
Matanya Loewenthal
Wr4thon
Dave Tapley
Archy de Berker
Kevin
Vincent Sanders
Marc Pauly
Andy Kobre
Brian Gillespie
Martin Wind
Peggy Youell
Poker Chen
Kees
Darko Sperac
Paul Moffat
Noel Kocheril
Jelle Langen
Lars Scholz ...

This is extra material from the AI gridworlds video: https://youtu.be/eElfR_BnL5k https://www.facebook.com/computerphile https://twitter.com/computer_phile This video was filmed and edited by Sean Riley. Computer Science at the University of Nottingham: https://bit.ly/nottscomputer Computerphile is a sister project to Brady Haran's Numberphile. More at http://www.bradyharan.com 16:48
EXTRA BITS: AI Gridworlds - Computerphile
YouTube Video UExTQ29YT1J1Z25sWXlvaE5kYzBfZVhOaHB5b016OWlWeS5DNzE1RjZEMUZCMjA0RDBB

EXTRA BITS: AI Gridworlds - Computerphile

May 9, 2018 5:19 pm

This is extra material from the AI gridworlds video: https://youtu.be/eElfR_BnL5k

https://www.facebook.com/computerphile
https://twitter.com/computer_phile

This video was filmed and edited by Sean Riley.

Computer Science at the University of Nottingham: https://bit.ly/nottscomputer

Computerphile is a sister project to Brady Haran's Numberphile. More at http://www.bradyharan.com ...

Sponsored by Wix Code: Check them out here: http://wix.com/go/computerphile A safe place to try out AI algorithms, gridworlds are a standardised testing ground. Rob Miles takes us through AI safety, gridworld style. EXTRA BITS: https://youtu.be/py5VRagG6t8 Gridworld Paper: https://bit.ly/2ryxhGt Gridworld Github: https://bit.ly/2KJE6xH More from Rob Miles: http://bit.ly/Rob_Miles_YouTube Thanks to Nottingham Hackspace for providing the filming location: http://bit.ly/notthack https://www.facebook.com/computerphile https://twitter.com/computer_phile This video was filmed and edited by Sean Riley. Computer Science at the University of Nottingham: https://bit.ly/nottscomputer Computerphile is a sister project to Brady Haran's Numberphile. More at http://www.bradyharan.com 10:15
AI Gridworlds - Computerphile
YouTube Video UExTQ29YT1J1Z25sWXlvaE5kYzBfZVhOaHB5b016OWlWeS43MTI1NDIwOTMwQjIxMzNG

AI Gridworlds - Computerphile

May 10, 2018 4:52 pm

Sponsored by Wix Code: Check them out here: http://wix.com/go/computerphile

A safe place to try out AI algorithms, gridworlds are a standardised testing ground. Rob Miles takes us through AI safety, gridworld style.

EXTRA BITS: https://youtu.be/py5VRagG6t8

Gridworld Paper: https://bit.ly/2ryxhGt
Gridworld Github: https://bit.ly/2KJE6xH

More from Rob Miles: http://bit.ly/Rob_Miles_YouTube

Thanks to Nottingham Hackspace for providing the filming location: http://bit.ly/notthack

https://www.facebook.com/computerphile
https://twitter.com/computer_phile

This video was filmed and edited by Sean Riley.

Computer Science at the University of Nottingham: https://bit.ly/nottscomputer

Computerphile is a sister project to Brady Haran's Numberphile. More at http://www.bradyharan.com ...

Got an AI safety idea? Now you can test it out! A recent paper from DeepMind sets out some environments for evaluating the safety of AI systems, and the code is on GitHub. The Computerphile video: https://www.youtube.com/watch?v=eElfR_BnL5k The EXTRA BITS video, with more detail: https://www.youtube.com/watch?v=py5VRagG6t8 The paper: https://arxiv.org/pdf/1711.09883.pdf The GitHub repos: https://github.com/deepmind/ai-safety-gridworlds https://www.patreon.com/robertskmiles With thanks to my wonderful Patreon supporters: - Jason Hise - Steef - Cooper Lawton - Jason Strack - Chad Jones - Stefan Skiles - Jordan Medina - Manuel Weichselbaum - Scott Worley - JJ Hepboin - Alex Flint - Justin Courtright - James McCuen - Richárd Nagyfi - Ville Ahlgren - Alec Johnson - Simon Strandgaard - Joshua Richardson - Jonatan R - Michael Greve - The Guru Of Vision - Fabrizio Pisani - Alexander Hartvig Nielsen - Volodymyr - David Tjäder - Paul Mason - Ben Scanlon - Julius Brash - Mike Bird - Tom O'Connor - Gunnar Guðvarðarson - Shevis Johnson - Erik de Bruijn - Robin Green - Alexei Vasilkov - Maksym Taran - Laura Olds - Jon Halliday - Robert Werner - Paul Hobbs - Jeroen De Dauw - Enrico Ros - Tim Neilson - Eric Scammell - christopher dasenbrock - Igor Keller - William Hendley - DGJono - robertvanduursen - Scott Stevens - Michael Ore - Dmitri Afanasjev - Brian Sandberg - Einar Ueland - Marcel Ward - Andrew Weir - Taylor Smith - Ben Archer - Scott McCarthy - Kabs Kabs - Phil - Tendayi Mawushe - Gabriel Behm - Anne Kohlbrenner - Jake Fish - Bjorn Nyblad - Jussi Männistö - Mr Fantastic - Matanya Loewenthal - Wr4thon - Dave Tapley - Archy de Berker - Kevin - Marc Pauly - Joshua Pratt - Andy Kobre - Brian Gillespie - Martin Wind - Peggy Youell - Poker Chen - pmilian - Kees - Darko Sperac - Paul Moffat - Jelle Langen - Lars Scholz - Anders Öhrt - Lupuleasa Ionuț - Marco Tiraboschi - Peter Kjeld Andersen - Michael Kuhinica - Fraser Cain - Robin Scharf - Oren Milman 7:23
AI Safety Gridworlds
YouTube Video UExTQ29YT1J1Z25sWXlvaE5kYzBfZVhOaHB5b016OWlWeS4zMDg5MkQ5MEVDMEM1NTg2

AI Safety Gridworlds

May 25, 2018 6:20 pm

Got an AI safety idea? Now you can test it out! A recent paper from DeepMind sets out some environments for evaluating the safety of AI systems, and the code is on GitHub.

The Computerphile video: https://www.youtube.com/watch?v=eElfR_BnL5k
The EXTRA BITS video, with more detail: https://www.youtube.com/watch?v=py5VRagG6t8

The paper: https://arxiv.org/pdf/1711.09883.pdf
The GitHub repos: https://github.com/deepmind/ai-safety-gridworlds

https://www.patreon.com/robertskmiles
With thanks to my wonderful Patreon supporters:

- Jason Hise
- Steef
- Cooper Lawton
- Jason Strack
- Chad Jones
- Stefan Skiles
- Jordan Medina
- Manuel Weichselbaum
- Scott Worley
- JJ Hepboin
- Alex Flint
- Justin Courtright
- James McCuen
- Richárd Nagyfi
- Ville Ahlgren
- Alec Johnson
- Simon Strandgaard
- Joshua Richardson
- Jonatan R
- Michael Greve
- The Guru Of Vision
- Fabrizio Pisani
- Alexander Hartvig Nielsen
- Volodymyr
- David Tjäder
- Paul Mason
- Ben Scanlon
- Julius Brash
- Mike Bird
- Tom O'Connor
- Gunnar Guðvarðarson
- Shevis Johnson
- Erik de Bruijn
- Robin Green
- Alexei Vasilkov
- Maksym Taran
- Laura Olds
- Jon Halliday
- Robert Werner
- Paul Hobbs
- Jeroen De Dauw
- Enrico Ros
- Tim Neilson
- Eric Scammell
- christopher dasenbrock
- Igor Keller
- William Hendley
- DGJono
- robertvanduursen
- Scott Stevens
- Michael Ore
- Dmitri Afanasjev
- Brian Sandberg
- Einar Ueland
- Marcel Ward
- Andrew Weir
- Taylor Smith
- Ben Archer
- Scott McCarthy
- Kabs Kabs
- Phil
- Tendayi Mawushe
- Gabriel Behm
- Anne Kohlbrenner
- Jake Fish
- Bjorn Nyblad
- Jussi Männistö
- Mr Fantastic
- Matanya Loewenthal
- Wr4thon
- Dave Tapley
- Archy de Berker
- Kevin
- Marc Pauly
- Joshua Pratt
- Andy Kobre
- Brian Gillespie
- Martin Wind
- Peggy Youell
- Poker Chen
- pmilian
- Kees
- Darko Sperac
- Paul Moffat
- Jelle Langen
- Lars Scholz
- Anders Öhrt
- Lupuleasa Ionuț
- Marco Tiraboschi
- Peter Kjeld Andersen
- Michael Kuhinica
- Fraser Cain
- Robin Scharf
- Oren Milman ...

The last video about the AI Safety Gridworlds paper. How does an agent detect and adapt to friendly and adversarial intentions in the environment? The previous video: https://youtu.be/CGTkoUidQ8I The Computerphile video: https://www.youtube.com/watch?v=eElfR_BnL5k The EXTRA BITS video, with more detail: https://www.youtube.com/watch?v=py5VRagG6t8 The paper: https://arxiv.org/pdf/1711.09883.pdf The GitHub repos: https://github.com/deepmind/ai-safety-gridworlds With thanks to my excellent Patreon supporters: https://www.patreon.com/robertskmiles Jason Hise Steef Cooper Lawton Jason Strack Chad Jones Stefan Skiles Jordan Medina Manuel Weichselbaum Scott Worley JJ Hepboin Alex Flint Justin Courtright Pedro A Ortega James McCuen Richárd Nagyfi Ville Ahlgren Alec Johnson Clement Chiris Simon Strandgaard Joshua Richardson Jonatan R Michael Greve The Guru Of Vision Alexander Hartvig Nielsen Volodymyr David Tjäder Julius Brash Tom O'Connor Gunnar Guðvarðarson Shevis Johnson Erik de Bruijn Robin Green Alexei Vasilkov Maksym Taran Laura Olds Jon Halliday Robert Werner Paul Hobbs Jeroen De Dauw Enrico Ros Tim Neilson Eric Scammell christopher dasenbrock Igor Keller Morten Jelle Ben Glanton Robert Sokolowski Vlad D William Hendley DGJono robertvanduursen Scott Stevens Emilio Alvarez Dmitri Afanasjev Brian Sandberg Einar Ueland Marcel Ward Andrew Weir Taylor Smith Ben Archer Scott McCarthy Kabs Phil Tendayi Mawushe Anne Kohlbrenner Jake Fish Bjorn Nyblad Jussi Männistö Mr Fantastic Matanya Loewenthal Wr4thon Dave Tapley Archy de Berker Kevin Marc Pauly Joshua Pratt Andy Kobre Brian Gillespie Martin Wind Peggy Youell Poker Chen Kees Darko Sperac Paul Moffat Jelle Langen Lars Scholz Anders Öhrt Lupuleasa Ionuț Marco Tiraboschi Michael Kuhinica Fraser Cain Robin Scharf Oren Milman John Rees Shawn Hartsock Seth Brothwell https://www.patreon.com/robertskmiles 3:47
Friend or Foe? AI Safety Gridworlds extra bit
YouTube Video UExTQ29YT1J1Z25sWXlvaE5kYzBfZVhOaHB5b016OWlWeS45ODRDNTg0QjA4NkFBNkQy

Friend or Foe? AI Safety Gridworlds extra bit

June 25, 2018 1:31 am

The last video about the AI Safety Gridworlds paper. How does an agent detect and adapt to friendly and adversarial intentions in the environment?

The previous video: https://youtu.be/CGTkoUidQ8I

The Computerphile video: https://www.youtube.com/watch?v=eElfR_BnL5k
The EXTRA BITS video, with more detail: https://www.youtube.com/watch?v=py5VRagG6t8

The paper: https://arxiv.org/pdf/1711.09883.pdf
The GitHub repos: https://github.com/deepmind/ai-safety-gridworlds


With thanks to my excellent Patreon supporters:
https://www.patreon.com/robertskmiles

Jason Hise
Steef
Cooper Lawton
Jason Strack
Chad Jones
Stefan Skiles
Jordan Medina
Manuel Weichselbaum
Scott Worley
JJ Hepboin
Alex Flint
Justin Courtright
Pedro A Ortega
James McCuen
Richárd Nagyfi
Ville Ahlgren
Alec Johnson
Clement Chiris
Simon Strandgaard
Joshua Richardson
Jonatan R
Michael Greve
The Guru Of Vision
Alexander Hartvig Nielsen
Volodymyr
David Tjäder
Julius Brash
Tom O'Connor
Gunnar Guðvarðarson
Shevis Johnson
Erik de Bruijn
Robin Green
Alexei Vasilkov
Maksym Taran
Laura Olds
Jon Halliday
Robert Werner
Paul Hobbs
Jeroen De Dauw
Enrico Ros
Tim Neilson
Eric Scammell
christopher dasenbrock
Igor Keller
Morten Jelle
Ben Glanton
Robert Sokolowski
Vlad D
William Hendley
DGJono
robertvanduursen
Scott Stevens
Emilio Alvarez
Dmitri Afanasjev
Brian Sandberg
Einar Ueland
Marcel Ward
Andrew Weir
Taylor Smith
Ben Archer
Scott McCarthy
Kabs
Phil
Tendayi Mawushe
Anne Kohlbrenner
Jake Fish
Bjorn Nyblad
Jussi Männistö
Mr Fantastic
Matanya Loewenthal
Wr4thon
Dave Tapley
Archy de Berker
Kevin
Marc Pauly
Joshua Pratt
Andy Kobre
Brian Gillespie
Martin Wind
Peggy Youell
Poker Chen
Kees
Darko Sperac
Paul Moffat
Jelle Langen
Lars Scholz
Anders Öhrt
Lupuleasa Ionuț
Marco Tiraboschi
Michael Kuhinica
Fraser Cain
Robin Scharf
Oren Milman
John Rees
Shawn Hartsock
Seth Brothwell

https://www.patreon.com/robertskmiles ...

To learn, you need to try new things, but that can be risky. How do we make AI systems that can explore safely? Playlist of the series so far: https://www.youtube.com/playlist?list=PLqL14ZxTTA4fEp5ltiNinNHdkPuLK4778 The paper, 'Concrete Problems in AI Safety': https://arxiv.org/pdf/1606.06565.pdf AI Safety Gridworlds: https://youtu.be/CGTkoUidQ8I Why Would AI Want to do Bad Things? Instrumental Convergence: https://youtu.be/ZeecOKBus3Q Scalable Supervision: Concrete Problems in AI Safety Part 5: https://youtu.be/nr1lHuFeq5w The Evolved Radio and its Implications for Modelling the Evolution of Novel Sensors: https://people.duke.edu/~ng46/topics/evolved-radio.pdf With thanks to my excellent Patreon supporters: https://www.patreon.com/robertskmiles Jason Hise Steef Jason Strack Stefan Skiles Jordan Medina Scott Worley JJ Hepboin Alex Flint Pedro A Ortega James McCuen Richárd Nagyfi Alec Johnson Clemens Arbesser Simon Strandgaard Jonatan R Michael Greve The Guru Of Vision Alexander Hartvig Nielsen Volodymyr David Tjäder Julius Brash Tom O'Connor Ville Ahlgren Erik de Bruijn Robin Green Maksym Taran Laura Olds Jon Halliday Bobby Cold Paul Hobbs Jeroen De Dauw Tim Neilson Eric Scammell christopher dasenbrock Igor Keller Ben Glanton Robert Sokolowski Vlad D Jérôme Frossard Lupuleasa Ionuț Sylvain Chevalier DGJono robertvanduursen Scott Stevens Dmitri Afanasjev Brian Sandberg Einar Ueland Marcel Ward Andrew Weir Taylor Smith Ben Archer Scott McCarthy Kabs Phil Moyer Tendayi Mawushe Anne Kohlbrenner Bjorn Nyblad Jussi Männistö Mr Fantastic Matanya Loewenthal Wr4thon Dave Tapley Archy de Berker Pablo Eder Kevin Marc Pauly Joshua Pratt Gunnar Guðvarðarson Shevis Johnson Andy Kobre Manuel Weichselbaum Brian Gillespie Martin Wind Peggy Youell Poker Chen Kees Darko Sperac Paul Moffat Jelle Langen Lars Scholz Anders Öhrt Marco Tiraboschi Michael Kuhinica Fraser Cain Robin Scharf Oren Milman John Rees Gladamas Shawn Hartsock Seth Brothwell Brian Goodrich Michael S McReynolds https://www.patreon.com/robertskmiles Media Sources: "DashCam Russia - Crazy Drivers and Car Crashes 2018" (https://youtu.be/h50TQ3i9k5I) Optimist Prime "Hapless Boston Dynamics robot in shelf-stacking fail" (https://youtu.be/JzlsvFN_5HI) "The Simpsons - Bart Gets Famous" (c) Fox 1994 "Donald Duck - Cured Duck" (c) Disney 1945 "Vase Breaking Slow Motion" (https://youtu.be/IJNPc_anP7U) "Fastest quadcopter i've ever flown + Most Destructive Crash" (https://youtu.be/OKT4cx7UKsk) "An athlete uses physics to shatter world records - Asaf Bar-Yosef" (https://youtu.be/RaGUW1d0w8g) "Uber self-driving car crash in Tempe, Arizona" (https://youtu.be/XtTB8hTgHbM) "Quadcopter Fx Simulator" (https://youtu.be/-6si8WkRtaY) "Fallout - New Vegas by progamingwithed in 24:00 - AGDQ 2017 - Part 59" (https://youtu.be/nuzDif16_nc) "Far Cry 5 out of 5 Physics Simulation" (https://youtu.be/4My0Bt30pX0) 13:46
Safe Exploration: Concrete Problems in AI Safety Part 6
YouTube Video UExTQ29YT1J1Z25sWXlvaE5kYzBfZVhOaHB5b016OWlWeS5DQUNERDQ2NkIzRUQxNTY1

Safe Exploration: Concrete Problems in AI Safety Part 6

September 21, 2018 1:20 pm

To learn, you need to try new things, but that can be risky. How do we make AI systems that can explore safely?

Playlist of the series so far: https://www.youtube.com/playlist?list=PLqL14ZxTTA4fEp5ltiNinNHdkPuLK4778
The paper, 'Concrete Problems in AI Safety': https://arxiv.org/pdf/1606.06565.pdf

AI Safety Gridworlds: https://youtu.be/CGTkoUidQ8I
Why Would AI Want to do Bad Things? Instrumental Convergence: https://youtu.be/ZeecOKBus3Q
Scalable Supervision: Concrete Problems in AI Safety Part 5: https://youtu.be/nr1lHuFeq5w
The Evolved Radio and its Implications for Modelling the Evolution of Novel Sensors: https://people.duke.edu/~ng46/topics/evolved-radio.pdf

With thanks to my excellent Patreon supporters:
https://www.patreon.com/robertskmiles

Jason Hise
Steef
Jason Strack
Stefan Skiles
Jordan Medina
Scott Worley
JJ Hepboin
Alex Flint
Pedro A Ortega
James McCuen
Richárd Nagyfi
Alec Johnson
Clemens Arbesser
Simon Strandgaard
Jonatan R
Michael Greve
The Guru Of Vision
Alexander Hartvig Nielsen
Volodymyr
David Tjäder
Julius Brash
Tom O'Connor
Ville Ahlgren
Erik de Bruijn
Robin Green
Maksym Taran
Laura Olds
Jon Halliday
Bobby Cold
Paul Hobbs
Jeroen De Dauw
Tim Neilson
Eric Scammell
christopher dasenbrock
Igor Keller
Ben Glanton
Robert Sokolowski
Vlad D
Jérôme Frossard
Lupuleasa Ionuț
Sylvain Chevalier
DGJono
robertvanduursen
Scott Stevens
Dmitri Afanasjev
Brian Sandberg
Einar Ueland
Marcel Ward
Andrew Weir
Taylor Smith
Ben Archer
Scott McCarthy
Kabs
Phil Moyer
Tendayi Mawushe
Anne Kohlbrenner
Bjorn Nyblad
Jussi Männistö
Mr Fantastic
Matanya Loewenthal
Wr4thon
Dave Tapley
Archy de Berker
Pablo Eder
Kevin
Marc Pauly
Joshua Pratt
Gunnar Guðvarðarson
Shevis Johnson
Andy Kobre
Manuel Weichselbaum
Brian Gillespie
Martin Wind
Peggy Youell
Poker Chen
Kees
Darko Sperac
Paul Moffat
Jelle Langen
Lars Scholz
Anders Öhrt
Marco Tiraboschi
Michael Kuhinica
Fraser Cain
Robin Scharf
Oren Milman
John Rees
Gladamas
Shawn Hartsock
Seth Brothwell
Brian Goodrich
Michael S McReynolds

https://www.patreon.com/robertskmiles

Media Sources:
"DashCam Russia - Crazy Drivers and Car Crashes 2018" (https://youtu.be/h50TQ3i9k5I)
Optimist Prime
"Hapless Boston Dynamics robot in shelf-stacking fail" (https://youtu.be/JzlsvFN_5HI)
"The Simpsons - Bart Gets Famous" (c) Fox 1994
"Donald Duck - Cured Duck" (c) Disney 1945
"Vase Breaking Slow Motion" (https://youtu.be/IJNPc_anP7U)
"Fastest quadcopter i've ever flown + Most Destructive Crash" (https://youtu.be/OKT4cx7UKsk)
"An athlete uses physics to shatter world records - Asaf Bar-Yosef" (https://youtu.be/RaGUW1d0w8g)
"Uber self-driving car crash in Tempe, Arizona" (https://youtu.be/XtTB8hTgHbM)
"Quadcopter Fx Simulator" (https://youtu.be/-6si8WkRtaY)
"Fallout - New Vegas by progamingwithed in 24:00 - AGDQ 2017 - Part 59" (https://youtu.be/nuzDif16_nc)
"Far Cry 5 out of 5 Physics Simulation" (https://youtu.be/4My0Bt30pX0) ...

Continuing to address the challenges of AI safety, Rob Miles discusses a paper from the Machine Intelligence Research Institute (MIRI). Read the paper for yourself here: http://bit.ly/LogicalInduction More from Rob Miles: http://bit.ly/Rob_Miles_YouTube https://www.facebook.com/computerphile https://twitter.com/computer_phile This video was filmed and edited by Sean Riley. Computer Science at the University of Nottingham: https://bit.ly/nottscomputer Computerphile is a sister project to Brady Haran's Numberphile. More at http://www.bradyharan.com 27:48
AI & Logical Induction - Computerphile
YouTube Video UExTQ29YT1J1Z25sWXlvaE5kYzBfZVhOaHB5b016OWlWeS5DQ0MyQ0Y4Mzg0M0VGOEYw

AI & Logical Induction - Computerphile

October 4, 2018 4:04 pm

Continuing to address the challenges of AI safety, Rob Miles discusses a paper from the Machine Intelligence Research Institute (MIRI).

Read the paper for yourself here: http://bit.ly/LogicalInduction

More from Rob Miles: http://bit.ly/Rob_Miles_YouTube

https://www.facebook.com/computerphile
https://twitter.com/computer_phile

This video was filmed and edited by Sean Riley.

Computer Science at the University of Nottingham: https://bit.ly/nottscomputer

Computerphile is a sister project to Brady Haran's Numberphile. More at http://www.bradyharan.com ...

[2nd upload] AI systems can be trained using demonstrations from experts, but how do you train them to out-perform those experts? Can this still be done even without clear win/loss criteria? And how do you do it safely? This video was based on work including: "Supervising strong learners by amplifying weak experts" by Paul Christiano, Buck Shlegeris, Dario Amodei (https://arxiv.org/abs/1810.08575) https://openai.com/blog/amplifying-ai-training/ https://www.alignmentforum.org/s/EmDuGeRw749sD3GKd https://ai-alignment.com/iterated-distillation-and-amplification-157debfd1616 With thanks to my wonderful Patrons: ( https://www.patreon.com/robertskmiles ) Steef Jason Strack Jordan Medina Jason Hise Scott Worley JJ Hepboin Pedro A Ortega Said Polat Chris Canal Nicholas Kees Dupuis James Richárd Nagyfi Phil Moyer Alec Johnson Clemens Arbesser Bryce Daifuku Simon Strandgaard Jonatan R Michael Greve The Guru Of Vision Volodymyr David Tjäder Julius Brash Tom O'Connor Erik de Bruijn Robin Green Laura Olds Jon Halliday Paul Hobbs Jeroen De Dauw Tim Neilson Eric Scammell Igor Keller Ben Glanton Robert Sokolowski anul kumar sinha Jérôme Frossard Sean Gibat Sun Sun andrew Russell Cooper Lawton Gladamas Sylvain Chevalier DGJono robertvanduursen Dmitri Afanasjev Brian Sandberg Einar Ueland Marcel Ward Andrew Weir Taylor Smith Ben Archer Scott McCarthy Kabs Kabs Kabs Tendayi Mawushe Jannik Olbrich Anne Kohlbrenner Bjorn Nyblad Jussi Männistö Mr Fantastic Wr4thon Archy de Berker Marc Pauly Joshua Pratt Shevis Johnson Andy Kobre Brian Gillespie Martin Wind Peggy Youell Poker Chen Kees Darko Sperac Truls Paul Moffat Jelle Langen Anders Öhrt Marco Tiraboschi Michael Kuhinica Fraser Cain Robin Scharf Oren Milman John Rees Shawn Hartsock Seth Brothwell Brian Goodrich Clark Mitchell Kasper Schnack Michael Hunter Klemen Slavic Patrick Henderson Long Nguyen Oct todo22 Melisa Kostrzewski Hendrik Daniel Munter Graham Henry Duncan Orr 11:32
How to Keep Improving When You're Better Than Any Teacher - Iterated Distillation and Amplification
YouTube Video UExTQ29YT1J1Z25sWXlvaE5kYzBfZVhOaHB5b016OWlWeS5EMEEwRUY5M0RDRTU3NDJC

How to Keep Improving When You're Better Than Any Teacher - Iterated Distillation and Amplification

March 11, 2019 2:14 pm

[2nd upload] AI systems can be trained using demonstrations from experts, but how do you train them to out-perform those experts? Can this still be done even without clear win/loss criteria? And how do you do it safely?

This video was based on work including:
"Supervising strong learners by amplifying weak experts" by Paul Christiano, Buck Shlegeris, Dario Amodei (https://arxiv.org/abs/1810.08575)
https://openai.com/blog/amplifying-ai-training/
https://www.alignmentforum.org/s/EmDuGeRw749sD3GKd
https://ai-alignment.com/iterated-distillation-and-amplification-157debfd1616

With thanks to my wonderful Patrons: ( https://www.patreon.com/robertskmiles )
Steef
Jason Strack
Jordan Medina
Jason Hise
Scott Worley
JJ Hepboin
Pedro A Ortega
Said Polat
Chris Canal
Nicholas Kees Dupuis
James
Richárd Nagyfi
Phil Moyer
Alec Johnson
Clemens Arbesser
Bryce Daifuku
Simon Strandgaard
Jonatan R
Michael Greve
The Guru Of Vision
Volodymyr
David Tjäder
Julius Brash
Tom O'Connor
Erik de Bruijn
Robin Green
Laura Olds
Jon Halliday
Paul Hobbs
Jeroen De Dauw
Tim Neilson
Eric Scammell
Igor Keller
Ben Glanton
Robert Sokolowski
anul kumar sinha
Jérôme Frossard
Sean Gibat
Sun Sun
andrew Russell
Cooper Lawton
Gladamas
Sylvain Chevalier
DGJono
robertvanduursen
Dmitri Afanasjev
Brian Sandberg
Einar Ueland
Marcel Ward
Andrew Weir
Taylor Smith
Ben Archer
Scott McCarthy
Kabs Kabs Kabs
Tendayi Mawushe
Jannik Olbrich
Anne Kohlbrenner
Bjorn Nyblad
Jussi Männistö
Mr Fantastic
Wr4thon
Archy de Berker
Marc Pauly
Joshua Pratt
Shevis Johnson
Andy Kobre
Brian Gillespie
Martin Wind
Peggy Youell
Poker Chen
Kees
Darko Sperac
Truls
Paul Moffat
Jelle Langen
Anders Öhrt
Marco Tiraboschi
Michael Kuhinica
Fraser Cain
Robin Scharf
Oren Milman
John Rees
Shawn Hartsock
Seth Brothwell
Brian Goodrich
Clark Mitchell
Kasper Schnack
Michael Hunter
Klemen Slavic
Patrick Henderson
Long Nguyen
Oct todo22
Melisa Kostrzewski
Hendrik
Daniel Munter
Graham Henry
Duncan Orr ...

Plausible text generation has been around for a couple of years, but how does it work - and what's next? Rob Miles on Language Models and Transformers. More from Rob Miles: http://bit.ly/Rob_Miles_YouTube AI YouTube Comments: https://youtu.be/XyMdpcAPnZc Thanks to Nottingham Hackspace for providing the filming location: http://bit.ly/notthack https://www.facebook.com/computerphile https://twitter.com/computer_phile This video was filmed and edited by Sean Riley. Computer Science at the University of Nottingham: https://bit.ly/nottscomputer Computerphile is a sister project to Brady Haran's Numberphile. More at http://www.bradyharan.com 20:39
AI Language Models & Transformers - Computerphile
YouTube Video UExTQ29YT1J1Z25sWXlvaE5kYzBfZVhOaHB5b016OWlWeS4yQUE2Q0JEMTk4NTM3RTZC

AI Language Models & Transformers - Computerphile

June 26, 2019 4:06 pm

Plausible text generation has been around for a couple of years, but how does it work - and what's next? Rob Miles on Language Models and Transformers.

More from Rob Miles: http://bit.ly/Rob_Miles_YouTube

AI YouTube Comments: https://youtu.be/XyMdpcAPnZc

Thanks to Nottingham Hackspace for providing the filming location: http://bit.ly/notthack

https://www.facebook.com/computerphile
https://twitter.com/computer_phile

This video was filmed and edited by Sean Riley.

Computer Science at the University of Nottingham: https://bit.ly/nottscomputer

Computerphile is a sister project to Brady Haran's Numberphile. More at http://www.bradyharan.com ...

GPT-2, the Language model that shocked the world with its entirely fictitious story about the unicorns inhabiting a secret South American valley. Rob Miles explains More on GPT-2: Coming Soon More from Rob Miles: http://bit.ly/Rob_Miles_YouTube Thanks to Nottingham Hackspace for providing the filming location: http://bit.ly/notthack https://www.facebook.com/computerphile https://twitter.com/computer_phile This video was filmed and edited by Sean Riley. Computer Science at the University of Nottingham: https://bit.ly/nottscomputer Computerphile is a sister project to Brady Haran's Numberphile. More at http://www.bradyharan.com 11:57
Unicorn AI - Computerphile
YouTube Video UExTQ29YT1J1Z25sWXlvaE5kYzBfZVhOaHB5b016OWlWeS5DMkU4NTY1QUFGQTYwMDE3

Unicorn AI - Computerphile

July 4, 2019 4:44 pm

GPT-2, the Language model that shocked the world with its entirely fictitious story about the unicorns inhabiting a secret South American valley. Rob Miles explains

More on GPT-2: Coming Soon

More from Rob Miles: http://bit.ly/Rob_Miles_YouTube

Thanks to Nottingham Hackspace for providing the filming location: http://bit.ly/notthack

https://www.facebook.com/computerphile
https://twitter.com/computer_phile

This video was filmed and edited by Sean Riley.

Computer Science at the University of Nottingham: https://bit.ly/nottscomputer

Computerphile is a sister project to Brady Haran's Numberphile. More at http://www.bradyharan.com ...

Powerful AI systems can be dangerous in part because they pursue their goals as strongly as they can. Perhaps it would be safer to have systems that don't aim for perfection, and stop at 'good enough'. How could we build something like that? Generating Fake YouTube comments with GPT-2: https://youtu.be/M6EXmoP5jX8 Computerphile Videos: Unicorn AI: https://youtu.be/89A4jGvaaKk More GPT-2, the 'writer' of Unicorn AI: https://youtu.be/p-6F4rhRYLQ AI Language Models & Transformers: https://youtu.be/rURRYI66E54 GPT-2: Why Didn't They Release It?: https://youtu.be/AJxLtdur5fc The Deadly Truth of General AI?: https://youtu.be/tcdVC4e6EV4 With thanks to my excellent Patreon supporters: https://www.patreon.com/robertskmiles Scott Worley Jordan Medina Simon Strandgaard JJ Hepboin Lupuleasa Ionuț Pedro A Ortega Said Polat Chris Canal Nicholas Kees Dupuis Jake Ehrlich Mark Hechim Kellen lask Francisco Tolmasky Michael Andregg Alexandru Dobre David Reid Robert Daniel Pickard Peter Rolf Chad Jones Truthdoc James Richárd Nagyfi Jason Hise Phil Moyer Shevis Johnson Alec Johnson Clemens Arbesser Ludwig Schubert Bryce Daifuku Allen Faure Eric James Jonatan R Ingvi Gautsson Michael Greve Julius Brash Tom O'Connor Erik de Bruijn Robin Green Laura Olds Jon Halliday Paul Hobbs Jeroen De Dauw Tim Neilson Eric Scammell Igor Keller Ben Glanton Robert Sokolowski anul kumar sinha Jérôme Frossard Sean Gibat Cooper Lawton Tyler Herrmann Tomas Sayder Ian Munro Jérôme Beaulieu Taras Bobrovytsky Anne Buit Tom Murphy Vaskó Richárd Sebastian Birjoveanu Gladamas Sylvain Chevalier DGJono Dmitri Afanasjev Brian Sandberg Marcel Ward Andrew Weir Ben Archer Scott McCarthy Kabs Miłosz Wierzbicki Tendayi Mawushe Jannik Olbrich Anne Kohlbrenner Jussi Männistö Mr Fantastic Wr4thon Martin Ottosen Archy de Berker Marc Pauly Joshua Pratt Andy Kobre Brian Gillespie Martin Wind Peggy Youell Poker Chen Kees Darko Sperac Truls Paul Moffat Anders Öhrt Marco Tiraboschi Michael Kuhinica Fraser Cain Robin Scharf Oren Milman John Rees Seth Brothwell Clark Mitchell Kasper Schnack Michael Hunter Klemen Slavic Patrick Henderson Long Nguyen Melisa Kostrzewski Hendrik Daniel Munter Graham Henry Volotat Duncan Orr Marin Aldimirov Bryan Egan James Fowkes Frame Problems Alan Bandurka Benjamin Hull Tatiana Ponomareva Aleksi Maunu Michael Bates Simon Pilkington Dion Gerald Bridger Steven Cope Marcos Alfredo Núñez Petr Smital Daniel Kokotajlo Fionn Yuchong Li Nathan Fish Diagon Parker Lund Russell schoen Andreas Blomqvist Bertalan Bodor David Morgan Ben Schultz Zannheim Daniel Eickhardt lyon549 HD https://www.patreon.com/robertskmiles 10:22
AI That Doesn't Try Too Hard - Maximizers and Satisficers
YouTube Video UExTQ29YT1J1Z25sWXlvaE5kYzBfZVhOaHB5b016OWlWeS40NzZCMERDMjVEN0RFRThB

AI That Doesn't Try Too Hard - Maximizers and Satisficers

August 23, 2019 5:05 pm

Powerful AI systems can be dangerous in part because they pursue their goals as strongly as they can. Perhaps it would be safer to have systems that don't aim for perfection, and stop at 'good enough'. How could we build something like that?

Generating Fake YouTube comments with GPT-2: https://youtu.be/M6EXmoP5jX8

Computerphile Videos:
Unicorn AI: https://youtu.be/89A4jGvaaKk
More GPT-2, the 'writer' of Unicorn AI: https://youtu.be/p-6F4rhRYLQ
AI Language Models & Transformers: https://youtu.be/rURRYI66E54
GPT-2: Why Didn't They Release It?: https://youtu.be/AJxLtdur5fc
The Deadly Truth of General AI?: https://youtu.be/tcdVC4e6EV4


With thanks to my excellent Patreon supporters:
https://www.patreon.com/robertskmiles

Scott Worley
Jordan Medina
Simon Strandgaard
JJ Hepboin
Lupuleasa Ionuț
Pedro A Ortega
Said Polat
Chris Canal
Nicholas Kees Dupuis
Jake Ehrlich
Mark Hechim
Kellen lask
Francisco Tolmasky
Michael Andregg
Alexandru Dobre
David Reid
Robert Daniel Pickard
Peter Rolf
Chad Jones
Truthdoc
James
Richárd Nagyfi
Jason Hise
Phil Moyer
Shevis Johnson
Alec Johnson
Clemens Arbesser
Ludwig Schubert
Bryce Daifuku
Allen Faure
Eric James
Jonatan R
Ingvi Gautsson
Michael Greve
Julius Brash
Tom O'Connor
Erik de Bruijn
Robin Green
Laura Olds
Jon Halliday
Paul Hobbs
Jeroen De Dauw
Tim Neilson
Eric Scammell
Igor Keller
Ben Glanton
Robert Sokolowski
anul kumar sinha
Jérôme Frossard
Sean Gibat
Cooper Lawton
Tyler Herrmann
Tomas Sayder
Ian Munro
Jérôme Beaulieu
Taras Bobrovytsky
Anne Buit
Tom Murphy
Vaskó Richárd
Sebastian Birjoveanu
Gladamas
Sylvain Chevalier
DGJono
Dmitri Afanasjev
Brian Sandberg
Marcel Ward
Andrew Weir
Ben Archer
Scott McCarthy
Kabs
Miłosz Wierzbicki
Tendayi Mawushe
Jannik Olbrich
Anne Kohlbrenner
Jussi Männistö
Mr Fantastic
Wr4thon
Martin Ottosen
Archy de Berker
Marc Pauly
Joshua Pratt
Andy Kobre
Brian Gillespie
Martin Wind
Peggy Youell
Poker Chen
Kees
Darko Sperac
Truls
Paul Moffat
Anders Öhrt
Marco Tiraboschi
Michael Kuhinica
Fraser Cain
Robin Scharf
Oren Milman
John Rees
Seth Brothwell
Clark Mitchell
Kasper Schnack
Michael Hunter
Klemen Slavic
Patrick Henderson
Long Nguyen
Melisa Kostrzewski
Hendrik
Daniel Munter
Graham Henry
Volotat
Duncan Orr
Marin Aldimirov
Bryan Egan
James Fowkes
Frame Problems
Alan Bandurka
Benjamin Hull
Tatiana Ponomareva
Aleksi Maunu
Michael Bates
Simon Pilkington
Dion Gerald Bridger
Steven Cope
Marcos Alfredo Núñez
Petr Smital
Daniel Kokotajlo
Fionn
Yuchong Li
Nathan Fish
Diagon
Parker Lund
Russell schoen
Andreas Blomqvist
Bertalan Bodor
David Morgan
Ben Schultz
Zannheim
Daniel Eickhardt
lyon549
HD

https://www.patreon.com/robertskmiles ...

How do you represent a word in AI? Rob Miles reveals how words can be formed from multi-dimensional vectors - with some unexpected results. 08:06 - Yes, it's a rubber egg :) Unicorn AI: EXTRA BITS: https://youtu.be/usthqKtw2LA AI YouTube Comments: https://youtu.be/XyMdpcAPnZc More from Rob Miles: http://bit.ly/Rob_Miles_YouTube Thanks to Nottingham Hackspace for providing the filming location: http://bit.ly/notthack https://www.facebook.com/computerphile https://twitter.com/computer_phile This video was filmed and edited by Sean Riley. Computer Science at the University of Nottingham: https://bit.ly/nottscomputer Computerphile is a sister project to Brady Haran's Numberphile. More at http://www.bradyharan.com 16:56
Vectoring Words (Word Embeddings) - Computerphile
YouTube Video UExTQ29YT1J1Z25sWXlvaE5kYzBfZVhOaHB5b016OWlWeS41QUZGQTY5OTE4QTREQUU4

Vectoring Words (Word Embeddings) - Computerphile

October 23, 2019 6:55 pm

How do you represent a word in AI? Rob Miles reveals how words can be formed from multi-dimensional vectors - with some unexpected results.

08:06 - Yes, it's a rubber egg :)

Unicorn AI:
EXTRA BITS: https://youtu.be/usthqKtw2LA
AI YouTube Comments: https://youtu.be/XyMdpcAPnZc

More from Rob Miles: http://bit.ly/Rob_Miles_YouTube

Thanks to Nottingham Hackspace for providing the filming location: http://bit.ly/notthack

https://www.facebook.com/computerphile
https://twitter.com/computer_phile

This video was filmed and edited by Sean Riley.

Computer Science at the University of Nottingham: https://bit.ly/nottscomputer

Computerphile is a sister project to Brady Haran's Numberphile. More at http://www.bradyharan.com ...

How do you get a reinforcement learning agent to do what you want, when you can't actually write a reward function that specifies what that is? The paper: https://arxiv.org/pdf/1706.03741.pdf The blogpost: https://openai.com/blog/deep-reinforcement-learning-from-human-preferences/ Thanks to my wonderful patrons: https://www.patreon.com/robertskmiles James Gladamas Steef Scott Worley Jordan Medina Simon Strandgaard JJ Hepboin Pedro A Ortega Said Polat Chris Canal Jake Ehrlich Kellen lask Francisco Tolmasky Michael Andregg David Reid Robert Daniel Pickard Peter Rolf Chad Jones Richárd Nagyfi Jason Hise Phil Moyer Shevis Johnson Erik de Bruijn Alec Johnson Clemens Arbesser Ludwig Schubert Bryce Daifuku Allen Faure Eric James Qeith Wreid Jonatan R Ingvi Gautsson Michael Greve Julius Brash Tom O'Connor Robin Green Laura Olds Jon Halliday Paul Hobbs Jeroen De Dauw Lupuleasa Ionuț Tim Neilson Eric Scammell Igor Keller Ben Glanton anul kumar sinha Sean Gibat Cooper Lawton Will Glynn Tyler Herrmann Tomas Sayder Ian Munro Jérôme Beaulieu Nathan Fish Taras Bobrovytsky Anne Buit Vaskó Richárd Sebastian Birjoveanu Euclidean Plane Andrew Harcourt DGJono robertvanduursen Dmitri Afanasjev Marcel Ward Andrew Weir Ben Archer Kabs Miłosz Wierzbicki Tendayi Mawushe Jannik Olbrich Anne Kohlbrenner Jussi Männistö Wr4thon Martin Ottosen Archy de Berker Marc Pauly Andy Kobre Brian Gillespie Poker Chen Kees Darko Sperac Truls Paul Moffat Anders Öhrt Marco Tiraboschi Michael Kuhinica Fraser Cain Robin Scharf Seth Brothwell Kasper Schnack Klemen Slavic Patrick Henderson Oct todo22 Melisa Kostrzewski Hendrik Daniel Munter Graham Henry Duncan Orr Bryan Egan Robert Hildebrandt James Fowkes Alan Bandurka Ben H Tatiana Ponomareva Michael Bates Simon Pilkington Dion Gerald Bridger Petr Smital Daniel Kokotajlo Fionn Yuchong Li Diagon Parker Lund Paul Emmerich Russell schoen Andreas Blomqvist Bertalan Bodor David Morgan Jeremy Ben Schultz Zannheim Daniel Eickhardt lyon549 HD Ihor Mukha 14zRobot Ivan Arne Strasser Jason Cherry Igor (Kerogi) Kostenko Isaac Boates Thomas Dingemanse Davy Ker Alexander Brown Devon Bernard Ted Stokes James Helms Matheson Bayley https://www.patreon.com/robertskmiles 17:52
Training AI Without Writing A Reward Function, with Reward Modelling
YouTube Video UExTQ29YT1J1Z25sWXlvaE5kYzBfZVhOaHB5b016OWlWeS5GNjNDRDREMDQxOThCMDQ2

Training AI Without Writing A Reward Function, with Reward Modelling

December 13, 2019 6:39 pm

How do you get a reinforcement learning agent to do what you want, when you can't actually write a reward function that specifies what that is?

The paper: https://arxiv.org/pdf/1706.03741.pdf
The blogpost: https://openai.com/blog/deep-reinforcement-learning-from-human-preferences/

Thanks to my wonderful patrons:
https://www.patreon.com/robertskmiles
James
Gladamas
Steef
Scott Worley
Jordan Medina
Simon Strandgaard
JJ Hepboin
Pedro A Ortega
Said Polat
Chris Canal
Jake Ehrlich
Kellen lask
Francisco Tolmasky
Michael Andregg
David Reid
Robert Daniel Pickard
Peter Rolf
Chad Jones
Richárd Nagyfi
Jason Hise
Phil Moyer
Shevis Johnson
Erik de Bruijn
Alec Johnson
Clemens Arbesser
Ludwig Schubert
Bryce Daifuku
Allen Faure
Eric James
Qeith Wreid
Jonatan R
Ingvi Gautsson
Michael Greve
Julius Brash
Tom O'Connor
Robin Green
Laura Olds
Jon Halliday
Paul Hobbs
Jeroen De Dauw
Lupuleasa Ionuț
Tim Neilson
Eric Scammell
Igor Keller
Ben Glanton
anul kumar sinha
Sean Gibat
Cooper Lawton
Will Glynn
Tyler Herrmann
Tomas Sayder
Ian Munro
Jérôme Beaulieu
Nathan Fish
Taras Bobrovytsky
Anne Buit
Vaskó Richárd
Sebastian Birjoveanu
Euclidean Plane
Andrew Harcourt
DGJono
robertvanduursen
Dmitri Afanasjev
Marcel Ward
Andrew Weir
Ben Archer
Kabs
Miłosz Wierzbicki
Tendayi Mawushe
Jannik Olbrich
Anne Kohlbrenner
Jussi Männistö
Wr4thon
Martin Ottosen
Archy de Berker
Marc Pauly
Andy Kobre
Brian Gillespie
Poker Chen
Kees
Darko Sperac
Truls
Paul Moffat
Anders Öhrt
Marco Tiraboschi
Michael Kuhinica
Fraser Cain
Robin Scharf
Seth Brothwell
Kasper Schnack
Klemen Slavic
Patrick Henderson
Oct todo22
Melisa Kostrzewski
Hendrik
Daniel Munter
Graham Henry
Duncan Orr
Bryan Egan
Robert Hildebrandt
James Fowkes
Alan Bandurka
Ben H
Tatiana Ponomareva
Michael Bates
Simon Pilkington
Dion Gerald Bridger
Petr Smital
Daniel Kokotajlo
Fionn
Yuchong Li
Diagon
Parker Lund
Paul Emmerich
Russell schoen
Andreas Blomqvist
Bertalan Bodor
David Morgan
Jeremy
Ben Schultz
Zannheim
Daniel Eickhardt
lyon549
HD
Ihor Mukha
14zRobot
Ivan
Arne Strasser
Jason Cherry
Igor (Kerogi) Kostenko
Isaac Boates
Thomas Dingemanse
Davy Ker
Alexander Brown
Devon Bernard
Ted Stokes
James Helms
Matheson Bayley
https://www.patreon.com/robertskmiles ...

Check out today's sponsor Fasthosts for all of your UK web hosting needs: https://www.fasthosts.co.uk/computerphile Rob Miles discusses the idea of a gym for training AI algorithms. https://www.facebook.com/computerphile https://twitter.com/computer_phile This video was filmed and edited by Sean Riley. Computer Science at the University of Nottingham: https://bit.ly/nottscomputer Computerphile is a sister project to Brady Haran's Numberphile. More at http://www.bradyharan.com 16:00
AI Safety Gym - Computerphile
YouTube Video UExTQ29YT1J1Z25sWXlvaE5kYzBfZVhOaHB5b016OWlWeS44Mjc5REFBRUE2MTdFRDU0

AI Safety Gym - Computerphile

January 30, 2020 8:15 pm

Check out today's sponsor Fasthosts for all of your UK web hosting needs: https://www.fasthosts.co.uk/computerphile

Rob Miles discusses the idea of a gym for training AI algorithms.

https://www.facebook.com/computerphile
https://twitter.com/computer_phile

This video was filmed and edited by Sean Riley.

Computer Science at the University of Nottingham: https://bit.ly/nottscomputer

Computerphile is a sister project to Brady Haran's Numberphile. More at http://www.bradyharan.com ...

AI systems do what you say, and it's hard to say exactly what you mean. Let's look at a list of real life examples of specification gaming! Related Videos from me: Reward Hacking: https://youtu.be/92qDfT8pENs Reward Hacking Reloaded: https://youtu.be/46nsTFfsBuc What Can We Do About Reward Hacking?: https://youtu.be/13tZ9Yia71c The list: http://tinyurl.com/specification-gaming The blogpost this video is based on: https://vkrakovna.wordpress.com/2018/04/02/specification-gaming-examples-in-ai/ The newer blogpost that happened while I was making this video: https://deepmind.com/blog/article/Specification-gaming-the-flip-side-of-AI-ingenuity (Explosion graphic from videezy.com) Thanks to my wonderful patrons: https://www.patreon.com/robertskmiles Gladamas James Steef Scott Worley Chad Jones Chris Canal David Reid Francisco Tolmasky Frank Kurka Jake Ehrlich JJ Hepboin Kellen lask Michael Andregg Pedro A Ortega Peter Rolf Said Polat Teague Lasser Allen Faure Bryce Daifuku Clemens Arbesser Eric James Erik de Bruijn Jason Hise jugettje dutchking Ludwig Schubert Qeith Wreid Andrew Harcourt anul kumar sinha Ben Glanton Benjamin Watkin Cooper Lawton Duncan Orr Eric Scammell Euclidean Plane Ian Munro Igor Keller Ingvi Gautsson James Hinchcliffe Jeroen De Dauw Jon Halliday Jonatan R Julius Brash Jérôme Beaulieu Laura Olds Luc Ritchie Lupuleasa Ionuț Michael Greve Nathan Fish Nicholas Guyett Paul Hobbs Sean Gibat Sebastian Birjoveanu Shevis Johnson Taras Bobrovytsky Tim Neilson Tom O'Connor Tomas Sayder Tyler Herrmann Vaskó Richárd Will Glynn 12tone 14zRobot Alan Bandurka Alexander Brown Anders Öhrt Andreas Blomqvist Andrew Weir Andy Kobre Anne Kohlbrenner Anthony Chiu Archy de Berker Ben Archer Ben H Ben Schultz Bertalan Bodor Brian Gillespie Bryan Egan Caleb Chris Dinant Daniel Bartovic Daniel Eickhardt Daniel Kokotajlo Daniel Munter Darko Sperac David Morgan DeepFriedJif Devon Bernard Diagon Dmitri Afanasjev Fionn Fraser Cain Garrett Maring Ghaith Tarawneh HD Hendrik ib_ Igor (Kerogi) Kostenko Ihor Mukha Ivan James Fowkes Jannik Olbrich Jason Cherry Jeremy Jesper Andersson Jim T Johannes Walter Josh Trevisiol Julian Schulz Jussi Männistö Kabs Kasper Kasper Schnack Kees Klemen Slavic Leo lyon549 Marc Pauly Marcel Ward Marco Tiraboschi Marko Topolnik Martin Ottosen Matt Stanton Melisa Kostrzewski Michael Bates Michael Kuhinica Miłosz Wierzbicki Mo Hossny Nathaniel Raddin Oct todo22 Owen Campbell-Moore Parker Lund Patrick Henderson Paul Moffat Poker Chen Rob Dawson Robert Hildebrandt robertvanduursen Robin Scharf Russell schoen Scott Viteri Simon Pilkington Stellated Hexahedron Tatiana Ponomareva Ted Stokes Tendayi Mawushe Thomas Dingemanse 9:40
9 Examples of Specification Gaming
YouTube Video UExTQ29YT1J1Z25sWXlvaE5kYzBfZVhOaHB5b016OWlWeS42MTI4Njc2QjM1RjU1MjlG

9 Examples of Specification Gaming

April 29, 2020 6:41 pm

AI systems do what you say, and it's hard to say exactly what you mean.
Let's look at a list of real life examples of specification gaming!

Related Videos from me:
Reward Hacking: https://youtu.be/92qDfT8pENs
Reward Hacking Reloaded: https://youtu.be/46nsTFfsBuc
What Can We Do About Reward Hacking?: https://youtu.be/13tZ9Yia71c

The list: http://tinyurl.com/specification-gaming
The blogpost this video is based on: https://vkrakovna.wordpress.com/2018/04/02/specification-gaming-examples-in-ai/
The newer blogpost that happened while I was making this video: https://deepmind.com/blog/article/Specification-gaming-the-flip-side-of-AI-ingenuity

(Explosion graphic from videezy.com)

Thanks to my wonderful patrons:
https://www.patreon.com/robertskmiles

Gladamas
James
Steef
Scott Worley
Chad Jones
Chris Canal
David Reid
Francisco Tolmasky
Frank Kurka
Jake Ehrlich
JJ Hepboin
Kellen lask
Michael Andregg
Pedro A Ortega
Peter Rolf
Said Polat
Teague Lasser
Allen Faure
Bryce Daifuku
Clemens Arbesser
Eric James
Erik de Bruijn
Jason Hise
jugettje dutchking
Ludwig Schubert
Qeith Wreid
Andrew Harcourt
anul kumar sinha
Ben Glanton
Benjamin Watkin
Cooper Lawton
Duncan Orr
Eric Scammell
Euclidean Plane
Ian Munro
Igor Keller
Ingvi Gautsson
James Hinchcliffe
Jeroen De Dauw
Jon Halliday
Jonatan R
Julius Brash
Jérôme Beaulieu
Laura Olds
Luc Ritchie
Lupuleasa Ionuț
Michael Greve
Nathan Fish
Nicholas Guyett
Paul Hobbs
Sean Gibat
Sebastian Birjoveanu
Shevis Johnson
Taras Bobrovytsky
Tim Neilson
Tom O'Connor
Tomas Sayder
Tyler Herrmann
Vaskó Richárd
Will Glynn
12tone
14zRobot
Alan Bandurka
Alexander Brown
Anders Öhrt
Andreas Blomqvist
Andrew Weir
Andy Kobre
Anne Kohlbrenner
Anthony Chiu
Archy de Berker
Ben Archer
Ben H
Ben Schultz
Bertalan Bodor
Brian Gillespie
Bryan Egan
Caleb
Chris Dinant
Daniel Bartovic
Daniel Eickhardt
Daniel Kokotajlo
Daniel Munter
Darko Sperac
David Morgan
DeepFriedJif
Devon Bernard
Diagon
Dmitri Afanasjev
Fionn
Fraser Cain
Garrett Maring
Ghaith Tarawneh
HD
Hendrik
ib_
Igor (Kerogi) Kostenko
Ihor Mukha
Ivan
James Fowkes
Jannik Olbrich
Jason Cherry
Jeremy
Jesper Andersson
Jim T
Johannes Walter
Josh Trevisiol
Julian Schulz
Jussi Männistö
Kabs
Kasper
Kasper Schnack
Kees
Klemen Slavic
Leo
lyon549
Marc Pauly
Marcel Ward
Marco Tiraboschi
Marko Topolnik
Martin Ottosen
Matt Stanton
Melisa Kostrzewski
Michael Bates
Michael Kuhinica
Miłosz Wierzbicki
Mo Hossny
Nathaniel Raddin
Oct todo22
Owen Campbell-Moore
Parker Lund
Patrick Henderson
Paul Moffat
Poker Chen
Rob Dawson
Robert Hildebrandt
robertvanduursen
Robin Scharf
Russell schoen
Scott Viteri
Simon Pilkington
Stellated Hexahedron
Tatiana Ponomareva
Ted Stokes
Tendayi Mawushe
Thomas Dingemanse ...

Load More... Subscribe

Interviews and Talks

Industry Leaders and Notable Public Figures

Elon Musk

Sam Altman

Dario Amodei

Paul Christiano

Stephen Hawking

Notable

Explainers

Learn about the issue by some of the best explainers out there

Lethal Intelligence Microblog

Blow your mind with the latest stories

Capabilities

Deniers

Superintelligence

AI Corporates

Anthropocene

Utopia | Dystopia

Warning Signs

Ghost in the Machine

Favorite Microbloggers

AI Notkilleveryoneism Memes

@AISafetyMemes

Kat Woods

@Kat__Woods

Yanco

@the_yanco

lethalintelligence.ai

@lethal_ai

Down the Rabbit Hole

On the News

Institutes & Establishments

Subscribe for important updates !!!

Newsletter
Follow

Watch The Ultimate Guide here

(Part 1)

Part 2 released in

Days
Hours
Minutes
Seconds
Contact

© 2024 Lethal Intelligence – Ai.   All rights reserved. 

Newsletter

Receive important updates!

Follow
YouTube

Your email will not be shared with anyone and won’t be used for any reason besides notifying you when we have important updates or new content

×