DeepMind’s Take on How To Create a Benign AI

Channel:
Hungary Two Minute Papers
Subscribers:
1,550,000
Published on ● Video Link: https://www.youtube.com/watch?v=pc_k-sgUYmY


Duration: 4:15
54,677 views
1,746

The paper "Scalable agent alignment via reward modeling: a research direction" is available here:
1. https://arxiv.org/abs/1811.07871
2. https://medium.com/@deepmindsafetyresearch/scalable-agent-alignment-via-reward-modeling-bf4ab06dfd84

Pick up cool perks on our Patreon page:
› https://www.patreon.com/TwoMinutePapers

We would like to thank our generous Patreon supporters who make Two Minute Papers possible:
313V, Alex Haro, Andrew Melnychuk, Angelos Evripiotis, Anthony Vdovitchenko, Brian Gilman, Christian Ahlin, Christoph Jadanowski, Dennis Abts, Emmanuel, Eric Haddad, Eric Martel, Evan Breznyik, Geronimo Moralez, Jason Rollins, Javier Bustamante, John De Witt, Kaiesh Vohra, Kjartan Olason, Lorin Atzberger, Marcin Dukaczewski, Marcin Dukaczewski, Marten Rauschenberg, Maurits van Mastrigt, Michael Albrecht, Michael Jensen, Morten Punnerud Engelstad, Nader Shakerin, Owen Skarpness, Raul Araújo da Silva, Richard Reis, Rob Rowe, Robin Graham, Ryan Monsurate, Shawn Azman, Steef, Steve Messina, Sunil Kim, Thomas Krcmar, Torsten Reil, Zach Boldyga, Zach Doty.
https://www.patreon.com/TwoMinutePapers

Crypto and PayPal links are available below. Thank you very much for your generous support!
› PayPal: https://www.paypal.me/TwoMinutePapers
› Bitcoin: 1a5ttKiVQiDcr9j8JT2DoHGzLG7XTJccX
› Ethereum: 0xbBD767C0e14be1886c6610bf3F592A91D866d380
› LTC: LM8AUh5bGcNgzq6HaV1jeaJrFvmKxxgiXg

Thumbnail background image credit: https://pixabay.com/photo-3706562/
Splash screen/thumbnail design: Felícia Fehér - http://felicia.hu

Károly Zsolnai-Fehér's links:
Facebook: https://www.facebook.com/TwoMinutePapers/
Twitter: https://twitter.com/karoly_zsolnai
Web: https://cg.tuwien.ac.at/~zsolnai/



Other Videos By Two Minute Papers


2019-02-20This AI Learned Image Decolorization..and More
2019-02-16Extracting Rotations The Right Way
2019-02-12OpenAI - Learning Dexterous In-Hand Manipulation
2019-02-06DeepMind’s AlphaStar Beats Humans 10-0 (or 1)
2019-01-30AI Learns Real-Time Defocus Effects in VR
2019-01-27None of These Faces Are Real!
2019-01-23What Makes a Good Image Generator AI?
2019-01-19This AI Produces Binaural (2.5D) Audio
2019-01-156 Life Lessons I Learned From AI Research
2019-01-10This AI Learns From Humans…and Exceeds Them
2019-01-02DeepMind’s Take on How To Create a Benign AI
2018-12-21AI Learning Morphology and Movement...at the Same Time!
2018-12-15BigGANs: AI-Based High-Fidelity Image Synthesis
2018-12-11Can an AI Learn To Draw a Caricature?
2018-12-06This AI Learns Human Movement From Videos
2018-12-02Building a Curious AI With Random Network Distillation
2018-11-22This AI Learns Acrobatics by Watching YouTube
2018-11-17This Curious AI Beats Many Games...and Gets Addicted to the TV
2018-11-12This AI Learned To Isolate Speech Signals
2018-11-08This AI Shows Us the Sound of Pixels
2018-11-04Full-Time Papers, Maybe Someday?


Tags:
two minute papers
deep learning
ai
Scalable agent alignment via reward modeling: a research direction
agent alignment problem
deepmind
deepmind ai