Home Creators Posts Import Register Favorites Logout
haven't archived this post yet. have a subscription? use the importer!

Content

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

This video gave me all kinds of trouble, so I had to split it in two; here's the first part!

Files

Previews only

Scalable Supervision: Concrete Problems in AI Safety Part 5

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

Comments

Anonymous

A paper that tries teaching the agent to see irreversible environment states before they happen and retrace its steps back to automatically reset itself without human intervention. <a href="https://arxiv.org/abs/1711.06782" rel="nofollow noopener" target="_blank">https://arxiv.org/abs/1711.06782</a> Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning

Anonymous

The orthogonality thesis is an excellent next subject. I have seen comparatively few arguments against it, it would be nice if you had the time to include a discussion of them.