Thank you for another great meeting in the AISafety.com Reading Group.
For session 117, we will read “The Rocket Alignment Problem” by Eliezer Yudkowsky:
https://intelligence.org/2018/10/03/rocket-alignment/
Join us by Skype (add “soeren.elverlin”) on Wednesday the 17th of October 18:45 UTC.
Thank you for another great meeting in the AISafety.com Reading Group.
For session 116, we will read “Technology Roulette – Managing Loss of Control as Many Militaries Pursue Technological Superiority” by Richard Danzig:
https://s3.amazonaws.com/files.cnas.org/documents/CNASReport-Technology-Roulette-DoSproof2v2.pdf?mtime=20180628072101
Join us by Skype (add “soeren.elverlin”) on Wednesday the 10th of October 18:45 UTC.
Thank you for another great meeting in the AISafety.com Reading Group.
For session 115, we will read “Towards a new Impact Measure” by Alex Turner:
https://www.alignmentforum.org/posts/yEa7kwoMpsBgaBCgb/towards-a-new-impact-measure
Read up to “Notation”, skip to “Experimental Results”, and then to “Desiderata”.
Join us by Skype (add “soeren.elverlin”) on Wednesday the 3rd of October 18:45 UTC.
Thank you for another great meeting in the AISafety.com Reading Group.
For session 114, we will read “Incomplete Contracting and AI Alignment” by Dylan Hadfield-Menell and Gillian K. Hadfield:
https://arxiv.org/pdf/1804.04268.pdf
Join us by Skype (add “soeren.elverlin”) on Wednesday the 19th of September 18:45 UTC.
Thank you for another great meeting in the AISafety.com Reading Group.
For session 113, we will read “Open Ended Intelligence – The individuation of Intelligent Agents” by David Weinbaum and Viktoras Veitas:
https://arxiv.org/pdf/1505.06366.pdf
We will skip chapter 4 for now, and maybe read it the following week.
Join us by Skype (add “soeren.elverlin”) on Wednesday the 12th of September 18:45 UTC.
Thank you for another great meeting in the AISafety.com Reading Group.
For session 112, we will reread “Strategic Implications of Openness in AI Development” by Nick Bostrom:
https://nickbostrom.com/papers/openness.pdf
Join us by Skype (add “soeren.elverlin”) on Wednesday the 5th of September 18:45 UTC.
Thank you for another great meeting in the AISafety.com Reading Group.
For session 111, we will read “A Survey of Artificial General Intelligence Projects for Ethics, Risk, and Policy” by Seth Baum:
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3070741
Focus on “Executive Summary”, “Main Results” and “Conclusion”.
Join us by Skype (add “soeren.elverlin”) on Wednesday the 29th of August 18:45 UTC.
Thank you for another great meeting in the AISafety.com Reading Group.
For session 110, we will read chapter “Strategic background” of “MIRI’s 2017 Fundraiser” by Malo Bourgon:
https://intelligence.org/2017/12/01/miris-2017-fundraiser/#3
We will also read “Two clarifications about ‘Strategic Background'” by Rob Bensinger:
https://www.lesswrong.com/posts/hL9ennoEfJXMj7r2D/two-clarifications-about-strategic-background
Join us by Skype (add “soeren.elverlin”) on Wednesday the 22nd of August 18:45 UTC.
Thank you for another great meeting in the AISafety.com Reading Group.
For session 109, we will read chapter 2 and 5 of “The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation” by Miles Brundage, Shahar Avin and many others:
https://www.eff.org/files/2018/02/20/malicious_ai_report_final.pdf
Join us by Skype (add “soeren.elverlin”) on Wednesday the 15th of August 18:45 UTC.
Thank you for another great meeting in the AISafety.com Reading Group.
For session 108, we will read “The Learning-Theoretic AI Alignment Research Agenda” by Vadim Kosoy:
https://agentfoundations.org/item?id=1816
(If you are pressed for time, skip section “Universal reinforcement learning”.)
Vadim Kosoy will present his research agenda, and participate in the discussion afterwards.
Join us by Skype (add “soeren.elverlin”) on Thursday the 9th of August 18:45 UTC.