Thank you for another great meeting in the AISafety.com Reading Group.
For session 104, we will read “Towards Interactive Inverse Reinforcement Learning” by Stuart Armstrong and Jan Leike:
https://jan.leike.name/publications/Towards%20Interactive%20Inverse%20Reinforcement%20Learning%20-%20Armstrong,%20Leike%202016.pdf
(We also read this article for session 37)
Join us by Skype (add “soeren.elverlin”) on Wednesday the 11th of June 18:45 UTC.
Thank you for another great meeting in the AISafety.com Reading Group.
For session 103, we will read “AlphaGo Zero and the Foom Debate” by Eliezer Yudkowsky, and “What Evidence Is AlphaGo Zero Re AGI Complexity?” by Robin Hanson:
https://www.lesswrong.com/posts/D3NspiH2nhKA6B2PE/what-evidence-is-alphago-zero-re-agi-complexity
Join us by Skype (add “soeren.elverlin”) on Wednesday the 4th of July 18:45 UTC.
Thank you for another great meeting in the AISafety.com Reading Group.
For session 102, we will read page 526 to 559 of “The Hanson-Yudkowsky AI-Foom Debate” by Kaj Sotala:
https://intelligence.org/files/AIFoomDebate.pdf
Join us by Skype (add “soeren.elverlin”) on Thursday the 28th of June 19:45 UTC.
Thank you for another great meeting in the AISafety.com Reading Group.
For session 101, we will read page 505 to 526 of “The Hanson-Yudkowsky AI-Foom Debate” by Kaj Sotala:
https://intelligence.org/files/AIFoomDebate.pdf
Join us by Skype (add “soeren.elverlin”) on Wednesday the 20th of June 18:45 UTC.
Thank you for another great meeting in the AISafety.com Reading Group.
For session 100, we will read “Taking AI Risk Seriously” by Raemon following Andrew Critch:
https://www.lesswrong.com/posts/HnC29723hm6kJT7KP/taking-ai-risk-seriously-thoughts-by-critch
Join us by Skype (add “soeren.elverlin”) on Thursday the 14th of June 18:45 UTC.
Thank you for another great meeting in the AISafety.com Reading Group.
For session 99, we will read “Current thoughts on Paul Christano’s research agenda” by Jessica Taylor:
https://agentfoundations.org/item?id=1534
Join us by Skype (add “soeren.elverlin”) on Wednesday the 6th of June 18:45 UTC.
Thank you for another great meeting in the AISafety.com Reading Group.
For session 98, we will read “Challenges to Christiano’s capability amplification proposal” by Eliezer Yudkowsky:
https://intelligence.org/2018/05/19/challenges-to-christianos-capability-amplification-proposal/
Join us by Skype (add “soeren.elverlin”) on Wednesday the 30th of May 18:45 UTC.
Thank you for another great meeting in the AISafety.com Reading Group.
For session 97, we will read “Long-term strategies for ending existential risk from fast takeoff” by Daniel Dewey:
https://drive.google.com/file/d/1Q4ypVnZspoHTd0OjEJYUHvSvq3O9wjRM/view
Join us by Skype (add “soeren.elverlin”) on Thursday the 24th of May 18:45 UTC.
Thank you for another great meeting in the AISafety.com Reading Group.
For session 96, we will read the “AI Safety Skeptical” parts of “Machines that Think: The future of artificial intelligence” by Toby Walsh.
(It’s a book, message me for help). In particular, pages 10,13, 76-81, 128, 129, 163-178, 184-191.
Join us by Skype (add “soeren.elverlin”) on Wednesday the 16th of May 18:45 UTC.
Thank you for another great meeting in the AISafety.com Reading Group.
For session 95, we will read “Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm” by David Silver et al.:
https://arxiv.org/pdf/1712.01815.pdf
Join us by Skype (add “soeren.elverlin”) on Thursday the 10th of May 18:45 UTC.