Thank you for another great meeting in the AISafety.com Reading Group.
For session 126, we will read chapter 1 and 2 of “Embedded Agency” by Abram Demski and Scott Garrabrant:
https://www.alignmentforum.org/s/Rm6oQRJJmhGCcLvxh/p/i3BTagvt3HbPMx6PN
Join us by Skype (add “soeren.elverlin”) on Wednesday the 2nd of January 19:45 UTC.
Thank you for another great meeting in the AISafety.com Reading Group.
For session 125, we will read the second half of “The Vulnerable World Hypothesis” by Nick Bostrom (from page 16):
https://nickbostrom.com/papers/vulnerable.pdf
Join us by Skype (add “soeren.elverlin”) on Wednesday the 12th of December 19:45 UTC.
Thank you for another great meeting in the AISafety.com Reading Group.
For session 123, Robin Hanson will present his AI Safety skeptical views.
A short summary of his views can be found here: https://www.overcomingbias.com/2017/08/foom-justifies-ai-risk-efforts-now.html
A longer summary by Kaj Sotala is http://intelligence.org/files/AIFoomDebate.pdf#page=537 , starting from chapter 6.
Join us by Skype (add “soeren.elverlin”) on Wednesday the 28th of November 19:45 UTC.
Thank you for another great meeting in the AISafety.com Reading Group.
For session 122, we will read “Why Altruists Should Perhaps Not Prioritize Artificial Intelligence: A Lengthy Critique” by Magnus Vinding (chapters 5, 6, 7 and 8):
https://magnusvinding.com/2018/09/18/why-altruists-should-perhaps-not-prioritize-artificial-intelligence-a-lengthy-critique/
Join us by Skype (add “soeren.elverlin”) on Tuesday the 20th of November 19:45 UTC.
Thank you for another great meeting in the AISafety.com Reading Group.
For session 121, we will read “Building Safer AGI by introducing Artificial Stupidity” by Michaël Trazzi1 and Roman V. Yampolskiy:
https://arxiv.org/pdf/1808.03644.pdf
Join us by Skype (add “soeren.elverlin”) on Thursday the 15th of November 19:45 UTC.
Roman Yampolskiy will present his work and answer questions.
Thank you for another great meeting in the AISafety.com Reading Group.
For session 120, we will read “Why Altruists Should Perhaps Not Prioritize Artificial Intelligence: A Lengthy Critique” by Magnus Vinding (focus on chapter 4, 7 and 8):
https://magnusvinding.com/2018/09/18/why-altruists-should-perhaps-not-prioritize-artificial-intelligence-a-lengthy-critique/
Join us by Skype (add “soeren.elverlin”) on Wednesday the 7th of November 19:45 UTC.
Thank you for another great meeting in the AISafety.com Reading Group.
For session 119, we will read the rest of “Are we Approaching an Economic Singularity?” by William D. Nordhaus (section 7 onwards):
https://www.nber.org/papers/w21547.pdf
Join us by Skype (add “soeren.elverlin”) on Tuesday the 30th of October 19:45 UTC.
Note UTC time change.
Thank you for another great meeting in the AISafety.com Reading Group.
For session 118, we will read section 1 to 6 of “Are we Approaching an Economic Singularity?” by William D. Nordhaus:
https://www.nber.org/papers/w21547.pdf
Join us by Skype (add “soeren.elverlin”) on Tuesday the 23rd of October 18:45 UTC.
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.