Thank you for another great meeting in the AISafety.com Reading Group.
For session 131, we will read Critique of Superintelligence (Part 1 and 2), by Fods12:
https://forum.effectivealtruism.org/posts/A8ndMGC4FTQq46RRX/criqitue-of-superintelligence-part-1
Join us by Skype (add “soeren.elverlin”) on Thursday the 7th of January 19:45 UTC.
Thank you for another great meeting in the AISafety.com Reading Group. For session 130, Scott Garrabrant will be present and answer the questions we have gathered over the past 4…
Thank you for another great meeting in the AISafety.com Reading Group. For session 129, we will read chapter 5 and 6 of “Embedded Agency” by Abram Demski and Scott Garrabrant:…
Thank you for another great meeting in the AISafety.com Reading Group. For session 128, we will read chapter 4 of “Embedded Agency” by Abram Demski and Scott Garrabrant: https://www.alignmentforum.org/s/Rm6oQ…/p/i3BTagvt3HbPMx6PN… Join…
Thank you for another great meeting in the AISafety.com Reading Group. For session 127, we will read chapter 3 of “Embedded Agency” by Abram Demski and Scott Garrabrant: https://www.alignmentforum.org/s/Rm6oQRJJmhGCcLvxh/p/i3BTagvt3HbPMx6PN?fbclid=IwAR32u6iDVBxa-L-3N2sEFdxRrsLoaf_fbDn_jmXJxuZHeblamWa4z1BPdPk Join…
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:…
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…
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…
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…
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.…