RSS

rohinmshah

Karma: 761

[AN #80]: Why AI risk might be solved with­out ad­di­tional in­ter­ven­tion from longtermists

rohinmshah
3 Jan 2020 7:52 UTC
56 points
11 comments10 min readEA link
(www.alignmentforum.org)

Sum­mary of Stu­art Rus­sell’s new book, “Hu­man Com­pat­i­ble”

rohinmshah
19 Oct 2019 19:56 UTC
29 points
1 comment15 min readEA link
(www.alignmentforum.org)