RSS

avturchin

Karma: 3,518

AI safety in the age of neu­ral net­works and Stanis­law Lem 1959 prediction

avturchin6 Feb 2016 12:50 UTC
0 points
0 comments1 min readLW link
(lesswrong.com)

Mini-con­fer­ence “Near-term AI safety”

avturchin11 Oct 2017 14:54 UTC
2 points
3 comments1 min readLW link

Mili­tary AI as a Con­ver­gent Goal of Self-Im­prov­ing AI

avturchin13 Nov 2017 12:09 UTC
0 points
0 comments1 min readLW link
(www.academia.edu)

Mili­tary AI as a Con­ver­gent Goal of Self-Im­prov­ing AI

avturchin13 Nov 2017 12:17 UTC
5 points
3 comments1 min readLW link

Mes­sage to any fu­ture AI: “There are sev­eral in­stru­men­tal rea­sons why ex­ter­mi­nat­ing hu­man­ity is not in your in­ter­est” [AI al­ign­ment prize en­try]

avturchin25 Nov 2017 11:28 UTC
3 points
22 comments67 min readLW link

Mes­sage to Any Fu­ture AI: “There are sev­eral in­stru­men­tal rea­sons why ex­ter­mi­nat­ing hu­man­ity is not in your in­ter­est”

avturchin28 Nov 2017 15:39 UTC
0 points
0 comments1 min readLW link
(docs.google.com)

The map of “Levels of defence” in AI safety

avturchin12 Dec 2017 10:45 UTC
6 points
11 comments1 min readLW link

Paper: Ar­tifi­cial In­tel­li­gence in Life Ex­ten­sion: from Deep Learn­ing to Su­per­in­tel­li­gence

avturchin4 Jan 2018 14:21 UTC
3 points
5 comments2 min readLW link

[Paper] Global Catas­trophic and Ex­is­ten­tial Risks Com­mu­ni­ca­tion Scale, similar to Tor­ino scale

avturchin14 Jan 2018 10:29 UTC
3 points
4 comments2 min readLW link

The Utility of Hu­man Atoms for the Paper­clip Maximizer

avturchin2 Feb 2018 10:06 UTC
2 points
21 comments3 min readLW link

[Paper] Sur­viv­ing global risks through the preser­va­tion of hu­man­ity’s data on the Moon

avturchin4 Mar 2018 7:07 UTC
4 points
5 comments1 min readLW link

[Preprint for com­ment­ing] Digi­tal Im­mor­tal­ity: The­ory and Pro­to­col for Indi­rect Mind Uploading

avturchin27 Mar 2018 11:49 UTC
8 points
5 comments1 min readLW link

[Draft for com­ment­ing] Near-Term AI risks predictions

avturchin3 Apr 2018 10:29 UTC
6 points
6 comments1 min readLW link

[Preprint for com­ment­ing] Fight­ing Aging as an Effec­tive Altru­ism Cause

avturchin16 Apr 2018 13:55 UTC
9 points
5 comments1 min readLW link

Levels of AI Self-Im­prove­ment

avturchin29 Apr 2018 11:45 UTC
11 points
1 comment39 min readLW link

[Paper]: Clas­sifi­ca­tion of global catas­trophic risks con­nected with ar­tifi­cial intelligence

avturchin6 May 2018 6:42 UTC
1 point
0 comments1 min readLW link
(link.springer.com)

In­for­ma­tional haz­ards and the cost-effec­tive­ness of open dis­cus­sion of catas­trophic risks

avturchin23 Jun 2018 13:31 UTC
−2 points
11 comments4 min readLW link
(effective-altruism.com)

“Cheat­ing Death in Da­m­as­cus” Solu­tion to the Fermi Para­dox

avturchin30 Jun 2018 12:00 UTC
14 points
5 comments3 min readLW link

[1607.08289] “Mam­malian Value Sys­tems” (as a start­ing point for hu­man value sys­tem model cre­ated by IRL agent)

avturchin14 Jul 2018 9:46 UTC
9 points
9 comments1 min readLW link
(arxiv.org)

Nar­row AI Nanny: Reach­ing Strate­gic Ad­van­tage via Nar­row AI to Prevent Creation of the Danger­ous Superintelligence

avturchin25 Jul 2018 17:12 UTC
12 points
7 comments21 min readLW link