RSS

Aryeh Englander

Karma: 1,417

I work on applied mathematics and AI at the Johns Hopkins University Applied Physics Laboratory (APL). I am also currently pursuing a PhD in Information Systems at the University of Maryland, Baltimore County (UMBC). My PhD research focuses on decision and risk analysis under extreme uncertainty, with a particular focus on potential existential risks from very advanced AI.

[Question] Good tax­onomies of all risks (small or large) from AI?

Aryeh Englander5 Mar 2024 18:15 UTC
6 points
1 comment1 min readLW link

High level overview on how to go about es­ti­mat­ing “p(doom)” or the like

Aryeh Englander27 Aug 2023 16:01 UTC
16 points
0 comments5 min readLW link

A Model-based Ap­proach to AI Ex­is­ten­tial Risk

25 Aug 2023 10:32 UTC
44 points
9 comments32 min readLW link

Flowchart: How might rogue AIs defeat all hu­mans?

Aryeh Englander12 Jul 2023 19:23 UTC
12 points
0 comments1 min readLW link

Three camps in AI x-risk dis­cus­sions: My per­sonal very over­sim­plified overview

Aryeh Englander4 Jul 2023 20:42 UTC
21 points
0 comments1 min readLW link

Re­quest: Put Carl Shul­man’s re­cent pod­cast into an or­ga­nized writ­ten format

Aryeh Englander28 Jun 2023 2:58 UTC
19 points
4 comments1 min readLW link

[Question] De­cep­tive AI vs. shift­ing in­stru­men­tal incentives

Aryeh Englander26 Jun 2023 18:09 UTC
7 points
2 comments3 min readLW link

[Question] Steel­man /​ Ide­olog­i­cal Tur­ing Test of Yann LeCun’s AI X-Risk ar­gu­ment?

Aryeh Englander4 Apr 2023 15:53 UTC
26 points
14 comments1 min readLW link

[Cross-post] Is the Fermi Para­dox due to the Flaw of Aver­ages?

18 Jan 2023 19:22 UTC
41 points
27 comments15 min readLW link
(lumina.com)

[Question] What would you ex­pect a mas­sive mul­ti­modal on­line fed­er­ated learner to be ca­pa­ble of?

Aryeh Englander27 Aug 2022 17:31 UTC
13 points
4 comments1 min readLW link

Epistemic mod­esty and how I think about AI risk

Aryeh Englander27 Jun 2022 18:47 UTC
22 points
4 comments4 min readLW link

[Link] OpenAI: Learn­ing to Play Minecraft with Video PreTrain­ing (VPT)

Aryeh Englander23 Jun 2022 16:29 UTC
53 points
3 comments1 min readLW link

Half-baked AI Safety ideas thread

Aryeh Englander23 Jun 2022 16:11 UTC
64 points
61 comments1 min readLW link

Will vague “AI sen­tience” con­cerns do more for AI safety than any­thing else we might do?

Aryeh Englander14 Jun 2022 23:53 UTC
15 points
2 comments1 min readLW link

[Link] New SEP ar­ti­cle on Bayesian Epistemology

Aryeh Englander13 Jun 2022 15:03 UTC
6 points
0 comments1 min readLW link

[Question] Why has no per­son /​ group ever taken over the world?

Aryeh Englander11 Jun 2022 20:51 UTC
25 points
19 comments1 min readLW link

AGI Safety FAQ /​ all-dumb-ques­tions-al­lowed thread

Aryeh Englander7 Jun 2022 5:47 UTC
226 points
526 comments4 min readLW link

[Link] New Stan­ford En­cy­clo­pe­dia of Philos­o­phy ar­ti­cle, “Nor­ma­tive The­o­ries of Ra­tional Choice: Ri­vals to Ex­pected Utility”

Aryeh Englander16 May 2022 19:33 UTC
10 points
0 comments1 min readLW link

Slides: Po­ten­tial Risks From Ad­vanced AI

Aryeh Englander28 Apr 2022 2:15 UTC
7 points
0 comments1 min readLW link

[Question] What to in­clude in a guest lec­ture on ex­is­ten­tial risks from AI?

Aryeh Englander13 Apr 2022 17:03 UTC
20 points
9 comments1 min readLW link