RSS

DragonGod

Karma: 2,484

Theoretical Computer Science Msc student at the University of [Redacted] in the United Kingdom.

I’m an aspiring alignment theorist; my research vibes are descriptive formal theories of intelligent systems (and their safety properties) with a bias towards constructive theories.

I think it’s important that our theories of intelligent systems remain rooted in the characteristics of real world intelligent systems; we cannot develop adequate theory from the null string as input.

[Question] Change My Mind: Thirders in “Sleep­ing Beauty” are Just Do­ing Episte­mol­ogy Wrong

DragonGodOct 16, 2024, 10:20 AM
8 points
67 comments6 min readLW link

Con­se­quen­tial­ism is in the Stars not Ourselves

DragonGodApr 24, 2023, 12:02 AM
7 points
19 comments5 min readLW link

[Question] Is “Strong Co­her­ence” Anti-Nat­u­ral?

DragonGodApr 11, 2023, 6:22 AM
23 points
25 comments2 min readLW link

Fea­ture Re­quest: Right Click to Copy LaTeX

DragonGodApr 8, 2023, 11:27 PM
18 points
4 comments1 min readLW link

Beren’s “De­con­fus­ing Direct vs Amor­tised Op­ti­mi­sa­tion”

DragonGodApr 7, 2023, 8:57 AM
52 points
10 comments3 min readLW link

[Question] Is “Re­cur­sive Self-Im­prove­ment” Rele­vant in the Deep Learn­ing Paradigm?

DragonGodApr 6, 2023, 7:13 AM
32 points
36 comments7 min readLW link

Orthog­o­nal­ity is Expensive

DragonGodApr 3, 2023, 12:43 AM
21 points
3 comments1 min readLW link
(www.beren.io)

“Dangers of AI and the End of Hu­man Civ­i­liza­tion” Yud­kowsky on Lex Fridman

DragonGodMar 30, 2023, 3:43 PM
38 points
33 comments1 min readLW link
(www.youtube.com)

Sparks of Ar­tifi­cial Gen­eral In­tel­li­gence: Early ex­per­i­ments with GPT-4 | Microsoft Research

DragonGodMar 23, 2023, 5:45 AM
68 points
23 comments1 min readLW link
(arxiv.org)

Con­tra “Strong Co­her­ence”

DragonGodMar 4, 2023, 8:05 PM
39 points
24 comments1 min readLW link

In­cen­tives and Selec­tion: A Miss­ing Frame From AI Threat Dis­cus­sions?

DragonGodFeb 26, 2023, 1:18 AM
11 points
16 comments2 min readLW link

[Question] Is In­struc­tGPT Fol­low­ing In­struc­tions in Other Lan­guages Sur­pris­ing?

DragonGodFeb 13, 2023, 11:26 PM
39 points
15 comments1 min readLW link

[Question] Do the Safety Prop­er­ties of Pow­er­ful AI Sys­tems Need to be Ad­ver­sar­i­ally Ro­bust? Why?

DragonGodFeb 9, 2023, 1:36 PM
22 points
42 comments2 min readLW link

[About Me] Cin­era’s Home Page

DragonGodFeb 7, 2023, 12:56 PM
30 points
2 comments9 min readLW link

[Question] What Are The Pre­con­di­tions/​Pr­ereq­ui­sites for Asymp­totic Anal­y­sis?

DragonGodFeb 3, 2023, 9:26 PM
8 points
2 comments1 min readLW link

AI Risk Man­age­ment Frame­work | NIST

DragonGodJan 26, 2023, 3:27 PM
36 points
4 comments2 min readLW link
(www.nist.gov)

“Hereti­cal Thoughts on AI” by Eli Dourado

DragonGodJan 19, 2023, 4:11 PM
146 points
38 comments3 min readLW link
(www.elidourado.com)

[Question] How Does the Hu­man Brain Com­pare to Deep Learn­ing on Sam­ple Effi­ciency?

DragonGodJan 15, 2023, 7:49 PM
11 points
6 comments1 min readLW link

Tracr: Com­piled Trans­form­ers as a Lab­o­ra­tory for In­ter­pretabil­ity | Deep­Mind

DragonGodJan 13, 2023, 4:53 PM
62 points
12 comments1 min readLW link
(arxiv.org)

Microsoft Plans to In­vest $10B in OpenAI; $3B In­vested to Date | For­tune

DragonGodJan 12, 2023, 3:55 AM
23 points
10 comments2 min readLW link
(fortune.com)