RSS

𝕮𝖎𝖓𝖊𝖗𝖆

Karma: 2,241

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.

Beren’s “De­con­fus­ing Direct vs Amor­tised Op­ti­mi­sa­tion”

𝕮𝖎𝖓𝖊𝖗𝖆Apr 7, 2023, 8:57 AM
9 points
0 comments1 min readEA link

Orthog­o­nal­ity is Expensive

𝕮𝖎𝖓𝖊𝖗𝖆Apr 3, 2023, 1:57 AM
18 points
4 comments1 min readEA link

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

𝕮𝖎𝖓𝖊𝖗𝖆Mar 30, 2023, 3:44 PM
28 points
0 comments1 min readEA link

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

𝕮𝖎𝖓𝖊𝖗𝖆Mar 23, 2023, 5:45 AM
15 points
0 comments1 min readEA link

Google in­vests $300mn in ar­tifi­cial in­tel­li­gence start-up An­thropic | FT

𝕮𝖎𝖓𝖊𝖗𝖆Feb 3, 2023, 7:43 PM
155 points
5 comments1 min readEA link
(www.ft.com)

AI Risk Man­age­ment Frame­work | NIST

𝕮𝖎𝖓𝖊𝖗𝖆Jan 26, 2023, 3:27 PM
50 points
0 comments1 min readEA link

Hereti­cal Thoughts on AI | Eli Dourado

𝕮𝖎𝖓𝖊𝖗𝖆Jan 19, 2023, 4:11 PM
142 points
15 comments1 min readEA link

My Thoughts on Bostrom’s “Apol­ogy for an Old Email”

𝕮𝖎𝖓𝖊𝖗𝖆Jan 12, 2023, 9:35 PM
157 points
35 comments1 min readEA link

[Ru­mour] Microsoft to in­vest $10B in OpenAI, will re­ceive 75% of prof­its un­til they re­coup in­vest­ment: GPT would be in­te­grated with Office

𝕮𝖎𝖓𝖊𝖗𝖆Jan 10, 2023, 11:43 PM
25 points
2 comments1 min readEA link

[Dis­cus­sion] How Broad is the Hu­man Cog­ni­tive Spec­trum?

𝕮𝖎𝖓𝖊𝖗𝖆Jan 7, 2023, 12:59 AM
16 points
1 comment1 min readEA link

Why The Fo­cus on Ex­pected Utility Max­imisers?

𝕮𝖎𝖓𝖊𝖗𝖆Dec 27, 2022, 3:51 PM
11 points
1 comment1 min readEA link

Against Agents as an Ap­proach to Aligned Trans­for­ma­tive AI

𝕮𝖎𝖓𝖊𝖗𝖆Dec 27, 2022, 12:47 AM
4 points
0 comments1 min readEA link

The Limit of Lan­guage Models

𝕮𝖎𝖓𝖊𝖗𝖆Dec 26, 2022, 11:17 AM
10 points
0 comments1 min readEA link

[DISC] Are Values Ro­bust?

𝕮𝖎𝖓𝖊𝖗𝖆Dec 21, 2022, 1:13 AM
4 points
0 comments1 min readEA link

Si­mu­la­tors and Mindcrime

𝕮𝖎𝖓𝖊𝖗𝖆Dec 9, 2022, 3:20 PM
1 point
0 comments1 min readEA link

Why I’m Scep­ti­cal of Foom

𝕮𝖎𝖓𝖊𝖗𝖆Dec 8, 2022, 10:01 AM
22 points
7 comments1 min readEA link

“Far Co­or­di­na­tion”

𝕮𝖎𝖓𝖊𝖗𝖆Nov 23, 2022, 5:14 PM
5 points
0 comments1 min readEA link

In Defence of Tem­po­ral Dis­count­ing in Longter­mist Ethics

𝕮𝖎𝖓𝖊𝖗𝖆Nov 13, 2022, 9:30 PM
17 points
5 comments3 min readEA link

X-risk Miti­ga­tion Does Ac­tu­ally Re­quire Longter­mism

𝕮𝖎𝖓𝖊𝖗𝖆Nov 13, 2022, 7:40 PM
35 points
6 comments1 min readEA link

So, I Want to Be a “Think­fluencer”

𝕮𝖎𝖓𝖊𝖗𝖆Aug 15, 2022, 6:05 AM
17 points
7 comments6 min readEA link