Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
Noosphere89
Karma:
1,463
All
Posts
Comments
New
Top
Old
Page
1
The problems with the concept of an infohazard as used by the LW community [Linkpost]
Noosphere89
22 Dec 2023 16:13 UTC
75
points
43
comments
3
min read
LW
link
(www.beren.io)
[Question]
What’s the minimal additive constant for Kolmogorov Complexity that a programming language can achieve?
Noosphere89
20 Dec 2023 15:36 UTC
11
points
15
comments
1
min read
LW
link
Arguments for optimism on AI Alignment (I don’t endorse this version, will reupload a new version soon.)
Noosphere89
15 Oct 2023 14:51 UTC
23
points
127
comments
25
min read
LW
link
Hilbert’s Triumph, Church and Turing’s failure, and what it means (Post #2)
Noosphere89
30 Jul 2023 14:33 UTC
−5
points
16
comments
15
min read
LW
link
[Question]
Does decidability of a theory imply completeness of the theory?
Noosphere89
29 Jul 2023 23:53 UTC
6
points
12
comments
1
min read
LW
link
Why you can’t treat decidability and complexity as a constant (Post #1)
Noosphere89
26 Jul 2023 17:54 UTC
6
points
13
comments
5
min read
LW
link
An Opinionated Guide to Computability and Complexity (Post #0)
Noosphere89
24 Jul 2023 17:53 UTC
10
points
10
comments
3
min read
LW
link
[Question]
Conditional on living in a AI safety/alignment by default universe, what are the implications of this assumption being true?
Noosphere89
17 Jul 2023 14:44 UTC
26
points
10
comments
1
min read
LW
link
A potentially high impact differential technological development area
Noosphere89
8 Jun 2023 14:33 UTC
5
points
2
comments
2
min read
LW
link
[Question]
Are computationally complex algorithms expensive to have, expensive to operate, or both?
Noosphere89
2 Jun 2023 17:50 UTC
7
points
5
comments
1
min read
LW
link
[Question]
Does reversible computation let you compute the complexity class PSPACE as efficiently as normal computers compute the complexity class P?
Noosphere89
9 May 2023 13:18 UTC
6
points
14
comments
1
min read
LW
link
[Question]
Are there AI policies that are robustly net-positive even when considering different AI scenarios?
Noosphere89
23 Apr 2023 21:46 UTC
11
points
1
comment
1
min read
LW
link
[Question]
Can we get around Godel’s Incompleteness theorems and Turing undecidable problems via infinite computers?
Noosphere89
17 Apr 2023 15:14 UTC
−11
points
12
comments
1
min read
LW
link
[Question]
Best arguments against the outside view that AGI won’t be a huge deal, thus we survive.
Noosphere89
27 Mar 2023 20:49 UTC
4
points
7
comments
1
min read
LW
link
A case for capabilities work on AI as net positive
Noosphere89
27 Feb 2023 21:12 UTC
10
points
37
comments
1
min read
LW
link
Some thoughts on the cults LW had
Noosphere89
26 Feb 2023 15:46 UTC
−6
points
28
comments
1
min read
LW
link
[Question]
How seriously should we take the hypothesis that LW is just wrong on how AI will impact the 21st century?
Noosphere89
16 Feb 2023 15:25 UTC
56
points
66
comments
1
min read
LW
link
I’ve updated towards AI boxing being surprisingly easy
Noosphere89
25 Dec 2022 15:40 UTC
8
points
20
comments
2
min read
LW
link
A first success story for Outer Alignment: InstructGPT
Noosphere89
8 Nov 2022 22:52 UTC
6
points
1
comment
1
min read
LW
link
(openai.com)
[Question]
Is the Orthogonality Thesis true for humans?
Noosphere89
27 Oct 2022 14:41 UTC
12
points
20
comments
1
min read
LW
link
Back to top
Next