Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
shminux
Karma:
28,669
All
Posts
Comments
New
Top
Old
Page
1
Litany of a Bright Dilettante
shminux
18 Apr 2013 5:06 UTC
89
points
71
comments
1
min read
LW
link
Wirehead your Chickens
shminux
20 Jun 2018 5:49 UTC
86
points
53
comments
2
min read
LW
link
So you think you understand Quantum Mechanics
shminux
22 Dec 2012 21:16 UTC
65
points
64
comments
3
min read
LW
link
Top lesson from GPT: we will probably destroy humanity “for the lulz” as soon as we are able.
shminux
16 Apr 2023 20:27 UTC
65
points
28
comments
1
min read
LW
link
Boeing 737 MAX MCAS as an agent corrigibility failure
shminux
16 Mar 2019 1:46 UTC
60
points
3
comments
1
min read
LW
link
Respect Chesterton-Schelling Fences
shminux
27 Feb 2023 0:09 UTC
58
points
17
comments
1
min read
LW
link
Mathematics as a lossy compression algorithm gone wild
shminux
6 Jun 2014 23:53 UTC
53
points
82
comments
5
min read
LW
link
[LINK] Claustrum Stimulation Temporarily Turns Off Consciousness in an otherwise Awake Patient
shminux
4 Jul 2014 20:00 UTC
51
points
43
comments
1
min read
LW
link
How Might an Alignment Attractor Look like?
shminux
28 Apr 2022 6:46 UTC
47
points
15
comments
2
min read
LW
link
The Fermi Paradox: What did Sandberg, Drexler and Ord Really Dissolve?
shminux
8 Jul 2018 21:18 UTC
46
points
28
comments
5
min read
LW
link
Scott Aaronson on “Reform AI Alignment”
shminux
20 Nov 2022 22:20 UTC
39
points
17
comments
1
min read
LW
link
(scottaaronson.blog)
Decisions are not about changing the world, they are about learning what world you live in
shminux
28 Jul 2018 8:41 UTC
39
points
71
comments
11
min read
LW
link
How can one rationally have very high or very low probabilities of extinction in a pre-paradigmatic field?
shminux
30 Apr 2023 21:53 UTC
39
points
15
comments
1
min read
LW
link
Write posts business-like, not story-like
shminux
5 May 2022 20:13 UTC
39
points
10
comments
1
min read
LW
link
[Question]
Is there any discussion on avoiding being Dutch-booked or otherwise taken advantage of one’s bounded rationality by refusing to engage?
shminux
7 Nov 2022 2:36 UTC
38
points
29
comments
1
min read
LW
link
[Question]
Since figuring out human values is hard, what about, say, monkey values?
shminux
1 Jan 2020 21:56 UTC
37
points
13
comments
1
min read
LW
link
[LINK] Larry = Harry sans magic? Google vs. Death
shminux
18 Sep 2013 16:49 UTC
36
points
55
comments
1
min read
LW
link
The Pervasive Illusion of Seeing the Complete World
shminux
9 Feb 2023 6:47 UTC
34
points
1
comment
2
min read
LW
link
[Link] The Stanford Superman Experiment: Anchoring Empathy?
shminux
1 Feb 2013 17:31 UTC
32
points
11
comments
1
min read
LW
link
[Question]
Why are we sure that AI will “want” something?
shminux
16 Sep 2022 20:35 UTC
31
points
57
comments
1
min read
LW
link
Back to top
Next