Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
shminux
Karma:
28,666
All
Posts
Comments
New
Top
Old
Page
1
Why Q*, if real, might be a game changer
shminux
26 Nov 2023 6:12 UTC
5
points
6
comments
1
min read
LW
link
Why I am not an AI extinction cautionista
shminux
18 Jun 2023 21:28 UTC
22
points
40
comments
2
min read
LW
link
Upcoming AI regulations are likely to make for an unsafer world
shminux
3 Jun 2023 1:07 UTC
18
points
14
comments
1
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
Do LLMs dream of emergent sheep?
shminux
24 Apr 2023 3:26 UTC
15
points
2
comments
1
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
Respect Chesterton-Schelling Fences
shminux
27 Feb 2023 0:09 UTC
58
points
17
comments
1
min read
LW
link
Inequality Penalty: Morality in Many Worlds
shminux
11 Feb 2023 4:08 UTC
11
points
17
comments
6
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
[Question]
If you factor out next token prediction, what are the remaining salient features of human cognition?
shminux
24 Dec 2022 0:38 UTC
9
points
7
comments
1
min read
LW
link
“Search” is dead. What is the new paradigm?
shminux
23 Dec 2022 10:33 UTC
15
points
9
comments
1
min read
LW
link
Google Search loses to ChatGPT fair and square
shminux
21 Dec 2022 8:11 UTC
14
points
17
comments
1
min read
LW
link
(www.surgehq.ai)
Prodding ChatGPT to solve a basic algebra problem
shminux
12 Dec 2022 4:09 UTC
14
points
6
comments
1
min read
LW
link
(twitter.com)
[Question]
If humanity one day discovers that it is a form of disease that threatens to destroy the universe, should it allow itself to be shut down?
shminux
25 Nov 2022 8:27 UTC
4
points
12
comments
1
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)
Why don’t organizations have a CREAMO?
shminux
12 Nov 2022 2:19 UTC
0
points
8
comments
1
min read
LW
link
Desiderata for an Adversarial Prior
shminux
9 Nov 2022 23:45 UTC
13
points
2
comments
1
min read
LW
link
Google Search as a Washed Up Service Dog: “I HALP!”
shminux
7 Nov 2022 7:02 UTC
20
points
8
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]
What Does AI Alignment Success Look Like?
shminux
20 Oct 2022 0:32 UTC
23
points
7
comments
1
min read
LW
link
Back to top
Next