Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
tailcalled
Karma:
5,436
All
Posts
Comments
New
Top
Old
Page
1
[Question]
Could there be “natural impact regularization” or “impact regularization by default”?
tailcalled
1 Dec 2023 22:01 UTC
18
points
5
comments
1
min read
LW
link
Utility is not the selection target
tailcalled
4 Nov 2023 22:48 UTC
24
points
1
comment
1
min read
LW
link
Contra Nora Belrose on Orthogonality Thesis Being Trivial
tailcalled
7 Oct 2023 11:47 UTC
8
points
21
comments
1
min read
LW
link
[Question]
What are some good language models to experiment with?
tailcalled
10 Sep 2023 18:31 UTC
16
points
3
comments
1
min read
LW
link
Aumann-agreement is common
tailcalled
26 Aug 2023 20:22 UTC
64
points
31
comments
7
min read
LW
link
A content analysis of the SQ-R questionnaire and a proposal for testing EQ-SQ theory
tailcalled
9 Aug 2023 13:51 UTC
9
points
2
comments
13
min read
LW
link
[Question]
If I showed the EQ-SQ theory’s findings to be due to measurement bias, would anyone change their minds about it?
tailcalled
29 Jul 2023 19:38 UTC
22
points
13
comments
1
min read
LW
link
Autogynephilia discourse is so absurdly bad on all sides
tailcalled
23 Jul 2023 13:12 UTC
41
points
24
comments
2
min read
LW
link
Boundary Placement Rebellion
tailcalled
20 Jul 2023 17:40 UTC
44
points
21
comments
12
min read
LW
link
Prospera-dump
tailcalled
18 Jul 2023 21:36 UTC
10
points
16
comments
1
min read
LW
link
[Question]
Are there any good, easy-to-understand examples of cases where statistical causal network discovery worked well in practice?
tailcalled
12 Jul 2023 22:08 UTC
42
points
6
comments
1
min read
LW
link
I think Michael Bailey’s dismissal of my autogynephilia questions for Scott Alexander and Aella makes very little sense
tailcalled
10 Jul 2023 17:39 UTC
45
points
45
comments
2
min read
LW
link
[Question]
What in your opinion is the biggest open problem in AI alignment?
tailcalled
3 Jul 2023 16:34 UTC
39
points
35
comments
1
min read
LW
link
Which personality traits are real? Stress-testing the lexical hypothesis
tailcalled
21 Jun 2023 19:46 UTC
60
points
4
comments
9
min read
LW
link
Book Review: Autoheterosexuality
tailcalled
12 Jun 2023 20:11 UTC
27
points
9
comments
24
min read
LW
link
[Question]
How accurate is data about past earth temperatures?
tailcalled
9 Jun 2023 21:29 UTC
10
points
2
comments
1
min read
LW
link
[Market] Will AI xrisk seem to be handled seriously by the end of 2026?
tailcalled
25 May 2023 18:51 UTC
15
points
2
comments
1
min read
LW
link
(manifold.markets)
Horizontal vs vertical generality
tailcalled
29 Apr 2023 19:14 UTC
10
points
9
comments
1
min read
LW
link
Core of AI projections from first principles: Attempt 1
tailcalled
11 Apr 2023 17:24 UTC
21
points
3
comments
3
min read
LW
link
[Question]
Is this true? @tyler_m_john: [If we had started using CFCs earlier, we would have ended most life on the planet]
tailcalled
10 Apr 2023 14:22 UTC
73
points
15
comments
1
min read
LW
link
(twitter.com)
Back to top
Next