Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
Adam Scherlis
Karma:
934
All
Posts
Comments
New
Top
Old
What can we learn about childrearing from J. S. Mill?
Adam Scherlis
2 Apr 2024 6:06 UTC
9
points
1
comment
1
min read
LW
link
Two Percolation Puzzles
Adam Scherlis
4 Jul 2023 5:34 UTC
43
points
14
comments
1
min read
LW
link
(adam.scherlis.com)
GPT-175bee
Adam Scherlis
and
LawrenceC
8 Feb 2023 18:58 UTC
121
points
14
comments
1
min read
LW
link
How to export Android Chrome tabs to an HTML file in Linux (as of February 2023)
Adam Scherlis
2 Feb 2023 2:03 UTC
7
points
3
comments
2
min read
LW
link
(adam.scherlis.com)
Inner Misalignment in “Simulator” LLMs
Adam Scherlis
31 Jan 2023 8:33 UTC
84
points
12
comments
4
min read
LW
link
Fun math facts about 2023
Adam Scherlis
1 Jan 2023 23:38 UTC
9
points
6
comments
1
min read
LW
link
A hundredth of a bit of extra entropy
Adam Scherlis
24 Dec 2022 21:12 UTC
84
points
4
comments
3
min read
LW
link
An exploration of GPT-2′s embedding weights
Adam Scherlis
13 Dec 2022 0:46 UTC
42
points
4
comments
10
min read
LW
link
A brainteaser for language models
Adam Scherlis
12 Dec 2022 2:43 UTC
47
points
3
comments
2
min read
LW
link
Adam Scherlis’s Shortform
Adam Scherlis
9 Dec 2022 0:11 UTC
4
points
16
comments
1
min read
LW
link
New Frontiers in Mojibake
Adam Scherlis
26 Nov 2022 2:37 UTC
60
points
7
comments
6
min read
LW
link
1
review
(adam.scherlis.com)
Cryptic symbols
Adam Scherlis
28 Oct 2022 6:44 UTC
6
points
17
comments
1
min read
LW
link
(adam.scherlis.com)
Five views of Bayes’ Theorem
Adam Scherlis
2 Jul 2022 2:25 UTC
38
points
4
comments
1
min read
LW
link
One is (almost) normal in base π
Adam Scherlis
1 Jul 2022 4:05 UTC
14
points
0
comments
1
min read
LW
link
(adam.scherlis.com)
Understanding the two-head strategy for teaching ML to answer questions honestly
Adam Scherlis
11 Jan 2022 23:24 UTC
29
points
1
comment
10
min read
LW
link
Fun with bitstrings and bijections
Adam Scherlis
2 Jan 2022 5:07 UTC
6
points
0
comments
1
min read
LW
link
(adam.scherlis.com)
Gradient Hacking via Schelling Goals
Adam Scherlis
28 Dec 2021 20:38 UTC
33
points
4
comments
4
min read
LW
link
A Generalization of ROC AUC for Binary Classifiers
Adam Scherlis
4 Dec 2021 21:47 UTC
10
points
0
comments
2
min read
LW
link
(adam.scherlis.com)
What’s the weirdest way to win this game?
Adam Scherlis
21 Nov 2021 5:18 UTC
9
points
5
comments
1
min read
LW
link
(adam.scherlis.com)
Back to top