Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
quetzal_rainbow
Karma:
1,753
All
Posts
Comments
New
Top
Old
[Question]
How do you shut down an escaped model?
quetzal_rainbow
Jun 2, 2024, 7:51 PM
15
points
8
comments
1
min read
LW
link
Training of superintelligence is secretly adversarial
quetzal_rainbow
Feb 7, 2024, 1:38 PM
15
points
2
comments
5
min read
LW
link
There is no sharp boundary between deontology and consequentialism
quetzal_rainbow
Jan 8, 2024, 11:01 AM
8
points
2
comments
1
min read
LW
link
Where Does Adversarial Pressure Come From?
quetzal_rainbow
Dec 14, 2023, 10:31 PM
16
points
1
comment
2
min read
LW
link
Predictable Defect-Cooperate?
quetzal_rainbow
Nov 18, 2023, 3:38 PM
7
points
1
comment
2
min read
LW
link
They are made of repeating patterns
quetzal_rainbow
Nov 13, 2023, 6:17 PM
50
points
4
comments
2
min read
LW
link
[Question]
How to model uncertainty about preferences?
quetzal_rainbow
Mar 24, 2023, 7:04 PM
10
points
2
comments
1
min read
LW
link
[Question]
What literature on the neuroscience of decision making can you recommend?
quetzal_rainbow
Mar 16, 2023, 3:32 PM
3
points
0
comments
1
min read
LW
link
[Question]
What specific thing would you do with AI Alignment Research Assistant GPT?
quetzal_rainbow
Jan 8, 2023, 7:24 PM
45
points
9
comments
1
min read
LW
link
[Question]
Are there any tools to convert LW sequences to PDF or any other file format?
quetzal_rainbow
Dec 7, 2022, 5:28 AM
2
points
2
comments
1
min read
LW
link
quetzal_rainbow’s Shortform
quetzal_rainbow
Nov 20, 2022, 4:00 PM
1
point
103
comments
1
min read
LW
link
Back to top