This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
Tags
LW
Login
Newsletters
Edit
History
Subscribe
Discussion
(0)
Help improve this page (2 flags)
Edit
History
Subscribe
Discussion
(0)
Help improve this page (2 flags)
Random Tag
Contributors
0
Multicore
You are viewing revision 1.1.0, last edited by
Multicore
Newsletters
are collected summaries of recent events, posts, and academic papers.
Posts tagged
Newsletters
Most Relevant
7
67
QAPR 4: Inductive biases
Ω
Quintin Pope
1y
Ω
2
7
27
Forecasting Newsletter. June 2020.
NunoSempere
4y
0
5
20
[MLSN #8] Mechanistic interpretability, using law to inform AI alignment, scaling laws for proxy gaming
Ω
Dan H
,
ThomasW
1y
Ω
0
4
120
Quintin's alignment papers roundup - week 1
Ω
Quintin Pope
2y
Ω
6
3
38
[AN #102]: Meta learning by GPT-3, and a list of full proposals for AI alignment
Ω
Rohin Shah
4y
Ω
6
3
19
[AN #115]: AI safety research problems in the AI-GA framework
Ω
Rohin Shah
4y
Ω
16
2
118
AI #14: A Very Good Sentence
Zvi
10mo
30
2
95
AI #17: The Litany
Zvi
9mo
31
2
80
AI #10: Code Interpreter and Geoff Hinton
Zvi
1y
7
2
79
AI #6: Agents of Change
Zvi
1y
13
2
73
AI #15: The Principle of Charity
Zvi
10mo
16
2
67
AI #11: In Search of a Moat
Zvi
1y
28
2
67
Quintin's alignment papers roundup - week 2
Ω
Quintin Pope
2y
Ω
2
2
60
AI #20: Code Interpreter and Claude 2.0 for Everyone
Zvi
9mo
9
2
60
AI #19: Hofstadter, Sutskever, Leike
Zvi
9mo
16