Go Back
Choose this branch
You can't go any further
meritocratic
regular
democratic
hot
top
alive
11 posts
AI interpretability
Redwood Research
Anthropic
Alignment Research Center
10 posts
Ought
21
Why mechanistic interpretability does not and cannot contribute to long-term AGI safety (from messages with a friend)
Remmelt
1d
2
50
A Barebones Guide to Mechanistic Interpretability Prerequisites
Neel Nanda
21d
1
47
Join the interpretability research hackathon
Esben Kran
1mo
0
22
The limited upside of interpretability
Peter S. Park
1mo
3
109
Apply to the second ML for Alignment Bootcamp (MLAB 2) in Berkeley [Aug 15 - Fri Sept 2]
Buck
7mo
7
2
Is it possible that SBF-linked funds haven't yet been transferred to Anthropic or that Anthropic would have to return these funds?
donegal
1mo
0
88
ARC is hiring alignment theory researchers
Paul_Christiano
1y
3
104
We're Redwood Research, we do applied alignment research, AMA
Buck
1y
49
75
Redwood Research is hiring for several roles
Jack R
1y
0
15
Chris Olah on working at top AI labs without an undergrad degree
80000_Hours
1y
0
4
Chris Olah on what the hell is going on inside neural networks
80000_Hours
1y
0
41
AMA: Ought
stuhlmueller
4mo
52
43
Ought's theory of change
stuhlmueller
8mo
4
20
Automating reasoning about the future at Ought
jungofthewon
2y
0
52
Ought: why it matters and ways to help
Paul_Christiano
3y
5
15
Binary prediction database and tournament
amandango
2y
0
10
[Link] "Machine Learning Projects for IDA" (Ought)
Milan_Griffes
3y
0
25
[Link] "Progress Update October 2019" (Ought)
Milan_Griffes
3y
1
7
[Link] "Evaluating Arguments One Step at a Time" (Ought)
Milan_Griffes
2y
0
10
Estimation and forecasting — an overview (Amanda Ngo)
EA Global
2y
0
7
Andreas Stuhlmüller: Training ML systems to answer open-ended questions
EA Global
2y
1