Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
21 posts
Ought
AI interpretability
Redwood Research
Anthropic
Alignment Research Center
7 posts
Nonlinear Fund
Superintelligence
AI Alignment Forum
Instrumental convergence thesis
Malignant AI failure mode
26
Why mechanistic interpretability does not and cannot contribute to long-term AGI safety (from messages with a friend)
Remmelt
1d
2
19
The limited upside of interpretability
Peter S. Park
1mo
3
36
AMA: Ought
stuhlmueller
4mo
52
41
A Barebones Guide to Mechanistic Interpretability Prerequisites
Neel Nanda
21d
1
113
Apply to the second ML for Alignment Bootcamp (MLAB 2) in Berkeley [Aug 15 - Fri Sept 2]
Buck
7mo
7
72
ARC is hiring alignment theory researchers
Paul_Christiano
1y
3
16
Binary prediction database and tournament
amandango
2y
0
14
Chris Olah on working at top AI labs without an undergrad degree
80000_Hours
1y
0
70
Redwood Research is hiring for several roles
Jack R
1y
0
5
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
5
Andreas Stuhlmüller: Training ML systems to answer open-ended questions
EA Global
2y
1
45
Ought: why it matters and ways to help
Paul_Christiano
3y
5
6
[Link] "Machine Learning Projects for IDA" (Ought)
Milan_Griffes
3y
0
18
Automating reasoning about the future at Ought
jungofthewon
2y
0
9
I there a demo of "You can't fetch the coffee if you're dead"?
Ram Rachum
1mo
3
193
Listen to more EA content with The Nonlinear Library
Kat Woods
1y
89
192
EA needs a hiring agency and Nonlinear will fund you to start one
Kat Woods
11mo
12
12
The Case for Superintelligence Safety As A Cause: A Non-Technical Summary
HunterJay
3y
9
9
[Linkpost] The Problem With The Current State of AGI Definitions
Yitz
6mo
0
71
I’ll pay you a $1,000 bounty for coming up with a good bounty (x-risk related)
Emerson Spartz
1y
48
6
How likely are malign priors over objectives? [aborted WIP]
David Johnston
1mo
0