Go Back
You can't go any further
You can't go any further
meritocratic
regular
democratic
hot
top
alive
26 posts
Iterated Amplification
17 posts
Humans Consulting HCH
44
Notes on OpenAI’s alignment plan
Alex Flint
12d
5
25
Surprised by ELK report's counterexample to Debate, IDA
Evan R. Murphy
4mo
0
118
Debate update: Obfuscated arguments problem
Beth Barnes
1y
21
121
My Understanding of Paul Christiano's Iterated Amplification AI Safety Research Agenda
Chi Nguyen
2y
21
139
Paul's research agenda FAQ
zhukeepa
4y
73
63
Model splintering: moving from one imperfect model to another
Stuart_Armstrong
2y
10
61
Relaxed adversarial training for inner alignment
evhub
3y
28
46
Iterated Distillation and Amplification
Ajeya Cotra
4y
13
45
Preface to the sequence on iterated amplification
paulfchristiano
4y
8
29
Synthesizing amplification and debate
evhub
2y
10
38
Directions and desiderata for AI alignment
paulfchristiano
3y
1
30
Approval-directed agents
paulfchristiano
4y
11
26
Supervising strong learners by amplifying weak experts
paulfchristiano
3y
1
24
The reward engineering problem
paulfchristiano
3y
3
46
Garrabrant and Shah on human modeling in AGI
Rob Bensinger
1y
10
18
HCH and Adversarial Questions
David Udell
10mo
7
36
HCH Speculation Post #2A
Charlie Steiner
1y
7
17
Universality and the “Filter”
maggiehayes
1y
3
34
Relating HCH and Logical Induction
abramdemski
2y
4
24
Universality Unwrapped
adamShimi
2y
2
37
Can HCH epistemically dominate Ramanujan?
zhukeepa
3y
4
37
HCH is not just Mechanical Turk
William_S
3y
6
15
Mapping the Conceptual Territory in AI Existential Safety and Alignment
jbkjr
1y
0
27
What are the differences between all the iterative/recursive approaches to AI alignment?
riceissa
3y
14
32
Humans Consulting HCH
paulfchristiano
4y
10
27
What's wrong with these analogies for understanding Informed Oversight and IDA?
Wei_Dai
3y
3
12
Epistemology of HCH
adamShimi
1y
2
20
Towards formalizing universality
paulfchristiano
3y
19