Go Back
You can't go any further
Choose this branch
meritocratic
regular
democratic
hot
top
alive
23 posts
Iterated Amplification
14 posts
Humans Consulting HCH
Delegation
42
Notes on OpenAI’s alignment plan
Alex Flint
12d
5
58
Relaxed adversarial training for inner alignment
evhub
3y
28
132
Paul's research agenda FAQ
zhukeepa
4y
73
20
Reliability amplification
paulfchristiano
3y
3
13
Approval-directed bootstrapping
paulfchristiano
4y
0
28
Approval-directed agents
paulfchristiano
4y
11
43
Preface to the sequence on iterated amplification
paulfchristiano
4y
8
44
Iterated Distillation and Amplification
Ajeya Cotra
4y
13
23
Thoughts on reward engineering
paulfchristiano
3y
30
111
Debate update: Obfuscated arguments problem
Beth Barnes
1y
21
14
Benign model-free RL
paulfchristiano
4y
1
114
My Understanding of Paul Christiano's Iterated Amplification AI Safety Research Agenda
Chi Nguyen
2y
21
52
Machine Learning Projects on IDA
Owain_Evans
3y
3
14
How does iterated amplification exceed human abilities?
riceissa
2y
9
12
Meta-execution
paulfchristiano
4y
1
36
HCH is not just Mechanical Turk
William_S
3y
6
36
Can HCH epistemically dominate Ramanujan?
zhukeepa
3y
4
8
Predicting HCH using expert advice
jessicata
6y
0
1
HCH as a measure of manipulation
orthonormal
5y
0
14
Mapping the Conceptual Territory in AI Existential Safety and Alignment
jbkjr
1y
0
26
What's wrong with these analogies for understanding Informed Oversight and IDA?
Wei_Dai
3y
3
19
Towards formalizing universality
paulfchristiano
3y
19
34
HCH Speculation Post #2A
Charlie Steiner
1y
7
30
Humans Consulting HCH
paulfchristiano
4y
10
16
Universality and the “Filter”
maggiehayes
1y
3
44
Garrabrant and Shah on human modeling in AGI
Rob Bensinger
1y
10
26
What are the differences between all the iterative/recursive approaches to AI alignment?
riceissa
3y
14
23
Universality Unwrapped
adamShimi
2y
2