Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
1014 posts
AI
AI Timelines
Value Learning
AI Takeoff
Embedded Agency
Community
Eliciting Latent Knowledge (ELK)
Reinforcement Learning
Infra-Bayesianism
Counterfactuals
Logic & Mathematics
Interviews
111 posts
Iterated Amplification
Game Theory
Factored Cognition
Humans Consulting HCH
Research Agendas
Ought
Debate (AI safety technique)
Risks of Astronomical Suffering (S-risks)
Center on Long-Term Risk (CLR)
Mechanism Design
Fairness
Group Rationality
79
Towards Hodge-podge Alignment
Cleo Nardo
1d
20
39
The "Minimal Latents" Approach to Natural Abstractions
johnswentworth
22h
6
251
AI alignment is distinct from its near-term applications
paulfchristiano
7d
5
7
Note on algorithms with multiple trained components
Steven Byrnes
7h
1
12
Take 12: RLHF's use is evidence that orgs will jam RL at real-world problems.
Charlie Steiner
19h
0
53
Can we efficiently explain model behaviors?
paulfchristiano
4d
0
85
Trying to disambiguate different questions about whether RLHF is “good”
Buck
6d
39
182
Using GPT-Eliezer against ChatGPT Jailbreaking
Stuart_Armstrong
14d
77
13
Event [Berkeley]: Alignment Collaborator Speed-Meeting
AlexMennen
1d
2
154
Causal Scrubbing: a method for rigorously testing interpretability hypotheses [Redwood Research]
LawrenceC
17d
9
49
Existential AI Safety is NOT separate from near-term applications
scasper
7d
15
29
High-level hopes for AI alignment
HoldenKarnofsky
5d
3
13
Looking for an alignment tutor
JanBrauner
3d
2
129
Mechanistic anomaly detection and ELK
paulfchristiano
25d
17
44
«Boundaries», Part 3b: Alignment problems in terms of boundaries
Andrew_Critch
6d
2
33
My AGI safety research—2022 review, ’23 plans
Steven Byrnes
6d
6
42
Notes on OpenAI’s alignment plan
Alex Flint
12d
5
25
Take 9: No, RLHF/IDA/debate doesn't solve outer alignment.
Charlie Steiner
8d
14
285
On how various plans miss the hard bits of the alignment challenge
So8res
5mo
81
181
Some conceptual alignment research projects
Richard_Ngo
3mo
14
174
Unifying Bargaining Notions (1/2)
Diffractor
4mo
38
16
Theories of impact for Science of Deep Learning
Marius Hobbhahn
19d
0
80
Threat-Resistant Bargaining Megapost: Introducing the ROSE Value
Diffractor
2mo
11
125
«Boundaries», Part 1: a key missing concept from utility theory
Andrew_Critch
4mo
26
63
A Library and Tutorial for Factored Cognition with Language Models
stuhlmueller
2mo
0
84
Unifying Bargaining Notions (2/2)
Diffractor
4mo
11
49
Ought will host a factored cognition “Lab Meeting”
jungofthewon
3mo
1
61
Rant on Problem Factorization for Alignment
johnswentworth
4mo
48