LESSWRONGTags
LW

AI Success Models

EditHistory
Discussion (1)
Help improve this page
EditHistory
Discussion (1)
Help improve this page
AI Success Models
Random Tag
Contributors
3plex

AI Success Models are proposed paths to an existential win via aligned AI. They are (so far) high level overviews and won't contain all the details, but present at least a sketch of what a full solution might look like. They can be contrasted with threat models, which are stories about how AI might lead to major problems.

Posts tagged AI Success Models
8
63Solving the whole AGI control problem, version 0.0001Ω
Steven Byrnes
2y
Ω
7
5
206An overview of 11 proposals for building safe advanced AIΩ
evhub
3y
Ω
36
5
79A positive case for how we might succeed at prosaic AI alignmentΩ
evhub
2y
Ω
46
4
120Conversation with Eliezer: What do you want the system to do?
Akash
1y
38
4
52Interpretability’s Alignment-Solving Potential: Analysis of 7 ScenariosΩ
Evan R. Murphy
1y
Ω
0
3
53a narrative explanation of the QACI alignment plan
Tamsin Leake
4mo
28
3
7Any further work on AI Safety Success Stories?Q
Krieger
8mo
Q
6
2
115AI Safety "Success Stories"Ω
Wei Dai
4y
Ω
27
2
79Various Alignment Strategies (and how likely they are to work)
Logan Zoellner
1y
34
2
64Success without dignity: a nearcasting story of avoiding catastrophe by luck
HoldenKarnofsky
3mo
8
2
56An Open Agency Architecture for Safe Transformative AIΩ
davidad
6mo
Ω
22
2
53Conditioning Generative Models for AlignmentΩ
Jozdien
1y
Ω
8
2
43formal alignment: what it is, and some proposalsΩ
Tamsin Leake
5mo
Ω
3
1
84Towards Hodge-podge AlignmentΩ
Cleo Nardo
6mo
Ω
29
1
65AI Safety via LuckΩ
Jozdien
2mo
Ω
6
Load More (15/27)
Add Posts