AI ALIGNMENT FORUM
AF

Wikitags

AI Success Models

Edited by plex last updated 17th Nov 2021

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.

Subscribe
1
Subscribe
1
Discussion0
Discussion0
Posts tagged AI Success Models
28Solving the whole AGI control problem, version 0.0001
Steven Byrnes
4y
2
72An overview of 11 proposals for building safe advanced AI
evhub
5y
32
43A positive case for how we might succeed at prosaic AI alignment
evhub
4y
33
23Interpretability’s Alignment-Solving Potential: Analysis of 7 Scenarios
Evan R. Murphy
3y
0
50AI Safety "Success Stories"
Wei Dai
6y
11
46Four visions of Transformative AI success
Steven Byrnes
2y
11
34An Open Agency Architecture for Safe Transformative AI
davidad
3y
18
28Conditioning Generative Models for Alignment
Jozdien
3y
8
26Gradient Descent on the Human Brain
Jozdien, gaspode
1y
0
11How Would an Utopia-Maximizer Look Like?
Thane Ruthenis
2y
9
23Towards Hodge-podge Alignment
Cleo Nardo
3y
3
18AI Safety via Luck
Jozdien
2y
0
18Acceptability Verification: A Research Agenda
David Udell, evhub
3y
0
13AI Safety Endgame Stories
Ivan Vendrov
3y
0
8What success looks like
Marius Hobbhahn, MaxRa, JasperGeh, Yannick_Muehlhaeuser
3y
0
Load More (15/19)
Add Posts