AI ALIGNMENT FORUMTags
AF

AI Success Models

EditHistorySubscribe
Discussion (0)
Help improve this page
EditHistorySubscribe
Discussion (0)
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
Most Relevant
0
27Solving the whole AGI control problem, version 0.0001
Steve Byrnes
2y
2
0
67An overview of 11 proposals for building safe advanced AI
Evan Hubinger
3y
25
0
42A positive case for how we might succeed at prosaic AI alignment
Evan Hubinger
1y
25
2
20Interpretability’s Alignment-Solving Potential: Analysis of 7 Scenarios
Evan R. Murphy
9mo
0
1
21Conditioning Generative Models for Alignment
Arun Jose
6mo
8
1
13An Open Agency Architecture for Safe Transformative AI
davidad (David A. Dalrymple)
1mo
17
0
45AI Safety "Success Stories"
Wei Dai
3y
11
0
16Towards Hodge-podge Alignment
Cleo Nardo
1mo
3
0
15Acceptability Verification: A Research Agenda
David Udell, Evan Hubinger
7mo
0
1
12AI Safety Endgame Stories
Ivan Vendrov
4mo
0
1
4Introduction to the sequence: Interpretability Research for the Most Important Century
Evan R. Murphy
9mo
0
0
5Making it harder for an AGI to "trick" us, with STVs
Tor Økland Barstad
7mo
0
0
4Getting from an unaligned AGI to an aligned AGI?
Tor Økland Barstad
7mo
0
1
4Alignment with argument-networks and assessment-predictions
Tor Økland Barstad
2mo
0
Add Posts