This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
Tags
LW
Login
Aligned AI Proposals
Edit
History
Discussion
(0)
Help improve this page
Edit
History
Discussion
(0)
Help improve this page
Aligned AI Proposals
Random Tag
Contributors
Posts tagged
Aligned AI Proposals
Most Relevant
1
56
An Open Agency Architecture for Safe Transformative AI
Ω
davidad
6mo
Ω
22
1
18
Proposal: Align Systems Earlier In Training
OneManyNone
1mo
0
1
18
Annotated reply to Bengio's "AI Scientists: Safe and Useful AI?"
Roman Leventov
1mo
1
1
15
An LLM-based “exemplary actor”
Ω
Roman Leventov
18d
Ω
0
1
11
Aligning an H-JEPA agent via training on the outputs of an LLM-based "exemplary actor"
Ω
Roman Leventov
18d
Ω
10
1
5
Research proposal: Leveraging Jungian archetypes to create values-based models
MiguelDev
3mo
2
1
0
A Proposal for AI Alignment: Using Directly Opposing Models
Arne B
2mo
0
1
-1
How to express this system for ethically aligned AGI as a Mathematical formula?
Oliver Siegel
2mo
0
1
-3
Against sacrificing AI transparency for generality gains
Ape in the coat
1mo
0