LESSWRONGTags
LW

Aligned AI Proposals

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