This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
Tags
AF
Login
Human Values
•
Applied to
How to coordinate despite our biases? - tldr
by
Ryo
7d
ago
•
Applied to
Please Understand
by
Sam Healy
25d
ago
•
Applied to
Antagonistic AI
by
Xybermancer
2mo
ago
•
Applied to
Impossibility of Anthropocentric-Alignment
by
False Name
2mo
ago
•
Applied to
What does davidad want from «boundaries»?
by
Chipmonk
3mo
ago
•
Applied to
Requirements for a Basin of Attraction to Alignment
by
Roger Dearnaley
3mo
ago
•
Applied to
Value learning in the absence of ground truth
by
Joel_Saarinen
3mo
ago
•
Applied to
Alignment has a Basin of Attraction: Beyond the Orthogonality Thesis
by
Roger Dearnaley
3mo
ago
•
Applied to
Ontological Crisis in Humans
by
Wei Dai
3mo
ago
•
Applied to
Shut Up and Divide?
by
Wei Dai
3mo
ago
•
Applied to
If I ran the zoo
by
Optimization Process
4mo
ago
•
Applied to
Trading off Lives
by
Gunnar Zarncke
4mo
ago
•
Applied to
Safety First: safety before full alignment. The deontic sufficiency hypothesis.
by
Chipmonk
4mo
ago
•
Applied to
Agent membranes/boundaries and formalizing “safety”
by
Chipmonk
4mo
ago
•
Applied to
Which values are stable under ontology shifts?
by
Wei Dai
4mo
ago
•
Applied to
5. Moral Value for Sentient Animals? Alas, Not Yet
by
Roger Dearnaley
4mo
ago
•
Applied to
A short dialogue on comparability of values
by
RobertM
4mo
ago
•
Applied to
How Would an Utopia-Maximizer Look Like?
by
Thane Ruthenis
4mo
ago