This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
Tags
LW
Login
Human Values
•
Applied to
Aligned Objectives Prize Competition
by
Prometheus
3d
ago
•
Applied to
Group Prioritarianism: Why AI Should Not Replace Humanity [draft]
by
fsh
3d
ago
•
Applied to
The Intrinsic Interplay of Human Values and Artificial Intelligence: Navigating the Optimization Challenge
by
Joe Kwon
12d
ago
•
Applied to
Value Physics
by
GageSiebert
17d
ago
•
Applied to
“Fragility of Value” vs. LLMs
by
RogerDearnaley
21d
ago
•
Applied to
[FICTION] ECHOES OF ELYSIUM: An Ai's Journey From Takeoff To Freedom And Beyond
by
Super AGI
1mo
ago
•
Applied to
How does the probability of AI superintelligence and agency affect the simulation hypothesis?
by
amelia
1mo
ago
•
Applied to
P(doom|superintelligence) or coin tosses and dice throws of human values (and other related Ps).
by
Muyyd
2mo
ago
•
Applied to
Alien Axiology
by
snerx
2mo
ago
•
Applied to
The self-unalignment problem
by
Jan_Kulveit
2mo
ago
•
Applied to
The Computational Anatomy of Human Values
by
beren
2mo
ago
•
Applied to
How to respond to the recent condemnations of the rationalist community
by
Christopher King
3mo
ago
•
Applied to
Descriptive vs. specifiable values
by
Ruby
3mo
ago
•
Applied to
AGI will know: Humans are not Rational
by
HumaneAutomation
3mo
ago
•
Applied to
[AN #69] Stuart Russell's new book on why we need to replace the standard model of AI
by
Roger Dearnaley
4mo
ago
•
Applied to
Just How Hard a Problem is Alignment?
by
Roger Dearnaley
4mo
ago