This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
Tags
LW
Login
Wireheading
Settings
•
Applied to
Some implications of radical empathy
by
MichaelStJules
20d
ago
•
Applied to
Utilitarianism and the replaceability of desires and attachments
by
MichaelStJules
20d
ago
•
Applied to
Really radical empathy
by
MichaelStJules
24d
ago
•
Applied to
What is "wireheading"?
by
RobertM
1mo
ago
•
Applied to
Clarifying wireheading terminology
by
Sheikh Abdur Raheem Ali
5mo
ago
•
Applied to
Principled Satisficing To Avoid Goodhart
by
JenniferRM
5mo
ago
•
Applied to
Recursion in AI is scary. But let’s talk solutions.
by
Oleg Trott
7mo
ago
•
Applied to
Assessment of AI safety agendas: think about the downside risk
by
Roman Leventov
1y
ago
•
Applied to
Reward Hacking from a Causal Perspective
by
tom4everitt
2y
ago
Diabloto96
v1.7.0
Mar 19th 2023 GMT
1
•
Applied to
Note on algorithms with multiple trained components
by
Steven Byrnes
2y
ago
•
Applied to
Four usages of "loss" in AI
by
TurnTrout
2y
ago
•
Applied to
Towards deconfusing wireheading and reward maximization
by
leogao
2y
ago
•
Applied to
Artificial intelligence wireheading
by
Big Tony
2y
ago
•
Applied to
Reward is not the optimization target
by
TurnTrout
3y
ago
•
Applied to
Reinforcement Learner Wireheading
by
Nate Showell
3y
ago
•
Applied to
Value extrapolation vs Wireheading
by
Ruby
3y
ago