This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
Tags
AF
Login
Oracle AI
•
Applied to
The Binding of Isaac & Transparent Newcomb's Problem
by
suvjectibity
6mo
ago
•
Applied to
Gaia Network: An Illustrated Primer
by
Rafael Kaufmann Nedal
7mo
ago
•
Applied to
Annotated reply to Bengio's "AI Scientists: Safe and Useful AI?"
by
Roman Leventov
1y
ago
•
Applied to
Where Free Will and Determinism Meet
by
David Bravo
1y
ago
•
Applied to
How to safely use an optimizer
by
Simon Fischer
1y
ago
•
Applied to
The algorithm isn't doing X, it's just doing Y.
by
Cleo Nardo
1y
ago
•
Applied to
A multi-disciplinary view on AI safety research
by
Roman Leventov
2y
ago
•
Applied to
What is the risk of asking a counterfactual oracle a question that already had its answer erased?
by
Chris_Leong
2y
ago
•
Applied to
Underspecification of Oracle AI
by
Evan R. Murphy
2y
ago
•
Applied to
Stop-gradients lead to fixed point predictions
by
Johannes Treutlein
2y
ago
•
Applied to
Oracle AGI - How can it escape, other than security issues? (Steganography?)
by
RationalSieve
2y
ago
•
Applied to
Proper scoring rules don’t guarantee predicting fixed points
by
Johannes Treutlein
2y
ago
•
Applied to
Prosaic misalignment from the Solomonoff Predictor
by
Cleo Nardo
2y
ago
•
Applied to
Anthropomorphic AI and Sandboxed Virtual Universes
by
Noosphere89
2y
ago
•
Applied to
Simulators
by
janus
2y
ago
•
Applied to
Strategy For Conditioning Generative Models
by
james.lucassen
2y
ago
•
Applied to
Beliefs and Disagreements about Automating Alignment Research
by
Ian McKenzie
2y
ago
•
Applied to
Training goals for large language models
by
Johannes Treutlein
2y
ago