This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
Tags
AF
Login
Academic Papers
Edit Wiki
History
Discussion
Posts either linking to, or summarizing, formal papers published elsewhere.
Posts tagged
Academic Papers
Most Relevant
1
18
Why is pseudo-alignment "worse" than other ways ML can fail to generalize?
Q
nostalgebraist
,
Evan Hubinger
4mo
Q
7
0
47
Some AI research areas and their relevance to existential safety
Andrew Critch
6d
26
0
15
Learning preferences by looking at the world
Rohin Shah
2y
4
0
17
Learning biases and rewards simultaneously
Rohin Shah
1y
3
0
19
Human-AI Collaboration
Rohin Shah
1y
4
0
9
New paper: Corrigibility with Utility Preservation
Koen Holtman
1y
0
0
10
New paper: The Incentives that Shape Behaviour
Ryan Carey
10mo
3
0
5
Implications of Quantum Computing for Artificial Intelligence Alignment Research
Jsevillamol
,
Pablo Antonio Moreno Casares
1y
0