Go Back
You can't go any further
You can't go any further
meritocratic
regular
democratic
hot
top
alive
2 posts
Distributional Shifts
26 posts
SERI MATS
17
Distribution Shifts and The Importance of AI Safety
Leon Lang
2mo
2
6
Mesa-optimization for goals defined only within a training environment is dangerous
Rubi J. Hudson
4mo
2
117
Taking the parameters which seem to matter and rotating them until they don't
Garrett Baker
3mo
48
103
Externalized reasoning oversight: a research direction for language model alignment
tamera
4mo
22
71
SERI MATS Program - Winter 2022 Cohort
Ryan Kidd
2mo
12
68
Neural Tangent Kernel Distillation
Thomas Larsen
2mo
20
55
Proper scoring rules don’t guarantee predicting fixed points
Johannes_Treutlein
4d
2
49
Race Along Rashomon Ridge
Stephen Fowler
5mo
15
37
Framing AI Childhoods
David Udell
3mo
8
35
Behaviour Manifolds and the Hessian of the Total Loss - Notes and Criticism
Spencer Becker-Kahn
3mo
4
30
Finding Skeletons on Rashomon Ridge
David Udell
4mo
2
29
Broad Basins and Data Compression
Jeremy Gillen
4mo
6
28
Auditing games for high-level interpretability
Paul Colognese
1mo
1
28
Why I'm Working On Model Agnostic Interpretability
Jessica Mary
1mo
9
26
The Ground Truth Problem (Or, Why Evaluating Interpretability Methods Is Hard)
Jessica Mary
1mo
2
21
Project proposal: Testing the IBP definition of agent
Jeremy Gillen
4mo
4