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
27
Distribution Shifts and The Importance of AI Safety
Leon Lang
2mo
2
13
Mesa-optimization for goals defined only within a training environment is dangerous
Rubi J. Hudson
4mo
2
138
Taking the parameters which seem to matter and rotating them until they don't
Garrett Baker
3mo
48
134
Externalized reasoning oversight: a research direction for language model alignment
tamera
4mo
22
82
Neural Tangent Kernel Distillation
Thomas Larsen
2mo
20
81
SERI MATS Program - Winter 2022 Cohort
Ryan Kidd
2mo
12
71
Proper scoring rules don’t guarantee predicting fixed points
Johannes_Treutlein
4d
2
62
Race Along Rashomon Ridge
Stephen Fowler
5mo
15
44
Framing AI Childhoods
David Udell
3mo
8
43
Auditing games for high-level interpretability
Paul Colognese
1mo
1
42
Behaviour Manifolds and the Hessian of the Total Loss - Notes and Criticism
Spencer Becker-Kahn
3mo
4
37
Broad Basins and Data Compression
Jeremy Gillen
4mo
6
36
Why I'm Working On Model Agnostic Interpretability
Jessica Mary
1mo
9
33
Finding Skeletons on Rashomon Ridge
David Udell
4mo
2
29
What Makes an Idea Understandable? On Architecturally and Culturally Natural Ideas.
NickyP
4mo
2
26
Guardian AI (Misaligned systems are all around us.)
Jessica Mary
25d
6