This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
Wikitags
AF
Login
Bucket Errors
Settings
Applied to
Romance, misunderstanding, social stances, and the human LLM
by
Kaj Sotala
2y
ago
Applied to
Paper: Superposition, Memorization, and Double Descent (Anthropic)
by
Lauren (often wrong)
2y
ago
Applied to
[Interim research report] Taking features out of superposition with sparse autoencoders
by
Lauren (often wrong)
2y
ago
Applied to
Bucket Errors
by
Multicore
3y
ago
Applied to
Buckets & Bayes
by
Multicore
3y
ago
Applied to
Buckets and memetic immune disorders
by
Tyrrell_McAllister
3y
ago
Ozzie Gooen
v1.5.0
Aug 17th 2021 GMT
(+193)
LW
5
Yoav Ravid
v1.4.0
Jan 20th 2021 GMT
(+48)
LW
2
Applied to
Fusion and Equivocation in Korzybski's General Semantics
by
Abram Demski
4y
ago
Applied to
Emotions are not beliefs
by
Multicore
5y
ago
Applied to
CFAR Participant Handbook now available to all
by
Jérémy Perret
5y
ago
Applied to
Fallacies of Compression
by
Multicore
5y
ago
Applied to
Defending points you don't care about
by
Multicore
5y
ago
Applied to
Your Prioritization is Underspecified
by
romeostevensit
5y
ago
Applied to
Intentional Bucket Errors
by
Jim Babcock
5y
ago
Created by
Jim Babcock
at
5y
Ruben Bloom
v1.3.0
Apr 17th 2020 GMT
LW
2
Ruben Bloom
v1.2.0
Apr 16th 2020 GMT
(
+515
/
-141
)
LW
2
Ruben Bloom
v1.1.0
Apr 16th 2020 GMT
(+368)
LW
2