This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
Tags
AF
Login
Natural Abstraction
•
Applied to
[Linkpost] Concept Alignment as a Prerequisite for Value Alignment
by
Bogdan Ionut Cirstea
1mo
ago
•
Applied to
Natural Abstraction: Convergent Preferences Over Information Structures
by
paulom
2mo
ago
•
Applied to
[Linkpost] Generalization in diffusion models arises from geometry-adaptive harmonic representation
by
Bogdan Ionut Cirstea
2mo
ago
•
Applied to
The utility of humans within a Super Artificial Intelligence realm.
by
Marco Monroy
2mo
ago
•
Applied to
The Shadow Archetype in GPT-2XL: Results and Implications for Natural Abstractions
by
Miguel de Guzman
3mo
ago
•
Applied to
An embedding decoder model, trained with a different objective on a different dataset, can decode another model's embeddings surprisingly accurately
by
Logan Zoellner
3mo
ago
•
Applied to
[Linkpost] Large language models converge toward human-like concept organization
by
Bogdan Ionut Cirstea
3mo
ago
•
Applied to
how 2 tell if ur input is out of distribution given only model weights
by
Daniel Kirmani
4mo
ago
•
Applied to
[Linkpost] A shared linguistic space for transmitting our thoughts from brain to brain in natural conversations
by
Bogdan Ionut Cirstea
5mo
ago
•
Applied to
[Linkpost] Rosetta Neurons: Mining the Common Units in a Model Zoo
by
Bogdan Ionut Cirstea
6mo
ago
•
Applied to
[Linkpost] Mapping Brains with Language Models: A Survey
by
Bogdan Ionut Cirstea
6mo
ago
•
Applied to
[Linkpost] Large Language Models Converge on Brain-Like Word Representations
by
Bogdan Ionut Cirstea
6mo
ago
•
Applied to
[Linkpost] Scaling laws for language encoding models in fMRI
by
Bogdan Ionut Cirstea
6mo
ago
•
Applied to
Nature < Nurture for AIs
by
scottviteri
6mo
ago
•
Applied to
Abstraction is Bigger than Natural Abstraction
by
Nicholas Kross
6mo
ago
•
Applied to
$500 Bounty/Prize Problem: Channel Capacity Using "Insensitive" Functions
by
RobertM
7mo
ago
•
Applied to
The Lightcone Theorem: A Better Foundation For Natural Abstraction?
by
Raymond Arnold
7mo
ago
•
Applied to
«Boundaries/Membranes» and AI safety compilation
by
Chipmonk
7mo
ago
•
Applied to
Simulators Increase the Likelihood of Alignment by Default
by
Wuschel Schulz
7mo
ago