Anthropic
Corporate • 🇺🇸 United States
Big TechPapers (L12M)
4
Researchers (≈)
12
Papers w/ Code
3
Papers w/ Dataset
0
Topic Overview
Bubble chart placeholder
Recent Papers (see all )
The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models
Code
Computation and Language
Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks
Cryptography and Security
When Models Manipulate Manifolds: The Geometry of a Counting Task
Machine Learning (CS)
Emergent Introspective Awareness in Large Language Models
Computation and Language
Unsupervised decoding of encoded reasoning using language model interpretability
Code
Artificial Intelligence