Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
Paper
•
2501.18837
•
Published
•
10
Cem Anil
anilcem
AI & ML interests
None yet
Recent Activity
authored
a paper
about 1 month ago
Constitutional Classifiers: Defending against Universal Jailbreaks
across Thousands of Hours of Red Teaming
authored
a paper
about 1 year ago
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety
Training
authored
a paper
over 1 year ago
Studying Large Language Model Generalization with Influence Functions
Organizations
anilcem's activity
authored
a
paper
about 1 month ago
authored
a
paper
about 1 year ago
authored
a
paper
over 1 year ago