LLMpeople
Public Atlas People first, reports as evidence, organizations as context.

Atlas / People / Detail

Shibani Santurkar

Shibani Santurkar is listed as an author of the Anthropic technical report Constitutional Classifiers++: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming.

Researcher affiliated with Anthropic1 organizations1 reports

Profile status: updated

updated 1 public sources
report_author

Current frame

Researcher affiliated with Anthropic

Work

Anthropic Role not listed

Organizations

core Anthropic

Reports

Alignment and Safety Constitutional Classifiers++: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming

Supporting sources

Constitutional Classifiers++: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming Supporting source · report · arXiv