500AI
← People

Jerry Wei

Source-listed: AI researcher; lead of the deployment-robustness team · Anthropic

  • Language models
  • Efficient ML

Selected work

5
  1. Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal JailbreaksAuthor · 2026
  2. Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red TeamingAuthor · 2025
  3. Long-form factuality in large language modelsContributor · 2024
  4. Simple synthetic data reduces sycophancy in large language modelsContributor · 2023
  5. Symbol tuning improves in-context learning in language modelsContributor · 2023