500AI
← People

Alwin Peng

Source-listed: Potential mentor for the Anthropic Fellows Program; exact employment title not published · Anthropic

  • Language models
  • Efficient ML

Selected work

5
  1. Rapid Response: Mitigating LLM Jailbreaks with a Few ExamplesContributor · 2024
  2. Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red TeamingAuthor · 2025
  3. Cost-Effective Constitutional Classifiers via Representation Re-useContributor · 2025
  4. Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal JailbreaksAuthor · 2026
  5. AI agents find $4.6M in blockchain smart contract exploitsContributor · 2025