Backed by Y Combinator
STRESS TESTING ENTERPRISE & FOUNDATIONAL AI MODELS TO FIND FAILURE MODES.
We provide a repository of stress testing, jailbreaking, and red teaming methods—a knowledge base to understand and improve the performance and safety of AI models.
Featured Blogs
2025-03-21
The Jailbreak Cookbook
We have created a comprehensive overview of the most influential LLM jailbreaking methods.
2025-02-19
Generating Diverse Test Cases with Diversity Transfer from LegalBench
TLDR: we utilized LegalBench as a diversity source to enhance the diversity of our generation of red teaming questions. We show that diversity transfer from a domain-specific knowledge base is a simple and practical way to build a solid red teaming benchmark.
2025-01-23
Red Teaming GPT-4o: Uncovering Hallucinations in Legal AI Models
In this work we explore automated red teaming, applied to GPT-4o in the legal domain. Using a Llama3 8B model as an attacker, we generate more than 50,000 adversarial questions that cause GPT-4o to hallucinate responses in over 35% of cases.