Avoiding Data Leakage in Synthetic Data Projects
Synthetic data offers vast opportunities for machine learning model training without real-world constraints. Yet, beneath this promise lies the risk of…
Read more →Haize Labs, founded in 2023 by Leonard Tang, Steve Li, Richard Zhu, and Alex Gu, builds automated red-teaming (‘haizing’) tools that generate adversarial test cases to surface failure modes in LLMs and AI agents before deployment, working with frontier AI labs on pre-release safety testing.
Text