Joseph Millman
OpenAI
—
Member of Technical Staff (Detections and Response)
Links
Focus
Scalable Oversight, Control, Monitoring, Interpretability, Adversarial Robustness, Red-Teaming, Alignment Training, Security, Scheming and Deception, Multi-Agent Safety
Stream
OpenAI Safety Team
Joseph works in Detections and Response at OpenAI. His public security work includes using large language models to detect malicious macOS activity.