Dylan Sam
OpenAI
—
Member of Technical Staff
Links
Focus
Scalable Oversight, Control, Monitoring, Interpretability, Adversarial Robustness, Red-Teaming, Alignment Training, Security, Scheming and Deception, Multi-Agent Safety
Stream
OpenAI Safety Team
Dylan is a safety researcher at OpenAI, where he works on curating better/safer training data and monitoring models for harmful behavior.
Before that he completed a PhD in the Machine Learning Department at CMU.