Aashiq Muhamed (CMU AI Safety & Alignment)
ActiveResearch focus
Building technical foundations for navigating a potential intelligence explosion safely and reliably. This includes developing core theoretical science for foundation models and engineered tools to address AGI challenges such as preventing power concentration, enabling verifiable governance, and ensuring robust alignment.
Open to collaboration
Yes
Looking for
Volunteers and independent contributors, specifically those interested in mechanistic interpretability and preference alignment.
Contact
Join the Damaqu community to see this team's full profile.