Rowan Wang is interested in AI safety, interpretability and climbing trees and is currently on leave from Harvard working at Anthropic.
How media typically covers Rowan Wang
Research or work cited
Petri is an open-source alignment auditing agent that enables researchers to test AI safety hypotheses in minutes rather than weeks by autonomously crafting environments and running multi-turn audits against target models.
“Co-author of the Petri paper on alignment auditing agents”