Jinesis AI Lab
Active
Research focus
The Jinesis AI Lab focuses on AI safety across multiple domains such as improving adversarial defenses, analyzing interpretability effects of induced vulnerabilities, and evaluating sociopolitical risks within current state-of-the-art LLMs. Additionally, we have a line of multi-agent work focusing on game-theoretic aspects that extend to societies of agents
Join the Damaqu community to see this team's full profile.