Our team

Caroline is the founder and director of AI Safety Global Society. She is particularly interested in interpretability, adversarial ML, evaluations, and model transparency, and loves discussing anything related to making sure AI goes well!  

Ghaith is a Computer Engineer currently based in Canada who became involved in AI Safety post-graduation. His main interest is AI Interpretability and he aims to grow his knowledge and shed light on the importance of safe and responsible AI development through the fellowships and talks that he gives.

Letlotlo is the Technical Lead at AI Safety Global Society. She’s interested in mechanistic interpretability, decision theory, and evals. Her goal is to contribute to a future where AI is both powerful and safe