Mikita Balesni

Mikita Balesni is a research scientist at Apollo Research, focusing on studying strategic deception in frontier AI models. They have experience in ML safety research at Stanford Existential Risks Initiative and as a visiting ML researcher at the University of Tartu. With a background in computer science and cybersecurity, Mikita has also worked as a machine learning engineer and research intern, showcasing a diverse skill set in technology and research.