Scott Viteri

Scott Viteri is a Computer Science PhD candidate at the Center for Automated Reasoning at Stanford University, working under the guidance of Prof. Clark Barrett.12 His research focuses on producing informative and collaborative language models through reinforcement learning, with the goal of ensuring that wisdom and intelligence develop concurrently in AI systems.1

Currently in the fourth year of his PhD program, Viteri's academic journey has evolved from formal verification and programming languages to AI alignment.1 He believes that robust AI poses a significant existential threat to humanity, which has shaped his research direction.1

Prior to his doctoral studies, Viteri:

• Earned a B.S. in Computer Science and Electrical Engineering from the Massachusetts Institute of Technology in 20181
• Contributed to AI and robotics research during his time at MIT1
• Explored interactive theorem proving at Carnegie Mellon University with Simon Dedeo1
• Published research on the application of abduction in mathematics in the Cognition journal1

At Stanford, Viteri has been involved in various projects related to SMT solving and interactive theorem proving.1 He has also investigated ontology mapping as a technique for targeted neural network interpretability.1

Viteri describes his primary character trait as curiosity and expresses a strong passion for mathematics.1 He is currently applying to teach a graduate-level course on AI alignment at Stanford in the Spring.4

In addition to his academic pursuits, Viteri has professional experience, including a summer internship at Roambotics, where he was described as extremely capable, diligent, and hardworking.3