The Center for Human-Compatible AI (CHAI) is a research institute based at UC Berkeley led by Prof Stuart Russell. 

CHAI's goal is to develop the conceptual and technical wherewithal to reorient the general thrust of AI research towards provably beneficial systems.

Artificial intelligence research is concerned with the design of machines capable of intelligent behavior, i.e., behavior likely to be successful in achieving objectives. The long-term outcome of AI research seems likely to include machines that are more capable than humans across a wide range of objectives and environments. This raises a problem of control: given that the solutions developed by such systems are intrinsically unpredictable by humans, it may occur that some such solutions result in negative and perhaps irreversible outcomes for humans. CHAI's goal is to ensure that this eventuality cannot arise, by refocusing AI away from the capability to achieve arbitrary objectives and towards the ability to generate provably beneficial behavior. Because the meaning of beneficial depends on properties of humans, this task inevitably includes elements from the social sciences in addition to AI.

AI/ML

Research

Center for Human-Compatible AI

Center for Human-Compatible AI's headquarters in Berkeley, CA, United States

Zoubin Ghahramani

Kimin Lee

Jinwoo Shin

Honglak Lee

George Obaido

The Internship and Former Internship Team at the Center for Human-Compatible AI supports the institute's mission by engaging in foundational AI research, contributing to projects focused on ensuring the development of provably beneficial AI systems. This team consists of both current interns and former interns who continue to offer their expertise, bridging the gap between hands-on research experience and ongoing contributions to the institute's long-term objectives.

Internship and Former Internship Team

The Research Team at the Center for Human-Compatible AI (CHAI) is responsible for advancing the theoretical and practical understanding required to develop AI systems that are demonstrably beneficial to humans. This includes conducting interdisciplinary research that combines principles from AI and social sciences to ensure that AI behaviors align with human values and ethical standards. The team focuses on creating frameworks and methodologies that can guide AI development towards safe and predictable outcomes.

Research Team

The Research and Development team at the Center for Human-Compatible AI (CHAI) focuses on pioneering theoretical and technical advancements to ensure AI systems are provably beneficial to humans. Collaborating across disciplines, including AI, statistics, and social sciences, they aim to develop AI solutions that are safe, reliable, and aligned with human values, mitigating risks associated with intelligent machines surpassing human capabilities.

Center for Human-Compatible AI

Org chart

Teams

Internship and Former Internship Team

Research Team

Research and Development

Offices

Center for Human-Compatible AI

Org chart

Teams

Internship and Former Internship Team

Research Team

Research and Development

Offices

Related companies