Our Mission
We seek to advance the understanding and development of interpretable and aligned artificial intelligence systems. We are dedicated to addressing the long-term risks and potential harms associated with AI, as we approach the possibility of artificial general intelligence (AGI). Recognizing the profound uniqueness of human intelligence and the existential risks posed by unchecked AI advancement, we commit ourselves to ensuring that AI technologies align with human values and contribute positively to society.
Get Involved
Upcoming Events
Intro Fellowship
An eight week fellowship covering hallmark papers and key AI Safety concepts.
Thursdays
6:00 PM - 8:30 PM
Alignment Research Incubator
Hands-on technical AI alignment research for students who have completed the Intro Fellowship.
Mondays
5:00 PM - 6:30 PM
General Meeting
Our general meeting for all members, 1st and 3rd Tuesdays of the month.
Tuesdays
5:00 PM - 7:00 PM
Coworking Sessions
Collaborative work on AI safety projects, 2nd and 4th Tuesdays of the month
Tuesdays
5:00 PM - 7:00 PM