Our Programs
We provide ways to engage with AI alignment for all levels of experience through fellowships, socials, and speaker events. Plus, we provide free food at every event!
AI Safety Fundamentals
The main way people get involved with Princeton AI Alignment—an 8-week reading group on why AI safety matters and what's being done about it. Covers AI's trajectory, misalignment, technical safety, policy, and careers in the field. Open to anyone, with preference for Princeton undergrad and grad students.
8 weeks, ~2hr/wk
Free food at every session
No prior AI/ML background required
No reading required outside of meetings
Technical Reading Group
Each week, we select a technical paper from the AI alignment literature or related research and meet to individually read and then discuss them. Prior participation in our Fundamentals Fellowship is highly recommended for those without AI safety context. More information coming about the Technical Reading Group soon -- sign up on our mailing list to stay notified.
Retreats and Conferences
We send our members to AI safety retreats across the country, including GCP workshops, AISST/MAIA retreats, and retreats for university group organizers. We also support our members in attending AI safety-related conferences, such as Control Conf, AI Governance DCMC, and EA Globals.
Learning and Career Support
We want to accelerate your engagement with AI safety! If you’re excited to learn more beyond the pace of the fellowship, we’re here to guide you. We’ll keep you informed about internship opportunities like MATS Research, Horizon Policy Fellows, or the Generator Residency. Please don’t hesitate to reach out to us to talk about how we can support your personal growth and your career in the field.