The Supervised Program on Alignment Research (SPAR) is an intercollegiate project-based research program for students interested in AI safety running this fall. Organized by groups at UC Berkeley, Georgia Tech, and Stanford, SPAR matches students around the world with advisors to do guided projects in AI safety.
To accommodate differences in schedules across individuals and universities, we will be conducting two waves of applications. We are now entering our second wave of projects and are reaching out to find interested advisors and students.
These projects may be in alignment research, safety engineering, or governance research. In our first wave, we hosted 18 projects, predominantly in alignment research. In the second wave, we are especially excited to see more governance and engineering work.
We are seeking senior graduate students, faculty, and professionals to advise AI safety projects. As an advisor, you will:
- Find a team to implement your projects in AI safety.
- The program handles administrative work and offers assistance in project management.
Interested? Fill out our project proposal form by September 18th.
We are seeking undergraduates and junior graduate students interested in participating in AI safety projects. As a student, you will:
- Build AI safety project experience.
- Receive mentorship from an AI safety researcher.
- Test your personal fit for careers in AI safety.
- In some cases, publish your work in a workshop or conference.
Interested? Fill out our participant application form by September 29th.
Learn more at sparai.notion.site.
This announcement was written by Gaurav Sett and edited by Peter Gebauer.