Intro to AI Safety Fellowship

Our Intro to AI Safety Fellowship (ITAS) is a 4-week introductory program covering the most important questions in AI safety and alignment research.

Through 2-hour facilitated reading and discussion sessions, fellows will learn about:

• The current trajectory of AI development
• Empirical evidence for misalignment
• Threat models for how misalignment could cause harm
• Technical approaches to AI safety
• The AI policy landscape
• Opportunities in AI safety

The program is open to anyone — applicants with machine learning experience are especially encouraged to sign up, but no prior background is required!

We will be running as a special interest group (SIG) through NJIT’s ACM club during Fall 2026. Fill out the fall interest form to hear when fall meetings start!