<aside> 💡 Welcome to the BASIS AI Safety Policy Fellowship program! Here, you can find a draft of the syllabus we’ll use throughout the fellowship. Note that this is a draft and subject to change. This curriculum is adopted from Harvard’s AI Student Safety Team and also built from the BASIS leadership team. Note: please constitute the first fellowship meeting as ‘Week 0’ (no reading is required).

</aside>

Week 0: AI Safety, a Brief Introduction

1. AI Safety vs. AI Security: Demystifying the Distinction and Boundaries (Lin et al., 2025)
2. What is AI Safety and Security? (Berger, 2025)

Week 1: Foundations of AI and the Rationale for Safety

1. But what is a neural network? (3Blue1Brown, 2017). Watch first 12.5 min.
2. The AI Triad and what it means for national security strategy (Buchanan, 2020) 21 min.
3. Visualizing the deep learning revolution (Ngo, 2023). 15 min.
4. 4 charts that show why AI progress is unlikely to slow down (Henshall, 2023). 8 min.

Additional readings:

Week 2: Overview of risks from advanced AI systems

1. An overview of catastrophic AI risks (Hendrycks et al., 2023). Read pgs. 2, 6-7, bottom of page 8-11 (Executive summary; § 2.0, 2.1, 2.3, 2.4). 12 mins.
2. Harms from increasingly agentic algorithmic systems (Chan et al., 2023). Read pgs. 2-6 (§ 1 & 2). 10 min.
3. An overview of catastrophic AI risks (Hendrycks et al., 2023). Read pgs. 38–40 (§ 5.3, half of 5.4). 10 min.
4. The alignment problem from a deep learning perspective (Ngo et al., 2022).
5. International Scientific Report on the Safety of Advanced AI (AI Seoul Summit, 2024).