Tl;dr: The AI Safety Student Team (a group of students at Harvard) will be running two 8-week introductory reading groups this summer (in Boston and online), as well as summer socials (in Boston). Apply to our technical fellowship here or our policy fellowship here; express interest in our socials here.

Fellowships

We will host two intro fellowships (reading groups):

• Intro Technical Fellowship: covers topics such as neural network interpretability, learning from human feedback, goal misgeneralization in reinforcement learning agents, and eliciting latent knowledge. Curriculum, application, and FAQ available here. Students with machine learning experience are especially encouraged to apply.
• Intro Policy Fellowship: covers topics such as pace of progress in AI, potential threats from AI misuse and misalignment, AI audits and evaluations, and semiconductor policy. Curriculum, application, and FAQ available here.

Fellowships are primarily open to current or incoming undergraduate/graduate students at Boston universities, including Harvard and MIT. Recent grads and working professionals who will be in Boston during the 2024-25 academic year are also welcome to apply. 

Fellowships will meet weekly in small cohorts with a facilitator experienced in AI safety/policy (either 2 hours in person with dinner, or 1 hour online). 

We encourage you to apply (technical fellowship, policy fellowship) as soon as possible (deadline is Monday, June 10).

Socials

Our socials will be in Boston and are open to students and professionals interested in AI safety. Please fill out this form to get information about our socials!