As I am completing my capstone project for AGI Safety Fundamentals 2023, I wanted to link-post my notes for the core readings for the course. I have found it extremely rewarding to summarize key points and point out my topics of confusion in this manner.
I would like to improve on conveying complex topics more concisely, and I would like to make sure that I got most of the points addressed by the authors correctly. Feedback is appreciated!
I noticed that there has been a post dedicated to the 2022 iteration of the AGISF AI Alignment course here: [https://www.lesswrong.com/posts/ZLNgg49AxLtHDj5v5/agisf-2022-summaries], and it is very well-organized.
I hope this is useful to someone out there also, and thanks BlueDot Impact for offering this course!