MIT AI Safety Fundamentals

I wanted this section to be a place where I can organize my MAIA notes more carefully instead of keeping everything on one long page. Some of these entries are technical summaries, some are concept notes, and some are just my way of understanding the alignment questions more clearly by writing them out.

I am especially interested in how the sequence moves from predicting the trajectory of frontier systems to thinking about control, oversight, and governance. The notes here are meant to stay compact and readable, so each idea can stand on its own while still belonging to the larger map.