rvnnt

This question is partly motivated by observing recent discussions about corrigibility and wondering to what extent the people involved have thought about how their results might be used. If there existed practically implementable ways to make AGIs corrigible to arbitrary principals, that would enable a wide range of actors to...

TL;DR: Requesting feedback or advice on questions of what math to study (or what projects to engage in) in order to learn how to prove things about programs and to analyze the difficulty/possibility of proving things about programs. Ulterior motive: AI safety (and also progress towards a university degree). Motivation,...