That is, getting a superintelligent hacker that finds security vulnerabilities before it gains other capabilities is great. Firstly if it is extremely good, a later misaligned AI would not be able to cause hacking danger
This assumes the “software is either fundamentally secure or insecure” model from a previous post, which no one knows to be true or false
Thanks for this post, I also tend to get totally obsessed with fandom and the periods in which I’m not are quite valuable. Unfortunately/fortunately those periods are only when I’m writing original works