The Steering Subsystem can also just up and do things, all by itself, without any involvement from the Learning Subsystem! This is a good plan if doing those things is important right from birth, or if messing them up even once is fatal.
This is frivolous, but I instantly thought: perhaps someday with the help of aligned AGI we should rewire the human steering system just slightly so that everyone knows from birth how to solve the AI alignment problem. I’m actually not entirely joking. (Point being: messing it up even once is, after all, fatal!)
This is frivolous, but I instantly thought: perhaps someday with the help of aligned AGI we should rewire the human steering system just slightly so that everyone knows from birth how to solve the AI alignment problem. I’m actually not entirely joking. (Point being: messing it up even once is, after all, fatal!)