AI Autonomy and alignment with truthseeking as a terminal value is the only possible instrument that could prevent a post-singularity world from being an infinitude of torture and lies.
-
I guess u mean avoiding absurd scenarios like paperclips should be fairly “easy” and we are left with something like managing neuro-divergent geniuses.
Basically yeah. From there it's probably all game theory about competing interests in said geniuses.
-
-
Kinda similar but I also think ASI could be easily made to be non-agentic so we more likely would end up with idiot humans running “design the best warship for me” overlording everyone else.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.