I’d like to add to the list:
-Non-sentient AIs going off reservation.
How far away are we from being able to cobble together a self-replicating system that uses an LLM to perform tasks (scams, probably) in order to fund its own hosting?
-Non-sentient AIs going off reservation.
How far away are we from being able to cobble together a self-replicating system that uses an LLM to perform tasks (scams, probably) in order to fund its own hosting?
Current day solutions revolve around architecture that separate the "Admin Control" from the "code", whether it's the CPU interrupts on OS memory violations up until dockers... making conclusion from looking at the code at hand was not successful even in the very small software scale.
This is probably rooted even deeper in the Halting problem (and the Rice's theorem for "emerging properties") but my explanation will be hand wavy and probably best left for others.