Even if the AI can modify its code, it can’t really do anything that wasn’t entailed by its original programming.
The hard part is predicting everything that was entailed by its initial programing and making sure it’s all safe.
That’s right, history of engineering tells us that “provably safe” and “provably secure” systems fail in unanticipated ways.
The hard part is predicting everything that was entailed by its initial programing and making sure it’s all safe.
That’s right, history of engineering tells us that “provably safe” and “provably secure” systems fail in unanticipated ways.