Avoiding Ex Machina: How We Can Ensure Our AI Are Safe

As artificial intelligence improves, machines will soon be equipped with intellectual and practical capabilities that surpass the smartest humans. But not only will machines be more capable than people, they will also be able to make themselves better. That is, these machines will understand their own design and how to improve it – or they could create entirely new machines that are even more capable. The human creators of AIs must be able to trust these machines to remain safe and beneficial even as they self-improve and adapt to the real world. This idea of an autonomous agent making increasingly better modifications to its own code is called recursive self-improvement.