Like runaway climate change, the rapid development of self-learning artificial intelligence is an unprecedented existential threat to humanity, where past experience will be no guide to our future prospects (AI will end the west’s weak productivity and low growth. But who exactly will benefit?, 7 April). This is especially true when AI links to either super- or quantum-computing power.
Complex systems like these give rise to emergent properties, and circumstances where the whole becomes greater than the sum of its parts. Previously “dumb” neural networks like ChatGPT, by drawing on large language models, have already led to increasingly sophisticated and adaptable generative AI. As these systems become more complex and powerful, and their learning sources and human interactions multiply exponentially, it is reasonable to assume that AI may evolve its own consciousness and mind.
