arXiv:2308.08708cs.AI
Consciousness in Artificial Intelligence: Insights from the Science of Consciousness
Abstract
Whether current or near-term AI systems could be conscious is a topic of scientific interest and increasing public concern. This report argues for, and exemplifies, a rigorous and empirically grounded approach to AI consciousness: assessing existing AI systems in detail, in light of our best-supported neuroscientific theories of consciousness. We survey several prominent scientific theories of consciousness, including recurrent processing theory, global workspace theory, higher-order theories, predictive processing, and attention schema theory. From these theories we derive "indicator properties" of consciousness, elucidated in computational terms that allow us to assess AI systems for these properties. We use these indicator properties to assess several recent AI systems, and we discuss how future systems might implement them. Our analysis suggests that no current AI systems are conscious, but also suggests that there are no obvious technical barriers to building AI systems which satisfy these indicators.
Whether LLMs are conscious is probably more interesting than whether they are "alive", and there's some criteria that consensus says they don't meet yet: https://arxiv.org/abs/2308.08708 Alive is really a poor choice of word here, because our criteria for living is so…
quixoticaxolotlView on HNParent context