Russell argues that continuing progress in AI capability is inevitable because of economic pressures. Russell asserts that precisely because the timeline for developing human-level or superintelligent AI is highly uncertain, safety research should be begun as soon as possible, as it is also highly uncertain how long it would take to complete such research.
If an AI developed according to the standard model were to become superintelligent, it would likely not fully reflect human values and could be catastrophic to humanity. Such goals may not actually reflect what human designers intend, such as by failing to take into account any human values not included in the goals. Russell begins by asserting that the standard model of AI research, in which the primary definition of success is getting better and better at achieving rigid human-specified goals, is dangerously misguided.
It also proposes an approach to the AI control problem. It asserts that risk to humanity from advanced artificial intelligence (AI) is a serious concern despite the uncertainty surrounding future progress in AI.
Human Compatible: Artificial Intelligence and the Problem of Control is a 2019 non-fiction book by computer scientist Stuart J.
0 kommentar(er)
