QuanShu
Sign in
RealmsSuper IntelligenceSafety

Topic

Safety

Alignment, evaluation, governance, and the superintelligence debate.

4 entries in Super Intelligence

A

Safety

Artificial general intelligence

Artificial general intelligence is the contested goal of a system that matches or exceeds human capability across most tasks. There is no agreed definition, no accepted test, and no settled timeline.

A

Safety

AI alignment

AI alignment is the problem of building systems that reliably pursue the goals their designers intend, including systems more capable than the people supervising them.

A

Safety

AI safety

AI safety is the research field and set of engineering practices aimed at preventing AI systems from failing, being misused, or behaving in ways their operators cannot control.

S

Safety

Superintelligence

Superintelligence is a hypothetical form of intelligence far exceeding human performance across cognitive tasks; it exists in argument and forecasting rather than in evidence.