AI capability control
HYPOTHETICAL ISOLATED COMPUTER HARDWARE SYSTEM WHERE A POSSIBLY DANGEROUS ARTIFICIAL INTELLIGENCE IS KEPT CONSTRAINED IN A VIRTUAL PRISON AND NOT ALLOWED TO MANIPULATE EVENTS IN THE EXTERNAL WORLD
Artificial intelligence box; A.I. box; AI box experiment; AI-box experiment; AI boxing; AI box
In the field of artificial intelligence (AI) design, AI capability control proposals, also referred to more restrictively as AI confinement, aim to increase our ability to monitor and control the behavior of AI systems, including proposed artificial general intelligences (AGIs), in order to reduce the danger they might pose if misaligned. However, capability control becomes less effective as agents become more intelligent and their ability to exploit flaws in human control systems increases, potentially resulting in an existential risk from AGI.