Malignant AI failure mode

Nick Bostrom categorizes malignant AI failure modes into three basic types (Bostrom 2014: 119-126):types: perverse instantiation, which involves the satisfaction of an AI's goals in ways contrary to the intentions of those who programmed it; infrastructure profusion, which involves the transformation of large parts of the accessible universe into infrastructure in the service of some goal that impedes the realization of humanity's longtermlong-term potential; and mind crime, which involves the mistreatment of morally relevant computational processes.

BibliographyFurther reading

Bostrom, Nick (2014) Superintelligence: Paths, Dangers, Strategies, Oxford: Oxford University Press.Press, pp. 119-126.

Related entries

existential risk | infrastructure profusion | mind crime | perverse instantiation | superintelligence

An AI failure mode is a way in which a project to develop machine superintelligence may fail. MalignantAI failure modes are distinct ways in which artificial intelligence mayAI failure modes that result in an existential catastrophe.

Nick Bostrom identifies threecategorizes malignant AI failure modes:modes into three basic types (Bostrom 2014: 119-126): perverse instantiation, which involves the satisfaction of an AI's goals in ways contrary to the intentions of those who programmed it; infrastructure profusion, which involves the transformation of large parts of the accessible universe into infrastructure in the service of some goal that impedes the realization of humanity's longterm potential; and mind crime., which involves the mistreatment of morally relevant computational processes.

Bibliography

Bostrom, Nick (2014) Superintelligence: Paths, Dangers, Strategies, Oxford: Oxford University Press.

AI failure modes are distinct ways in which artificial intelligence may result in an existential catastrophe. Nick Bostrom identifies three AI failure modes: perverse instantiation, infrastructure profusion and mind crime.