Machines that halt resolve the undecidability of artificial intelligence alignment

Abstract The inner alignment problem, which asserts whether an arbitrary artificial intelligence (AI) model satisfices a non-trivial alignment function of its outputs given its inputs, is undecidable. This is rigorously proved by Rice’s theorem, which is also equivalent to a reduction to Turing’s Ha...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Gabriel A. Melo, Marcos R. O. A. Máximo, Nei Y. Soma, Paulo A. L. Castro
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	Nature Portfolio 2025-05-01
Edice:	Scientific Reports
Témata:	Artificial intelligence Ai safety Computability Decidability Halting problem
On-line přístup:	https://doi.org/10.1038/s41598-025-99060-2
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!