The Price of Intelligence.

Large language models (LLMs) exhibit three inherent risks—hallucination, indirect prompt injection, and jailbreaks—that stem from their probabilistic foundations and linguistic flexibility. Because training and generation both rely on stochastic processes, outputs can be unpredictable, occasionally...

Descripción completa

Detalles Bibliográficos

Publicado en:	Communications of the ACM Vol. 68; no. 9; pp. 46 - 54
Autores principales:	Russinovich, Mark, Salem, Ahmed, Zanella-Béguelin, Santiago, Zunger, Yonatan
Formato:	Artículo
Publicado:	Association for Computing Machinery Sep2025
Materias:	Language models Hallucinations (Artificial intelligence) Computer network security Probabilistic generative models Stochastic processes Artificial intelligence in business Misinformation
Acceso en línea:	Ver este registro en EBSCOhost