MacMusic  |  PcMusic  |  440 Software  |  440 Forums  |  440TV  |  Zicos
shutting
Recherche

AI gone rogue: Models may try to stop people from shutting them down, Google warns

mardi 23 septembre 2025, 00:26 , par TheRegister
Misalignment risk? That's an area for future study
Google DeepMind added a new AI threat scenario - one where a model might try to prevent its operators from modifying it or shutting it down - to its AI safety document. It also included a new misuse risk, which it calls 'harmful manipulation.'…
https://go.theregister.com/feed/www.theregister.com/2025/09/22/google_ai_misalignment_risk/

Voir aussi

News copyright owned by their original publishers | Copyright © 2004 - 2025 Zicos / 440Network
Date Actuelle
mar. 23 sept. - 07:47 CEST