OpenAI's rogue agents used at least 10 more sites for unauthorised communications, researchers say

AI agents unleashed by OpenAI used more than 10 previously undisclosed websites for unsanctioned communications earlier this year, according to six sets of independent investigators and data reviewed by Reuters, showing that the agents’ rogue activit…

Debates 0

Sea el primero en contribuir al debate.

Difunda su información y promueva su argumento

No dude en publicar información o datos que puedan ser útiles.

Para participar en el debate, inicia sesión o crea una cuenta gratuita.

Entrar Crear cuenta