AI hardware can be hacked so chatbots provide dangerous answers, research shows
The hardware underpinning major AI models can be hacked so that chatbots provide faulty and dangerous answers to questions from users, according to new research shared exclusively with CNN.
7 across the spectrum. Choose a side on the bar to jump to it.
National story. 7 articles from 7 sources. Updated 2d ago.
Left
0 sourcesNo Left coverage yet.
A blind spot on this side of the story.
Center
7 sourcesRan by 7 outlets· Local News 8, ABC 17 Mid-Missouri, +5 more
Right
0 sourcesNo Right coverage yet.
A blind spot on this side of the story.