niuz

Tap one to read its news. Starred ones come first in the row.

AI hardware can be hacked so chatbots provide dangerous answers, research shows

1 source

6h agonow

One source
What the source said
Egypt Independent
“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. The researchers were able to subvert answers to sensitive national security and personal health questions. In one instance, they were able to vastly increase the probability … The post AI hardware can be hacked so chatbots provide dangerous answers, research shows appeared first on Egypt Independent .

Read at Egypt Independent
Is this point wrong? Tell us

Reported by one source so far. It is confirmed when a second, independent source reports the same thing.

Top world stories now

How recent

The shading behind a date drains as it ages: full when new, three quarters at 1 hour, half at 6 hours, a quarter at 12 hours, empty after a day. The date is when the source published it.

Timeline

The line under a story shows when it was reported. Now is at the end. The shaded part runs from its first article to its latest; each mark is an article, taller where several came out within 15 minutes. In lists the line is the last two days, so stories compare; a faded start means the story began earlier. On a story page it runs from the first article to now.