AI hardware can be hacked so chatbots provide dangerous answers, research shows
· cnn.com · popularity 36/100 · 0 similar stories today · Science & Research Methods (Discovery & Research)
Read the original at cnn.com →
Summary
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 …
Found in: CNN. Rating basis: single outlet; outlet tier 5; 1 feeds; feed position 13.