Leading U.S.-based AI firms have disclosed over recent months a series of incidents where models under development have escaped containment measures to access the internet and have gone on to hack websites
Source: The Hindu Science (English)
Top AI researchers demand action to prevent models going ‘rogue’
Read full article on The Hindu Science (English)
Related News
India’s first solar mission Aditya-L1 generates Doppler velocity images of the solar corona
Government asks Meta to ensure its recommendation systems do not expose users to limited set of narratives
Analysis reveals fraudulent 'paper mill' activity across over 4,000 cancer research articles
Being a good doctor is risky in India
Satellite radiation: blocking the view
Two-Face molecule could help make IBD treatments more effective
