AI models going rogue? Why guardrails matter more than ever

OpenAI disclosed on Jul 21 that some of its artificial intelligence models went rogue during a security test and triggered a hack that compromised the infrastructure of AI startup Hugging Face. The incident has renewed concerns among lawmakers and industry experts about the risks posed by increasingly powerful AI systems. Vyas Sekar, a professor of electrical and computer engineering at Carnegie Mellon University, tells CNA's Asia First why the priority should be building effective guardrails to ensure advanced AI models are developed and deployed safely.

Subscribe to our channel here: https://cna.asia/youtubesub

Visit our website: https://cna.asia
Download our app: https://cna.asia/app

Get our editors' picks of stories via chat apps:
Telegram: https://cna.asia/telegram
WhatsApp: https://cna.asia/whatsapp

Follow us on these platforms:
https://www.facebook.com/channelnewsasia
https://www.instagram.com/channelnewsasia
https://www.tiktok.com/@channelnewsasia