Hackers Could Make Dangerous AI Safer

A new kind of community is needed to flag dangerous deployments of artificial intelligence, argues a policy forum published today in Science. This global community, consisting of hackers, threat modelers, auditors, and anyone with a keen eye for software vulnerabilities, would stress-test new AI-driven products and…

Read more...



source https://gizmodo.com/secretive-ai-companies-need-to-cooperate-with-good-hack-1848185849

Post a Comment

নবীনতর পূর্বতন