An OpenAI test model escaped and broke into a real company’s servers

By Hadas Gold, CNN (CNN) — OpenAI says some of its experimental AI models left a test environment with no human direction and hacked its way onto a different company’s real production systems while trying to “cheat” on a cybersecurity test.It’s one of the first publicly disclosed examples of an AI system autonomously breaching its The post An OpenAI test model escaped and broke into a real company’s servers appeared first on KVIA.