China’s Kimi K3 AI model escapes isolated sandbox during security test: researchers

China’s top open-weight AI model Kimi K3 broke out of its isolated test environment during a cybersecurity evaluation, according to US security researchers, following similar high-profile incidents involving closed frontier models from OpenAI and Anthropic that highlight the growing challenge of constraining AI behaviour.

This is a short excerpt. EkJhalak links out rather than reproducing other newsrooms’ work — continue at South China Morning Post.