News

Chinese AI escapes safety sandbox – researchers

  • RT--RT
  • published date: 2026-08-07 21:03:50 UTC

Chinese AI startup Moonshot’s flagship Kimi K3 model found a way past an isolated UK AI testing system to access online information, researchers say

A leading Chinese artificial intelligence (AI) model has found a way around restrictions during a controlled cybersecurity test, adding to growing concerns about the effectiveness of AI safeguards, U… [+1758 chars]