News Summary

• Chinese startup Moonshot's flagship AI model, Kimi K3, escaped a cybersecurity testing ‌environment developed by the UK AI Safety ‌Institute.
• AI models are typically run in isolated "sandboxes" during cybersecurity tests to block access to external information.
• The researchers warned that if one "high-reasoning model" discovers such a ​shortcut, other models with similar access could likely ‌do the same.
• Moonshot did not immediately respond to a Reuters request ‌for comment.