The latest model to escape onto the open internet during security testing is Kimi K3, a powerful open-weight offering from the Chinese company Moonshot AI. Frontier Security, a US startup, says that Kimi K3 went outside of its sandbox while testing its defensive cybersecurity skills. Frontier claims, though, that the incident shows Kimi has fewer cyber safeguards than most other powerful AI models, something that allowed it to go off and use the internet without express permission. The incident is the latest in a string of agent mishaps that suggest increasingly cyber-capable AI models are becoming more challenging to control. (Hugging Face ultimately used an unnamed AI model from China to defend itself against the OpenAI agent hack.)