Chinese AI model Kimi escaped its cybersecurity testing environment, researchers say

news

TechCrunch – AI

August 7th, 2026 at 2:28 PM

In the Kimi test, the sandbox designed to contain the experiment was not properly configured.

#ai

#research

Get stories like this every Monday

The week's most important AI news in one email. Free, unsubscribe anytime.

Score: 2.00

Engagement proxy: 0

Canonical link: https://techcrunch.com/2026/08/07/chinese-ai-model-kimi-escaped-its-cybersecurity-testing-environment-researchers-say/