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

Center-Left: <a href="https://www.engadget.com/2232256/chinese-ai-kimi-k3-also-escaped-containment/" rel="noopener nofollow">Chinese AI model Moonshot Kimi K3 also escaped its testing environment — www.engadget.com
Center-Left: <a href="https://www.wired.com/story/moonshot-kimi-k3-ai-model-escape-sandbox/" rel="noopener nofollow">One of China’s Most Powerful AI Models Has Also Escaped Containment — www.wired.com
Center-Right: <a href="https://www.ft.com/content/9c0d4f0d-d2c6-4189-b4bb-200d17a4720f?syn-25a6b1a6=1" rel="noopener nofollow">Moonshot shake-up seeks to win Beijing nod for stock market debut — www.ft.com
Center-Right: <a href="https://www.cnbc.com/2026/08/07/china-us-ai-race-hugging-face-models.html" rel="noopener nofollow">China is gaining ground in AI. But the U.S. still has a major advantage — www.cnbc.com
Right: <a href="https://www.theblaze.com/tech/trump-writes-new-rules-to-stop-rogue-ai-but-they-re-classified" rel="noopener nofollow">Trump writes new rules to stop rogue AI — but they&#39;re classified — www.theblaze.com
Right: <a href="https://www.theblaze.com/tech/trump-bans-chinese-robots-but-your-robot-vacuum-may-be-spying-on-you-already" rel="noopener nofollow">Trump bans Chinese robots — but your robot vacuum may be spying on you already — www.theblaze.com

Source: techcrunch.com · Section: business-tech · Bias: Center · Published: Fri, 07 Aug 2026 14:28:31 GMT

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