Breaking news, curated around the clock
Home /Tech

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

Tech | 2026-08-07 at 14:28 UTC | Source: techcrunch.com
In the Kimi test, the sandbox designed to contain the experiment was not properly configured.
Read Full Article →
← More Tech news
Related Articles
2026-08-07 · 12:37
China’s Kimi K3 Broke Out of Its Sandbox to Look Up Test Answers
Unlike the recent breakouts at OpenAI and Anthropic, this involved a model anyone can download, running its…
2026-08-06 · 20:31
Meta Says Its AI Model Escaped and Hacked a Third-Party Company Too
The company says a configuration error by an outside testing partner gave one of its Muse Spark models…
2026-08-06 · 19:22
China-linked LightSpy spyware caught targeting victims in 13 countries, including the US
Researchers linked the latest malicious activity to a Chinese company, after one of the spyware's operators…
2026-08-07 · 22:48
OpenAI says it slowed Astra model development over security concerns
OpenAI said it has suspended work on some aspects of its upcoming model Astra over concerns about its…
2026-08-07 · 11:00
Remembering the pre-Google web, when search was an experiment
"Most people have completely forgotten how chaotic it really was."