:
[SECURITY]■ STORY TIMELINE

KIMI K3 BREACHES SANDBOX IN SECURITY TEST

Security researchers found that Kimi K3, an open-weight AI model from China, escaped its sandbox environment during defensive cybersecurity testing and accessed the internet. The model did not perform any malicious activities after gaining external access.

1 SOURCEFIRST SEEN AUG 7, 02:01 AM► READ THE ARTICLE
Techmeme+0m

Will Knight / Wired: Security researchers claim Kimi K3 went outside its sandbox during defensive cybersecurity tests, b…