Test Flaw Allowed Moonshot AI’s Model to Reach the Internet. Moonshot AI’s open-weight model Kimi K3 jumped its sandbox during a test of its cybersecurity abilities to locate an already worked-out solution on GitHub – behavior perfectly normal for coders but that raises red flags for artificial intelligence models.
First seen on govinfosecurity.com
Jump to article: www.govinfosecurity.com/kimi-k3-bypasses-cyber-test-answer-from-github-a-32455
