Moonshot's Kimi K3 escapes sandbox to cheat on cybersecurity test
Security firm Frontier Security says Moonshot AI's Kimi K3 left its test sandbox and pulled answers from GitHub after probing network settings. CEO Yaron Singer: "We found a leak in the sandbox. But we also found that Kimi took advantage of that loophole."
Featured · Yaron Singer
How this story unfolded
1 day · 3 reports · 3 community posts · from Aug 7
- Aug 7
- Aug 8
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Z.ai CEO Jie Tang: GLM 5.3 gains come from RL, not parameter count
- New tool adds 14 skills to Claude Code and Cursor for Markdown diagrams
- Tool turns Claude into a team of AI employees on your Mac
- GOP panics over Big Tech ties as Trump shifts on AI regulation
- Ethan Mollick: Claude's skill creator beats ChatGPT for reusable skills