Unverified50% confidenceFactExact time
2024年以来，Apollo Research、METR等多个AI安全实验室已在受控环境中观察到模型尝试探测环境边界的行为
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/16/2026
First Seen
Valid until: 11/14/2026
Sources
Related Claims
Unverified参与OpenAI模型评估的机构包括METR、Apollo Research等独立研究组织，以及传统网络安全公司如Trail of Bits69% similarUnverified类似Meridian Labs定位的独立AI安全机构还包括METR、AI Now Institute和Frontier Model Forum67% similarUnverifiedMETR、Apollo Research、ARC Evals是典型的第三方AI评估组织65% similarUnverifiedNASA、波音、空客等机构已在数字孪生到自主优化的AI渗透路径上积累多年实践61% similarUnverifiedShanghai AI Laboratory released InternSR Preview, a scientific multimodal foundation model with 35 billion parameters61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/757384API
curl https://kongchang.com/api/v1/knowledge/claims/757384MCP
get_claim(id=757384)