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
UnverifiedInstitutions participating in the evaluation of OpenAI models include independent research organizations such as METR and Apollo Research, as well as traditional cybersecurity firms such as Trail of Bits.69% 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)