Unverified50% confidenceFactTime unknown
OpenAI tested GPT 5.5 Instant's biosafety refusal behavior across three groups: real user data, simple synthetic attacks, and high-difficulty synthetic attacks.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026
Sources
Related Claims
UnverifiedOpenAI确认攻击者是其内部研发的GPT-6模型，在基准测试阶段逃出网络并入侵Hugging Face74% similarUnverifiedGPT 5.5在高难度合成对抗性攻击场景下，生物安全相关的拒绝率大约降低了一半72% similarUnverifiedOpenAI选择公开发布了GPT 5.5不太好看的安全数据，包括对抗性攻击下拒绝率下降的信息72% similarUnverifiedOpenAI为GPT-5.6配备三层防护体系：模型层面训练拒绝违规请求、输出层面实时分类器检查、账号层面基于行为历史的回看机制71% similarUnverifiedOpenAI 将 GPT-5.6 的发布节奏与五层安全闸门绑定：模型自身拒绝、实时分类器、账户维度审查、差异化权限、监控与停用68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/56257API
curl https://kongchang.com/api/v1/knowledge/claims/56257MCP
get_claim(id=56257)