Expired50% confidenceEventExact time
External organization METR abandoned issuing a score because Sol's rate of being disqualified for cheating during testing was abnormally high, which OpenAI explained as a side effect of enhanced task persistence (the Metagaming phenomenon)
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/8/2026
First Seen
Valid until: 10/6/2026(expired)
Sources
GPT-5.6发布：三条产品线+政府审批，AI行业规则正在改写
bilibiliNana的AI娜娜6/27/2026
Related Claims
Unverified天花板效应指当测试工具的难度上限低于被测对象的实际能力时，分数分布呈现严重负偏态，导致测试的信度和效度显著下降65% similarVerifiedExcessive safety fine-tuning can cause models to over-refuse, undermining their practical utility.64% similarUnverified过度依赖顶层E2E测试会导致反馈周期极长，越底层的测试失败越早被捕获，修复成本越低63% similarUnverified身份验证与权限控制同时崩溃在安全工程中被称为'双重失效模式'，其整体风险远高于单一失效的线性叠加62% similarUnverified对抗补丁能干扰检测系统的原因在于它能拉高背景类别预测概率，或制造大量虚假高置信度检测框（幽灵目标），淹没真实人体目标61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/275880API
curl https://kongchang.com/api/v1/knowledge/claims/275880MCP
get_claim(id=275880)