ENTITY PROFILE / 实体档案
Opus 4.8
GPT‑5.5 and Opus 4.8 were evaluated in the same study on AI model honesty. GPT‑5.5 detects errors in every single case in the study. The Decoder published an article describing Opus 4.8’s high error‐flagging rate. Qwen3.5‑9B was evaluated in the same study on AI model honesty as Opus 4.8.· Graphiti 生成的实体摘要
RELATIONS
4关系CURRENT
4当前有效EVENTS
1相关事件REPORTS
1来源报道暂无可公开的邻近关系
按需展开实体的全部已公开关系，保留探索过的节点与连线。
关系变化
按生效时间- GPT-5.5EVALUATED IN SAME STUDYOpus 4.8
GPT‑5.5 and Opus 4.8 were evaluated in the same study on AI model honesty.
- Opus 4.8PUBLISHED ARTICLE CONCERNINGTHE DECODER
The Decoder published an article describing Opus 4.8’s high error‐flagging rate.
- GPT-5.5DETECTED ERRORS IN EVERY CASEOpus 4.8
GPT‑5.5 detects errors in every single case in the study.
- Qwen3.5-9BEVALUATED IN SAME STUDYOpus 4.8
Qwen3.5‑9B was evaluated in the same study on AI model honesty as Opus 4.8.
关系是 Graphiti 从报道中提取的事实陈述，不是原文引述；失效时间表示后来的报道显示这条关系已不成立。