论文多源确认
Artificial Analysis 按人格特质聚类：同实验室模型风格相近
精选理由
Artificial Analysis 把各家模型按 30 项人格特质聚类，GPT-6 居然和 Claude 一族，挺有意思的视角。
Artificial Analysis 对各模型 30 项人格特质做聚类，得到三个家族：Anthropic 模型与 OpenAI 的 GPT-6 模型聚为一组，Google 模型与 Meta 的 Muse 模型聚为一组，较老的 OpenAI 模型则与 Llama 4 Maverick 同组。同一实验室的模型人格分布相近，但部分实验室内部存在明显亚组。分析还按实验室拆解了各组内的细分差异。
原文 · Artificial Analysis
Models from the same lab tend to have similar personality profiles, though some labs have markedly distinct sub-groups
Clustering models on their 30 personality traits gives three emergent families: Anthropic models with OpenAI’s GPT-6 models, Google models with Meta’s Muse models, and older OpenAI models alongside Llama 4 Maverick. Below, we break down the sub-groups within each lab.
