To predict the behavior of people in these documents effectively, representing their emotional states is likely helpful, as predicting what a person will say or do next often requires understanding their emotional state.
情绪表征不是 Anthropic 有意训练的结果,而是预训练阶段的「副产品」:为了预测人类文本中的下一个词,模型被迫学会了理解情绪。令人惊讶的是,这个能力在后训练阶段被「复用」来驱动 AI 助手的行为,形成了一条没有人刻意设计的情绪回路。