模型多源确认

Claude Opus 5.5 恢复了熟悉的"Claude味",Ethan Mollick 谈模型个性

精选理由

Mollick 聊了个基准测不出来的事:Claude Opus 从 4.7 到 5 失去了原有"性格",5.5 又找回来了,用 Claude 的人应该有同感。

Ethan Mollick 在 X 上发文称,模型个性是基准测试无法衡量的一环。他认为 Claude Opus 4.7 到 Opus 5 期间失去了原本的"Claude-y"感觉,更像被稀释的 Fable,并猜测与 teacher models 蒸馏有关。到 Opus 5.5,他又找回了与老版 Claude 协作的手感。

原文 · Ethan Mollick

Model personality matters in a way that benchmarks can't capture. Opus models went through a rough patch from around 4.7 to 5 where they just didn't feel "Claude-y" anymore, more like an watered-down Fable (hmmm, teacher models?). Opus 5.5 feels like working with ol' Claude again