Nathan Lambert· @natolambert · X·· 3 天前AI 评分62
AI 导读
Nathan Lambert 发布的 Kimi K3.1 Pro 基准测试解读显示,该模型在强化学习方面取得了明显进展,其初始版本的轻量后训练已转变为更强的能力,表明中国在模型能力提升上正紧跟前沿。
正文 · 原文
TLDR on the kimi k3.1 pro benchmarks is that it looks like they figured out their RL, where the initial release was a very impressive base model with lighter post-training. China is very much keeping pace with capability gains.
来源:Nathan Lambert · x.com