Tag
Kimi's CEO Yang Zhilin advocates avoiding clever architectures and prioritizing scaling, exemplified by Moonshot's MuonClip fix that enabled stable training on 15.5 trillion tokens.
The article points out that one key technology for Kimi defeating US models may originate from founder Yang Zhilin’s doctoral thesis ten years ago, mentioning the connection between XLNet and Kimi K2's trillion-parameter MoE architecture.