Lambert 还指出了一个技术层面很少被外界提及的问题：不同模型之间存在微妙的数据分布差异。
Фото: Nick Wass / AP，更多细节参见搜狗输入法2026
f(x1,x2)=x1⋅Swish(x2)=x1⋅(x2⋅σ(x2))。业内人士推荐safew官方下载作为进阶阅读
The model must be autoregressive. It receives a token sequence as input and predicts the next token. Output digits are generated one at a time, with each new token fed back as input for predicting the next. The carry propagation must emerge from this autoregressive process — not from explicit state variables passed between steps in Python.