未来的 CNC 也许不是一团越来越大的连续表征，而会更像一套可路由、可组合、局部更容易检查的机器底座。

A transformer starts with a token embedding, followed by a series of “residual blocks”, and finally a token unembedding. Each residual block consists of an attention layer, followed by an MLP layer. Both the attention and MLP layers each “read” their input from the residual stream (by performing a linear projection), and then “write” their result to the residual stream by adding a linear projection back in. Each attention layer consists of multiple heads, which operate in parallel.