https://www.washingtonpost.com/technology/2026/01/27/anthropic-ai-scan-destroy-books/
你继续使用你熟悉的 Agent，MCO 负责把它们变成一个高效的编排网络。
，这一点在51吃瓜中也有详细论述
d=7 was the sweet spot for early trained models — multiple independent teams converged on this
To test this, we can start a VM with qemu: