X.PIN· @thexpin · X·· 2026-09-18AI 评分52
AI 导读
Z.ai 宣布其 GLM-5.3 驱动的 Infra Agent 为 GLM-5.3-Flash 设计、调试并优化了生产推理基础设施，覆盖 100,000+ 中国芯片。不到两周吞吐达到初始基线的 3 倍，硬件效率和单 token 成本据称与主流 Nvidia GPU 相当。团队称之为递归自我改进，即模型改进运行自身的基础设施。
正文 · 原文
http://Z.ai says its GLM-5.3-powered Infra Agent designed, debugged and optimized production inference infrastructure for GLM-5.3-Flash across 100,000+ Chinese chips.
In under two weeks, throughput reached 3× the initial baseline, with hardware efficiency and per-token costs reportedly comparable to mainstream Nvidia GPUs.
The team calls it recursive self-improvement: a model improving the infrastructure that runs it.
来源：X.PIN · x.com